:Author: Randy Dunlap <rdunlap@infradead.org>
:Author: Andrew Murray <amurray@mpc-data.co.uk>
-
Integer types
=============
Raw pointer value SHOULD be printed with %p. The kernel supports
the following extended format specifiers for pointer types:
+Pointer Types
+=============
+
+Pointers printed without a specifier extension (i.e unadorned %p) are
+hashed to give a unique identifier without leaking kernel addresses to user
+space. On 64 bit machines the first 32 bits are zeroed. If you _really_
+want the address see %px below.
+
+::
+
+ %p abcdef12 or 00000000abcdef12
+
Symbols/Function Pointers
=========================
printk("Faulted at %pS\n", (void *)regs->ip);
printk(" %s%pB\n", (reliable ? "" : "? "), (void *)*stack);
-
Kernel Pointers
===============
::
- %pK 0x01234567 or 0x0123456789abcdef
+ %pK 01234567 or 0123456789abcdef
For printing kernel pointers which should be hidden from unprivileged
users. The behaviour of ``%pK`` depends on the ``kptr_restrict sysctl`` - see
Documentation/sysctl/kernel.txt for more details.
+Unmodified Addresses
+====================
+
+::
+
+ %px 01234567 or 0123456789abcdef
+
+For printing pointers when you _really_ want to print the address. Please
+consider whether or not you are leaking sensitive information about the
+Kernel layout in memory before printing pointers with %px. %px is
+functionally equivalent to %lx. %px is preferred to %lx because it is more
+uniquely grep'able. If, in the future, we need to modify the way the Kernel
+handles printing pointers it will be nice to be able to find the call
+sites.
+
Struct Resources
================
value lower than this limit will be ignored and the old configuration will be
retained.
-Note: the value of dirty_bytes also must be set greater than
-dirty_background_bytes or the amount of memory corresponding to
-dirty_background_ratio.
-
==============================================================
dirty_expire_centisecs
The total available memory is not equal to total system memory.
-Note: dirty_ratio must be set greater than dirty_background_ratio or
-ratio corresponding to dirty_background_bytes.
-
==============================================================
dirty_writeback_centisecs
F: Documentation/devicetree/bindings/display/mxsfb-drm.txt
MYRICOM MYRI-10G 10GbE DRIVER (MYRI10GE)
-M: Hyong-Youb Kim <hykim@myri.com>
+M: Chris Lee <christopher.lee@cspi.com>
L: netdev@vger.kernel.org
-W: https://www.myricom.com/support/downloads/myri10ge.html
+W: https://www.cspi.com/ethernet-products/support/downloads/
S: Supported
F: drivers/net/ethernet/myricom/myri10ge/
}
#define __HAVE_ARCH_PTE_SPECIAL
-#define __HAVE_ARCH_PMD_WRITE
#define pmd_write(pmd) (pmd_isclear((pmd), L_PMD_SECT_RDONLY))
#define pmd_dirty(pmd) (pmd_isset((pmd), L_PMD_SECT_DIRTY))
#define pud_page(pud) pmd_page(__pmd(pud_val(pud)))
ifeq ($(CONFIG_ARM64_MODULE_PLTS),y)
KBUILD_LDFLAGS_MODULE += -T $(srctree)/arch/arm64/kernel/module.lds
-ifeq ($(CONFIG_DYNAMIC_FTRACE),y)
-KBUILD_LDFLAGS_MODULE += $(objtree)/arch/arm64/kernel/ftrace-mod.o
-endif
endif
# Default value
*
* See Documentation/cachetlb.txt for more information. Please note that
* the implementation assumes non-aliasing VIPT D-cache and (aliasing)
- * VIPT or ASID-tagged VIVT I-cache.
+ * VIPT I-cache.
*
* flush_cache_mm(mm)
*
struct mod_plt_sec init;
/* for CONFIG_DYNAMIC_FTRACE */
- void *ftrace_trampoline;
+ struct plt_entry *ftrace_trampoline;
};
#endif
#define module_alloc_base ((u64)_etext - MODULES_VSIZE)
#endif
+struct plt_entry {
+ /*
+ * A program that conforms to the AArch64 Procedure Call Standard
+ * (AAPCS64) must assume that a veneer that alters IP0 (x16) and/or
+ * IP1 (x17) may be inserted at any branch instruction that is
+ * exposed to a relocation that supports long branches. Since that
+ * is exactly what we are dealing with here, we are free to use x16
+ * as a scratch register in the PLT veneers.
+ */
+ __le32 mov0; /* movn x16, #0x.... */
+ __le32 mov1; /* movk x16, #0x...., lsl #16 */
+ __le32 mov2; /* movk x16, #0x...., lsl #32 */
+ __le32 br; /* br x16 */
+};
+
+static inline struct plt_entry get_plt_entry(u64 val)
+{
+ /*
+ * MOVK/MOVN/MOVZ opcode:
+ * +--------+------------+--------+-----------+-------------+---------+
+ * | sf[31] | opc[30:29] | 100101 | hw[22:21] | imm16[20:5] | Rd[4:0] |
+ * +--------+------------+--------+-----------+-------------+---------+
+ *
+ * Rd := 0x10 (x16)
+ * hw := 0b00 (no shift), 0b01 (lsl #16), 0b10 (lsl #32)
+ * opc := 0b11 (MOVK), 0b00 (MOVN), 0b10 (MOVZ)
+ * sf := 1 (64-bit variant)
+ */
+ return (struct plt_entry){
+ cpu_to_le32(0x92800010 | (((~val ) & 0xffff)) << 5),
+ cpu_to_le32(0xf2a00010 | ((( val >> 16) & 0xffff)) << 5),
+ cpu_to_le32(0xf2c00010 | ((( val >> 32) & 0xffff)) << 5),
+ cpu_to_le32(0xd61f0200)
+ };
+}
+
+static inline bool plt_entries_equal(const struct plt_entry *a,
+ const struct plt_entry *b)
+{
+ return a->mov0 == b->mov0 &&
+ a->mov1 == b->mov1 &&
+ a->mov2 == b->mov2;
+}
+
#endif /* __ASM_MODULE_H */
#define pmd_thp_or_huge(pmd) (pmd_huge(pmd) || pmd_trans_huge(pmd))
-#define __HAVE_ARCH_PMD_WRITE
#define pmd_write(pmd) pte_write(pmd_pte(pmd))
#define pmd_mkhuge(pmd) (__pmd(pmd_val(pmd) & ~PMD_TABLE_BIT))
ifeq ($(CONFIG_DEBUG_EFI),y)
AFLAGS_head.o += -DVMLINUX_PATH="\"$(realpath $(objtree)/vmlinux)\""
endif
-
-# will be included by each individual module but not by the core kernel itself
-extra-$(CONFIG_DYNAMIC_FTRACE) += ftrace-mod.o
const struct cpu_operations *cpu_ops[NR_CPUS] __ro_after_init;
-static const struct cpu_operations *dt_supported_cpu_ops[] __initconst = {
+static const struct cpu_operations *const dt_supported_cpu_ops[] __initconst = {
&smp_spin_table_ops,
&cpu_psci_ops,
NULL,
};
-static const struct cpu_operations *acpi_supported_cpu_ops[] __initconst = {
+static const struct cpu_operations *const acpi_supported_cpu_ops[] __initconst = {
#ifdef CONFIG_ARM64_ACPI_PARKING_PROTOCOL
&acpi_parking_protocol_ops,
#endif
static const struct cpu_operations * __init cpu_get_ops(const char *name)
{
- const struct cpu_operations **ops;
+ const struct cpu_operations *const *ops;
ops = acpi_disabled ? dt_supported_cpu_ops : acpi_supported_cpu_ops;
local_bh_disable();
- if (system_supports_sve() && test_thread_flag(TIF_SVE)) {
- current->thread.fpsimd_state = *state;
+ current->thread.fpsimd_state = *state;
+ if (system_supports_sve() && test_thread_flag(TIF_SVE))
fpsimd_to_sve(current);
- }
+
task_fpsimd_load();
if (test_and_clear_thread_flag(TIF_FOREIGN_FPSTATE)) {
+++ /dev/null
-/*
- * Copyright (C) 2017 Linaro Ltd <ard.biesheuvel@linaro.org>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#include <linux/linkage.h>
-#include <asm/assembler.h>
-
- .section ".text.ftrace_trampoline", "ax"
- .align 3
-0: .quad 0
-__ftrace_trampoline:
- ldr x16, 0b
- br x16
-ENDPROC(__ftrace_trampoline)
if (offset < -SZ_128M || offset >= SZ_128M) {
#ifdef CONFIG_ARM64_MODULE_PLTS
- unsigned long *trampoline;
+ struct plt_entry trampoline;
struct module *mod;
/*
* is added in the future, but for now, the pr_err() below
* deals with a theoretical issue only.
*/
- trampoline = (unsigned long *)mod->arch.ftrace_trampoline;
- if (trampoline[0] != addr) {
- if (trampoline[0] != 0) {
+ trampoline = get_plt_entry(addr);
+ if (!plt_entries_equal(mod->arch.ftrace_trampoline,
+ &trampoline)) {
+ if (!plt_entries_equal(mod->arch.ftrace_trampoline,
+ &(struct plt_entry){})) {
pr_err("ftrace: far branches to multiple entry points unsupported inside a single module\n");
return -EINVAL;
}
/* point the trampoline to our ftrace entry point */
module_disable_ro(mod);
- trampoline[0] = addr;
+ *mod->arch.ftrace_trampoline = trampoline;
module_enable_ro(mod, true);
/* update trampoline before patching in the branch */
smp_wmb();
}
- addr = (unsigned long)&trampoline[1];
+ addr = (unsigned long)(void *)mod->arch.ftrace_trampoline;
#else /* CONFIG_ARM64_MODULE_PLTS */
return -EINVAL;
#endif /* CONFIG_ARM64_MODULE_PLTS */
#include <linux/module.h>
#include <linux/sort.h>
-struct plt_entry {
- /*
- * A program that conforms to the AArch64 Procedure Call Standard
- * (AAPCS64) must assume that a veneer that alters IP0 (x16) and/or
- * IP1 (x17) may be inserted at any branch instruction that is
- * exposed to a relocation that supports long branches. Since that
- * is exactly what we are dealing with here, we are free to use x16
- * as a scratch register in the PLT veneers.
- */
- __le32 mov0; /* movn x16, #0x.... */
- __le32 mov1; /* movk x16, #0x...., lsl #16 */
- __le32 mov2; /* movk x16, #0x...., lsl #32 */
- __le32 br; /* br x16 */
-};
-
static bool in_init(const struct module *mod, void *loc)
{
return (u64)loc - (u64)mod->init_layout.base < mod->init_layout.size;
int i = pltsec->plt_num_entries;
u64 val = sym->st_value + rela->r_addend;
- /*
- * MOVK/MOVN/MOVZ opcode:
- * +--------+------------+--------+-----------+-------------+---------+
- * | sf[31] | opc[30:29] | 100101 | hw[22:21] | imm16[20:5] | Rd[4:0] |
- * +--------+------------+--------+-----------+-------------+---------+
- *
- * Rd := 0x10 (x16)
- * hw := 0b00 (no shift), 0b01 (lsl #16), 0b10 (lsl #32)
- * opc := 0b11 (MOVK), 0b00 (MOVN), 0b10 (MOVZ)
- * sf := 1 (64-bit variant)
- */
- plt[i] = (struct plt_entry){
- cpu_to_le32(0x92800010 | (((~val ) & 0xffff)) << 5),
- cpu_to_le32(0xf2a00010 | ((( val >> 16) & 0xffff)) << 5),
- cpu_to_le32(0xf2c00010 | ((( val >> 32) & 0xffff)) << 5),
- cpu_to_le32(0xd61f0200)
- };
+ plt[i] = get_plt_entry(val);
/*
* Check if the entry we just created is a duplicate. Given that the
* relocations are sorted, this will be the last entry we allocated.
* (if one exists).
*/
- if (i > 0 &&
- plt[i].mov0 == plt[i - 1].mov0 &&
- plt[i].mov1 == plt[i - 1].mov1 &&
- plt[i].mov2 == plt[i - 1].mov2)
+ if (i > 0 && plt_entries_equal(plt + i, plt + i - 1))
return (u64)&plt[i - 1];
pltsec->plt_num_entries++;
unsigned long core_plts = 0;
unsigned long init_plts = 0;
Elf64_Sym *syms = NULL;
+ Elf_Shdr *tramp = NULL;
int i;
/*
mod->arch.core.plt = sechdrs + i;
else if (!strcmp(secstrings + sechdrs[i].sh_name, ".init.plt"))
mod->arch.init.plt = sechdrs + i;
+ else if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE) &&
+ !strcmp(secstrings + sechdrs[i].sh_name,
+ ".text.ftrace_trampoline"))
+ tramp = sechdrs + i;
else if (sechdrs[i].sh_type == SHT_SYMTAB)
syms = (Elf64_Sym *)sechdrs[i].sh_addr;
}
mod->arch.init.plt_num_entries = 0;
mod->arch.init.plt_max_entries = init_plts;
+ if (tramp) {
+ tramp->sh_type = SHT_NOBITS;
+ tramp->sh_flags = SHF_EXECINSTR | SHF_ALLOC;
+ tramp->sh_addralign = __alignof__(struct plt_entry);
+ tramp->sh_size = sizeof(struct plt_entry);
+ }
+
return 0;
}
SECTIONS {
.plt (NOLOAD) : { BYTE(0) }
.init.plt (NOLOAD) : { BYTE(0) }
+ .text.ftrace_trampoline (NOLOAD) : { BYTE(0) }
}
[C(L1D)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV8_IMPDEF_PERFCTR_L1D_CACHE_RD,
[C(L1D)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV8_IMPDEF_PERFCTR_L1D_CACHE_WR,
-
- [C(NODE)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_RD,
- [C(NODE)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_WR,
-
- [C(NODE)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_RD,
- [C(NODE)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_WR,
};
static const unsigned armv8_thunder_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
set_reserved_asid_bits();
- /*
- * Ensure the generation bump is observed before we xchg the
- * active_asids.
- */
- smp_wmb();
-
for_each_possible_cpu(i) {
asid = atomic64_xchg_relaxed(&per_cpu(active_asids, i), 0);
/*
per_cpu(reserved_asids, i) = asid;
}
- /* Queue a TLB invalidate and flush the I-cache if necessary. */
+ /*
+ * Queue a TLB invalidation for each CPU to perform on next
+ * context-switch
+ */
cpumask_setall(&tlb_flush_pending);
}
asid = atomic64_read(&mm->context.id);
/*
- * The memory ordering here is subtle. We rely on the control
- * dependency between the generation read and the update of
- * active_asids to ensure that we are synchronised with a
- * parallel rollover (i.e. this pairs with the smp_wmb() in
- * flush_context).
+ * The memory ordering here is subtle.
+ * If our ASID matches the current generation, then we update
+ * our active_asids entry with a relaxed xchg. Racing with a
+ * concurrent rollover means that either:
+ *
+ * - We get a zero back from the xchg and end up waiting on the
+ * lock. Taking the lock synchronises with the rollover and so
+ * we are forced to see the updated generation.
+ *
+ * - We get a valid ASID back from the xchg, which means the
+ * relaxed xchg in flush_context will treat us as reserved
+ * because atomic RmWs are totally ordered for a given location.
*/
if (!((asid ^ atomic64_read(&asid_generation)) >> asid_bits)
&& atomic64_xchg_relaxed(&per_cpu(active_asids, cpu), asid))
#include <asm/page.h>
#include <asm/tlbflush.h>
-static struct kmem_cache *pgd_cache;
+static struct kmem_cache *pgd_cache __ro_after_init;
pgd_t *pgd_alloc(struct mm_struct *mm)
{
#include <linux/atomic.h>
#include <linux/mm_types.h>
+#include <linux/sched.h>
#include <asm/bitops.h>
#include <asm/mmu.h>
extern void set_pmd_at(struct mm_struct *mm, unsigned long addr,
pmd_t *pmdp, pmd_t pmd);
-#define __HAVE_ARCH_PMD_WRITE
+#define pmd_write pmd_write
static inline int pmd_write(pmd_t pmd)
{
return !!(pmd_val(pmd) & _PAGE_WRITE);
int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
{
int r = -EINTR;
- sigset_t sigsaved;
- if (vcpu->sigset_active)
- sigprocmask(SIG_SETMASK, &vcpu->sigset, &sigsaved);
+ kvm_sigset_activate(vcpu);
if (vcpu->mmio_needed) {
if (!vcpu->mmio_is_write)
local_irq_enable();
out:
- if (vcpu->sigset_active)
- sigprocmask(SIG_SETMASK, &sigsaved, NULL);
+ kvm_sigset_deactivate(vcpu);
return r;
}
}
#endif /* CONFIG_NUMA_BALANCING */
-#define __HAVE_ARCH_PMD_WRITE
#define pmd_write(pmd) pte_write(pmd_pte(pmd))
#define __pmd_write(pmd) __pte_write(pmd_pte(pmd))
#define pmd_savedwrite(pmd) pte_savedwrite(pmd_pte(pmd))
struct iommu_group *grp);
extern int kvmppc_switch_mmu_to_hpt(struct kvm *kvm);
extern int kvmppc_switch_mmu_to_radix(struct kvm *kvm);
+extern void kvmppc_setup_partition_table(struct kvm *kvm);
extern long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
struct kvm_create_spapr_tce_64 *args);
* NOTE, we rely on r0 being 0 from above.
*/
mtspr SPRN_IAMR,r0
+BEGIN_FTR_SECTION_NESTED(42)
mtspr SPRN_AMOR,r0
+END_FTR_SECTION_NESTED_IFSET(CPU_FTR_HVMODE, 42)
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
/* save regs for local vars on new stack.
*/
int set_thread_tidr(struct task_struct *t)
{
+ int rc;
+
if (!cpu_has_feature(CPU_FTR_ARCH_300))
return -EINVAL;
if (t != current)
return -EINVAL;
- t->thread.tidr = assign_thread_tidr();
- if (t->thread.tidr < 0)
- return t->thread.tidr;
+ if (t->thread.tidr)
+ return 0;
+
+ rc = assign_thread_tidr();
+ if (rc < 0)
+ return rc;
+ t->thread.tidr = rc;
mtspr(SPRN_TIDR, t->thread.tidr);
return 0;
unsigned long vpte, rpte, guest_rpte;
int ret;
struct revmap_entry *rev;
- unsigned long apsize, psize, avpn, pteg, hash;
+ unsigned long apsize, avpn, pteg, hash;
unsigned long new_idx, new_pteg, replace_vpte;
+ int pshift;
hptep = (__be64 *)(old->virt + (idx << 4));
goto out;
rpte = be64_to_cpu(hptep[1]);
- psize = hpte_base_page_size(vpte, rpte);
- avpn = HPTE_V_AVPN_VAL(vpte) & ~((psize - 1) >> 23);
+ pshift = kvmppc_hpte_base_page_shift(vpte, rpte);
+ avpn = HPTE_V_AVPN_VAL(vpte) & ~(((1ul << pshift) - 1) >> 23);
pteg = idx / HPTES_PER_GROUP;
if (vpte & HPTE_V_SECONDARY)
pteg = ~pteg;
offset = (avpn & 0x1f) << 23;
vsid = avpn >> 5;
/* We can find more bits from the pteg value */
- if (psize < (1ULL << 23))
- offset |= ((vsid ^ pteg) & old_hash_mask) * psize;
+ if (pshift < 23)
+ offset |= ((vsid ^ pteg) & old_hash_mask) << pshift;
- hash = vsid ^ (offset / psize);
+ hash = vsid ^ (offset >> pshift);
} else {
unsigned long offset, vsid;
/* We only have 40 - 23 bits of seg_off in avpn */
offset = (avpn & 0x1ffff) << 23;
vsid = avpn >> 17;
- if (psize < (1ULL << 23))
- offset |= ((vsid ^ (vsid << 25) ^ pteg) & old_hash_mask) * psize;
+ if (pshift < 23)
+ offset |= ((vsid ^ (vsid << 25) ^ pteg) & old_hash_mask) << pshift;
- hash = vsid ^ (vsid << 25) ^ (offset / psize);
+ hash = vsid ^ (vsid << 25) ^ (offset >> pshift);
}
new_pteg = hash & new_hash_mask;
ssize_t nb;
long int err, ret;
int mmu_ready;
+ int pshift;
if (!access_ok(VERIFY_READ, buf, count))
return -EFAULT;
err = -EINVAL;
if (!(v & HPTE_V_VALID))
goto out;
+ pshift = kvmppc_hpte_base_page_shift(v, r);
+ if (pshift <= 0)
+ goto out;
lbuf += 2;
nb += HPTE_SIZE;
goto out;
}
if (!mmu_ready && is_vrma_hpte(v)) {
- unsigned long psize = hpte_base_page_size(v, r);
- unsigned long senc = slb_pgsize_encoding(psize);
- unsigned long lpcr;
+ unsigned long senc, lpcr;
+ senc = slb_pgsize_encoding(1ul << pshift);
kvm->arch.vrma_slb_v = senc | SLB_VSID_B_1T |
(VRMA_VSID << SLB_VSID_SHIFT_1T);
- lpcr = senc << (LPCR_VRMASD_SH - 4);
- kvmppc_update_lpcr(kvm, lpcr, LPCR_VRMASD);
+ if (!cpu_has_feature(CPU_FTR_ARCH_300)) {
+ lpcr = senc << (LPCR_VRMASD_SH - 4);
+ kvmppc_update_lpcr(kvm, lpcr,
+ LPCR_VRMASD);
+ } else {
+ kvmppc_setup_partition_table(kvm);
+ }
mmu_ready = 1;
}
++i;
static void kvmppc_end_cede(struct kvm_vcpu *vcpu);
static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu);
-static void kvmppc_setup_partition_table(struct kvm *kvm);
static inline struct kvm_vcpu *next_runnable_thread(struct kvmppc_vcore *vc,
int *ip)
return;
}
-static void kvmppc_setup_partition_table(struct kvm *kvm)
+void kvmppc_setup_partition_table(struct kvm *kvm)
{
unsigned long dw0, dw1;
int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
{
int r;
- sigset_t sigsaved;
if (vcpu->mmio_needed) {
vcpu->mmio_needed = 0;
#endif
}
- if (vcpu->sigset_active)
- sigprocmask(SIG_SETMASK, &vcpu->sigset, &sigsaved);
+ kvm_sigset_activate(vcpu);
if (run->immediate_exit)
r = -EINTR;
else
r = kvmppc_vcpu_run(run, vcpu);
- if (vcpu->sigset_active)
- sigprocmask(SIG_SETMASK, &sigsaved, NULL);
+ kvm_sigset_deactivate(vcpu);
return r;
}
DEFINE_RAW_SPINLOCK(native_tlbie_lock);
-static inline void __tlbie(unsigned long vpn, int psize, int apsize, int ssize)
+static inline unsigned long ___tlbie(unsigned long vpn, int psize,
+ int apsize, int ssize)
{
unsigned long va;
unsigned int penc;
: "memory");
break;
}
- trace_tlbie(0, 0, va, 0, 0, 0, 0);
+ return va;
+}
+
+static inline void __tlbie(unsigned long vpn, int psize, int apsize, int ssize)
+{
+ unsigned long rb;
+
+ rb = ___tlbie(vpn, psize, apsize, ssize);
+ trace_tlbie(0, 0, rb, 0, 0, 0, 0);
}
static inline void __tlbiel(unsigned long vpn, int psize, int apsize, int ssize)
if (hpte_v & HPTE_V_VALID) {
hpte_decode(hptep, slot, &psize, &apsize, &ssize, &vpn);
hptep->v = 0;
- __tlbie(vpn, psize, apsize, ssize);
+ ___tlbie(vpn, psize, apsize, ssize);
}
}
generic-y += scatterlist.h
generic-y += sections.h
generic-y += sembuf.h
+generic-y += serial.h
generic-y += setup.h
generic-y += shmbuf.h
generic-y += shmparam.h
#endif
#if (__SIZEOF_INT__ == 4)
-#define INT __ASM_STR(.word)
-#define SZINT __ASM_STR(4)
-#define LGINT __ASM_STR(2)
+#define RISCV_INT __ASM_STR(.word)
+#define RISCV_SZINT __ASM_STR(4)
+#define RISCV_LGINT __ASM_STR(2)
#else
#error "Unexpected __SIZEOF_INT__"
#endif
#if (__SIZEOF_SHORT__ == 2)
-#define SHORT __ASM_STR(.half)
-#define SZSHORT __ASM_STR(2)
-#define LGSHORT __ASM_STR(1)
+#define RISCV_SHORT __ASM_STR(.half)
+#define RISCV_SZSHORT __ASM_STR(2)
+#define RISCV_LGSHORT __ASM_STR(1)
#else
#error "Unexpected __SIZEOF_SHORT__"
#endif
* have the AQ or RL bits set. These don't return anything, so there's only
* one version to worry about.
*/
-#define ATOMIC_OP(op, asm_op, c_op, I, asm_type, c_type, prefix) \
-static __always_inline void atomic##prefix##_##op(c_type i, atomic##prefix##_t *v) \
-{ \
- __asm__ __volatile__ ( \
- "amo" #asm_op "." #asm_type " zero, %1, %0" \
- : "+A" (v->counter) \
- : "r" (I) \
- : "memory"); \
+#define ATOMIC_OP(op, asm_op, I, asm_type, c_type, prefix) \
+static __always_inline void atomic##prefix##_##op(c_type i, atomic##prefix##_t *v) \
+{ \
+ __asm__ __volatile__ ( \
+ "amo" #asm_op "." #asm_type " zero, %1, %0" \
+ : "+A" (v->counter) \
+ : "r" (I) \
+ : "memory"); \
}
#ifdef CONFIG_GENERIC_ATOMIC64
-#define ATOMIC_OPS(op, asm_op, c_op, I) \
- ATOMIC_OP (op, asm_op, c_op, I, w, int, )
+#define ATOMIC_OPS(op, asm_op, I) \
+ ATOMIC_OP (op, asm_op, I, w, int, )
#else
-#define ATOMIC_OPS(op, asm_op, c_op, I) \
- ATOMIC_OP (op, asm_op, c_op, I, w, int, ) \
- ATOMIC_OP (op, asm_op, c_op, I, d, long, 64)
+#define ATOMIC_OPS(op, asm_op, I) \
+ ATOMIC_OP (op, asm_op, I, w, int, ) \
+ ATOMIC_OP (op, asm_op, I, d, long, 64)
#endif
-ATOMIC_OPS(add, add, +, i)
-ATOMIC_OPS(sub, add, +, -i)
-ATOMIC_OPS(and, and, &, i)
-ATOMIC_OPS( or, or, |, i)
-ATOMIC_OPS(xor, xor, ^, i)
+ATOMIC_OPS(add, add, i)
+ATOMIC_OPS(sub, add, -i)
+ATOMIC_OPS(and, and, i)
+ATOMIC_OPS( or, or, i)
+ATOMIC_OPS(xor, xor, i)
#undef ATOMIC_OP
#undef ATOMIC_OPS
* There's two flavors of these: the arithmatic ops have both fetch and return
* versions, while the logical ops only have fetch versions.
*/
-#define ATOMIC_FETCH_OP(op, asm_op, c_op, I, asm_or, c_or, asm_type, c_type, prefix) \
+#define ATOMIC_FETCH_OP(op, asm_op, I, asm_or, c_or, asm_type, c_type, prefix) \
static __always_inline c_type atomic##prefix##_fetch_##op##c_or(c_type i, atomic##prefix##_t *v) \
{ \
register c_type ret; \
#ifdef CONFIG_GENERIC_ATOMIC64
#define ATOMIC_OPS(op, asm_op, c_op, I, asm_or, c_or) \
- ATOMIC_FETCH_OP (op, asm_op, c_op, I, asm_or, c_or, w, int, ) \
+ ATOMIC_FETCH_OP (op, asm_op, I, asm_or, c_or, w, int, ) \
ATOMIC_OP_RETURN(op, asm_op, c_op, I, asm_or, c_or, w, int, )
#else
#define ATOMIC_OPS(op, asm_op, c_op, I, asm_or, c_or) \
- ATOMIC_FETCH_OP (op, asm_op, c_op, I, asm_or, c_or, w, int, ) \
+ ATOMIC_FETCH_OP (op, asm_op, I, asm_or, c_or, w, int, ) \
ATOMIC_OP_RETURN(op, asm_op, c_op, I, asm_or, c_or, w, int, ) \
- ATOMIC_FETCH_OP (op, asm_op, c_op, I, asm_or, c_or, d, long, 64) \
+ ATOMIC_FETCH_OP (op, asm_op, I, asm_or, c_or, d, long, 64) \
ATOMIC_OP_RETURN(op, asm_op, c_op, I, asm_or, c_or, d, long, 64)
#endif
#undef ATOMIC_OPS
#ifdef CONFIG_GENERIC_ATOMIC64
-#define ATOMIC_OPS(op, asm_op, c_op, I, asm_or, c_or) \
- ATOMIC_FETCH_OP(op, asm_op, c_op, I, asm_or, c_or, w, int, )
+#define ATOMIC_OPS(op, asm_op, I, asm_or, c_or) \
+ ATOMIC_FETCH_OP(op, asm_op, I, asm_or, c_or, w, int, )
#else
-#define ATOMIC_OPS(op, asm_op, c_op, I, asm_or, c_or) \
- ATOMIC_FETCH_OP(op, asm_op, c_op, I, asm_or, c_or, w, int, ) \
- ATOMIC_FETCH_OP(op, asm_op, c_op, I, asm_or, c_or, d, long, 64)
+#define ATOMIC_OPS(op, asm_op, I, asm_or, c_or) \
+ ATOMIC_FETCH_OP(op, asm_op, I, asm_or, c_or, w, int, ) \
+ ATOMIC_FETCH_OP(op, asm_op, I, asm_or, c_or, d, long, 64)
#endif
-ATOMIC_OPS(and, and, &, i, , _relaxed)
-ATOMIC_OPS(and, and, &, i, .aq , _acquire)
-ATOMIC_OPS(and, and, &, i, .rl , _release)
-ATOMIC_OPS(and, and, &, i, .aqrl, )
+ATOMIC_OPS(and, and, i, , _relaxed)
+ATOMIC_OPS(and, and, i, .aq , _acquire)
+ATOMIC_OPS(and, and, i, .rl , _release)
+ATOMIC_OPS(and, and, i, .aqrl, )
-ATOMIC_OPS( or, or, |, i, , _relaxed)
-ATOMIC_OPS( or, or, |, i, .aq , _acquire)
-ATOMIC_OPS( or, or, |, i, .rl , _release)
-ATOMIC_OPS( or, or, |, i, .aqrl, )
+ATOMIC_OPS( or, or, i, , _relaxed)
+ATOMIC_OPS( or, or, i, .aq , _acquire)
+ATOMIC_OPS( or, or, i, .rl , _release)
+ATOMIC_OPS( or, or, i, .aqrl, )
-ATOMIC_OPS(xor, xor, ^, i, , _relaxed)
-ATOMIC_OPS(xor, xor, ^, i, .aq , _acquire)
-ATOMIC_OPS(xor, xor, ^, i, .rl , _release)
-ATOMIC_OPS(xor, xor, ^, i, .aqrl, )
+ATOMIC_OPS(xor, xor, i, , _relaxed)
+ATOMIC_OPS(xor, xor, i, .aq , _acquire)
+ATOMIC_OPS(xor, xor, i, .rl , _release)
+ATOMIC_OPS(xor, xor, i, .aqrl, )
#undef ATOMIC_OPS
#undef ATOMIC_OP
#undef ATOMIC_OPS
-#define ATOMIC_OP(op, func_op, c_op, I, c_type, prefix) \
+#define ATOMIC_OP(op, func_op, I, c_type, prefix) \
static __always_inline void atomic##prefix##_##op(atomic##prefix##_t *v) \
{ \
atomic##prefix##_##func_op(I, v); \
}
-#define ATOMIC_FETCH_OP(op, func_op, c_op, I, c_type, prefix) \
+#define ATOMIC_FETCH_OP(op, func_op, I, c_type, prefix) \
static __always_inline c_type atomic##prefix##_fetch_##op(atomic##prefix##_t *v) \
{ \
return atomic##prefix##_fetch_##func_op(I, v); \
#ifdef CONFIG_GENERIC_ATOMIC64
#define ATOMIC_OPS(op, asm_op, c_op, I) \
- ATOMIC_OP (op, asm_op, c_op, I, int, ) \
- ATOMIC_FETCH_OP (op, asm_op, c_op, I, int, ) \
+ ATOMIC_OP (op, asm_op, I, int, ) \
+ ATOMIC_FETCH_OP (op, asm_op, I, int, ) \
ATOMIC_OP_RETURN(op, asm_op, c_op, I, int, )
#else
#define ATOMIC_OPS(op, asm_op, c_op, I) \
- ATOMIC_OP (op, asm_op, c_op, I, int, ) \
- ATOMIC_FETCH_OP (op, asm_op, c_op, I, int, ) \
+ ATOMIC_OP (op, asm_op, I, int, ) \
+ ATOMIC_FETCH_OP (op, asm_op, I, int, ) \
ATOMIC_OP_RETURN(op, asm_op, c_op, I, int, ) \
- ATOMIC_OP (op, asm_op, c_op, I, long, 64) \
- ATOMIC_FETCH_OP (op, asm_op, c_op, I, long, 64) \
+ ATOMIC_OP (op, asm_op, I, long, 64) \
+ ATOMIC_FETCH_OP (op, asm_op, I, long, 64) \
ATOMIC_OP_RETURN(op, asm_op, c_op, I, long, 64)
#endif
/*
* atomic_{cmp,}xchg is required to have exactly the same ordering semantics as
- * {cmp,}xchg and the operations that return, so they need a barrier. We just
- * use the other implementations directly.
+ * {cmp,}xchg and the operations that return, so they need a barrier.
+ */
+/*
+ * FIXME: atomic_cmpxchg_{acquire,release,relaxed} are all implemented by
+ * assigning the same barrier to both the LR and SC operations, but that might
+ * not make any sense. We're waiting on a memory model specification to
+ * determine exactly what the right thing to do is here.
*/
#define ATOMIC_OP(c_t, prefix, c_or, size, asm_or) \
static __always_inline c_t atomic##prefix##_cmpxchg##c_or(atomic##prefix##_t *v, c_t o, c_t n) \
#define smp_rmb() RISCV_FENCE(r,r)
#define smp_wmb() RISCV_FENCE(w,w)
-/*
- * These fences exist to enforce ordering around the relaxed AMOs. The
- * documentation defines that
- * "
- * atomic_fetch_add();
- * is equivalent to:
- * smp_mb__before_atomic();
- * atomic_fetch_add_relaxed();
- * smp_mb__after_atomic();
- * "
- * So we emit full fences on both sides.
- */
-#define __smb_mb__before_atomic() smp_mb()
-#define __smb_mb__after_atomic() smp_mb()
-
-/*
- * These barriers prevent accesses performed outside a spinlock from being moved
- * inside a spinlock. Since RISC-V sets the aq/rl bits on our spinlock only
- * enforce release consistency, we need full fences here.
- */
-#define smb_mb__before_spinlock() smp_mb()
-#define smb_mb__after_spinlock() smp_mb()
-
#include <asm-generic/barrier.h>
#endif /* __ASSEMBLY__ */
: "memory");
#define __test_and_op_bit(op, mod, nr, addr) \
- __test_and_op_bit_ord(op, mod, nr, addr, )
+ __test_and_op_bit_ord(op, mod, nr, addr, .aqrl)
#define __op_bit(op, mod, nr, addr) \
__op_bit_ord(op, mod, nr, addr, )
typedef u32 bug_insn_t;
#ifdef CONFIG_GENERIC_BUG_RELATIVE_POINTERS
-#define __BUG_ENTRY_ADDR INT " 1b - 2b"
-#define __BUG_ENTRY_FILE INT " %0 - 2b"
+#define __BUG_ENTRY_ADDR RISCV_INT " 1b - 2b"
+#define __BUG_ENTRY_FILE RISCV_INT " %0 - 2b"
#else
#define __BUG_ENTRY_ADDR RISCV_PTR " 1b"
#define __BUG_ENTRY_FILE RISCV_PTR " %0"
#define __BUG_ENTRY \
__BUG_ENTRY_ADDR "\n\t" \
__BUG_ENTRY_FILE "\n\t" \
- SHORT " %1"
+ RISCV_SHORT " %1"
#else
#define __BUG_ENTRY \
__BUG_ENTRY_ADDR
#undef flush_icache_range
#undef flush_icache_user_range
+#undef flush_dcache_page
static inline void local_flush_icache_all(void)
{
asm volatile ("fence.i" ::: "memory");
}
+#define PG_dcache_clean PG_arch_1
+
+static inline void flush_dcache_page(struct page *page)
+{
+ if (test_bit(PG_dcache_clean, &page->flags))
+ clear_bit(PG_dcache_clean, &page->flags);
+}
+
+/*
+ * RISC-V doesn't have an instruction to flush parts of the instruction cache,
+ * so instead we just flush the whole thing.
+ */
+#define flush_icache_range(start, end) flush_icache_all()
+#define flush_icache_user_range(vma, pg, addr, len) flush_icache_all()
+
#ifndef CONFIG_SMP
-#define flush_icache_range(start, end) local_flush_icache_all()
-#define flush_icache_user_range(vma, pg, addr, len) local_flush_icache_all()
+#define flush_icache_all() local_flush_icache_all()
+#define flush_icache_mm(mm, local) flush_icache_all()
#else /* CONFIG_SMP */
-#define flush_icache_range(start, end) sbi_remote_fence_i(0)
-#define flush_icache_user_range(vma, pg, addr, len) sbi_remote_fence_i(0)
+#define flush_icache_all() sbi_remote_fence_i(0)
+void flush_icache_mm(struct mm_struct *mm, bool local);
#endif /* CONFIG_SMP */
+/*
+ * Bits in sys_riscv_flush_icache()'s flags argument.
+ */
+#define SYS_RISCV_FLUSH_ICACHE_LOCAL 1UL
+#define SYS_RISCV_FLUSH_ICACHE_ALL (SYS_RISCV_FLUSH_ICACHE_LOCAL)
+
#endif /* _ASM_RISCV_CACHEFLUSH_H */
#ifndef _ASM_RISCV_IO_H
#define _ASM_RISCV_IO_H
+#include <linux/types.h>
+
#ifdef CONFIG_MMU
extern void __iomem *ioremap(phys_addr_t offset, unsigned long size);
#define ioremap_wc(addr, size) ioremap((addr), (size))
#define ioremap_wt(addr, size) ioremap((addr), (size))
-extern void iounmap(void __iomem *addr);
+extern void iounmap(volatile void __iomem *addr);
#endif /* CONFIG_MMU */
const ctype *buf = buffer; \
\
do { \
- __raw_writeq(*buf++, addr); \
+ __raw_write ## len(*buf++, addr); \
} while (--count); \
} \
afence; \
__io_reads_ins(ins, u8, b, __io_pbr(), __io_par())
__io_reads_ins(ins, u16, w, __io_pbr(), __io_par())
__io_reads_ins(ins, u32, l, __io_pbr(), __io_par())
-#define insb(addr, buffer, count) __insb((void __iomem *)addr, buffer, count)
-#define insw(addr, buffer, count) __insw((void __iomem *)addr, buffer, count)
-#define insl(addr, buffer, count) __insl((void __iomem *)addr, buffer, count)
+#define insb(addr, buffer, count) __insb((void __iomem *)(long)addr, buffer, count)
+#define insw(addr, buffer, count) __insw((void __iomem *)(long)addr, buffer, count)
+#define insl(addr, buffer, count) __insl((void __iomem *)(long)addr, buffer, count)
__io_writes_outs(writes, u8, b, __io_bw(), __io_aw())
__io_writes_outs(writes, u16, w, __io_bw(), __io_aw())
__io_writes_outs(outs, u8, b, __io_pbw(), __io_paw())
__io_writes_outs(outs, u16, w, __io_pbw(), __io_paw())
__io_writes_outs(outs, u32, l, __io_pbw(), __io_paw())
-#define outsb(addr, buffer, count) __outsb((void __iomem *)addr, buffer, count)
-#define outsw(addr, buffer, count) __outsw((void __iomem *)addr, buffer, count)
-#define outsl(addr, buffer, count) __outsl((void __iomem *)addr, buffer, count)
+#define outsb(addr, buffer, count) __outsb((void __iomem *)(long)addr, buffer, count)
+#define outsw(addr, buffer, count) __outsw((void __iomem *)(long)addr, buffer, count)
+#define outsl(addr, buffer, count) __outsl((void __iomem *)(long)addr, buffer, count)
#ifdef CONFIG_64BIT
__io_reads_ins(reads, u64, q, __io_br(), __io_ar())
typedef struct {
void *vdso;
+#ifdef CONFIG_SMP
+ /* A local icache flush is needed before user execution can resume. */
+ cpumask_t icache_stale_mask;
+#endif
} mm_context_t;
#endif /* __ASSEMBLY__ */
/*
* Copyright (C) 2012 Regents of the University of California
+ * Copyright (C) 2017 SiFive
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
#ifndef _ASM_RISCV_MMU_CONTEXT_H
#define _ASM_RISCV_MMU_CONTEXT_H
+#include <linux/mm_types.h>
#include <asm-generic/mm_hooks.h>
#include <linux/mm.h>
#include <linux/sched.h>
#include <asm/tlbflush.h>
+#include <asm/cacheflush.h>
static inline void enter_lazy_tlb(struct mm_struct *mm,
struct task_struct *task)
csr_write(sptbr, virt_to_pfn(pgd) | SPTBR_MODE);
}
+/*
+ * When necessary, performs a deferred icache flush for the given MM context,
+ * on the local CPU. RISC-V has no direct mechanism for instruction cache
+ * shoot downs, so instead we send an IPI that informs the remote harts they
+ * need to flush their local instruction caches. To avoid pathologically slow
+ * behavior in a common case (a bunch of single-hart processes on a many-hart
+ * machine, ie 'make -j') we avoid the IPIs for harts that are not currently
+ * executing a MM context and instead schedule a deferred local instruction
+ * cache flush to be performed before execution resumes on each hart. This
+ * actually performs that local instruction cache flush, which implicitly only
+ * refers to the current hart.
+ */
+static inline void flush_icache_deferred(struct mm_struct *mm)
+{
+#ifdef CONFIG_SMP
+ unsigned int cpu = smp_processor_id();
+ cpumask_t *mask = &mm->context.icache_stale_mask;
+
+ if (cpumask_test_cpu(cpu, mask)) {
+ cpumask_clear_cpu(cpu, mask);
+ /*
+ * Ensure the remote hart's writes are visible to this hart.
+ * This pairs with a barrier in flush_icache_mm.
+ */
+ smp_mb();
+ local_flush_icache_all();
+ }
+#endif
+}
+
static inline void switch_mm(struct mm_struct *prev,
struct mm_struct *next, struct task_struct *task)
{
if (likely(prev != next)) {
+ /*
+ * Mark the current MM context as inactive, and the next as
+ * active. This is at least used by the icache flushing
+ * routines in order to determine who should
+ */
+ unsigned int cpu = smp_processor_id();
+
+ cpumask_clear_cpu(cpu, mm_cpumask(prev));
+ cpumask_set_cpu(cpu, mm_cpumask(next));
+
set_pgdir(next->pgd);
local_flush_tlb_all();
+
+ flush_icache_deferred(next);
}
}
#define pte_offset_map(dir, addr) pte_offset_kernel((dir), (addr))
#define pte_unmap(pte) ((void)(pte))
-/*
- * Certain architectures need to do special things when PTEs within
- * a page table are directly modified. Thus, the following hook is
- * made available.
- */
-static inline void set_pte(pte_t *ptep, pte_t pteval)
-{
- *ptep = pteval;
-}
-
-static inline void set_pte_at(struct mm_struct *mm,
- unsigned long addr, pte_t *ptep, pte_t pteval)
-{
- set_pte(ptep, pteval);
-}
-
-static inline void pte_clear(struct mm_struct *mm,
- unsigned long addr, pte_t *ptep)
-{
- set_pte_at(mm, addr, ptep, __pte(0));
-}
-
static inline int pte_present(pte_t pte)
{
return (pte_val(pte) & _PAGE_PRESENT);
return (pte_val(pte) == 0);
}
-/* static inline int pte_read(pte_t pte) */
-
static inline int pte_write(pte_t pte)
{
return pte_val(pte) & _PAGE_WRITE;
}
+static inline int pte_exec(pte_t pte)
+{
+ return pte_val(pte) & _PAGE_EXEC;
+}
+
static inline int pte_huge(pte_t pte)
{
return pte_present(pte)
&& (pte_val(pte) & (_PAGE_READ | _PAGE_WRITE | _PAGE_EXEC));
}
-/* static inline int pte_exec(pte_t pte) */
-
static inline int pte_dirty(pte_t pte)
{
return pte_val(pte) & _PAGE_DIRTY;
return pte_val(pte_a) == pte_val(pte_b);
}
+/*
+ * Certain architectures need to do special things when PTEs within
+ * a page table are directly modified. Thus, the following hook is
+ * made available.
+ */
+static inline void set_pte(pte_t *ptep, pte_t pteval)
+{
+ *ptep = pteval;
+}
+
+void flush_icache_pte(pte_t pte);
+
+static inline void set_pte_at(struct mm_struct *mm,
+ unsigned long addr, pte_t *ptep, pte_t pteval)
+{
+ if (pte_present(pteval) && pte_exec(pteval))
+ flush_icache_pte(pteval);
+
+ set_pte(ptep, pteval);
+}
+
+static inline void pte_clear(struct mm_struct *mm,
+ unsigned long addr, pte_t *ptep)
+{
+ set_pte_at(mm, addr, ptep, __pte(0));
+}
+
#define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
static inline int ptep_set_access_flags(struct vm_area_struct *vma,
unsigned long address, pte_t *ptep,
/* FIXME: Replace this with a ticket lock, like MIPS. */
-#define arch_spin_is_locked(x) ((x)->lock != 0)
+#define arch_spin_is_locked(x) (READ_ONCE((x)->lock) != 0)
static inline void arch_spin_unlock(arch_spinlock_t *lock)
{
}
}
-static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
-{
- smp_rmb();
- do {
- cpu_relax();
- } while (arch_spin_is_locked(lock));
- smp_acquire__after_ctrl_dep();
-}
-
/***********************************************************/
static inline void arch_read_lock(arch_rwlock_t *lock)
typedef unsigned long cycles_t;
-static inline cycles_t get_cycles(void)
+static inline cycles_t get_cycles_inline(void)
{
cycles_t n;
: "=r" (n));
return n;
}
+#define get_cycles get_cycles_inline
#ifdef CONFIG_64BIT
static inline uint64_t get_cycles64(void)
#ifdef CONFIG_MMU
-/* Flush entire local TLB */
+#include <linux/mm_types.h>
+
+/*
+ * Flush entire local TLB. 'sfence.vma' implicitly fences with the instruction
+ * cache as well, so a 'fence.i' is not necessary.
+ */
static inline void local_flush_tlb_all(void)
{
__asm__ __volatile__ ("sfence.vma" : : : "memory");
--- /dev/null
+/*
+ * Copyright (C) 2017 SiFive
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef _ASM_RISCV_VDSO_SYSCALLS_H
+#define _ASM_RISCV_VDSO_SYSCALLS_H
+
+#ifdef CONFIG_SMP
+
+/* These syscalls are only used by the vDSO and are not in the uapi. */
+#define __NR_riscv_flush_icache (__NR_arch_specific_syscall + 15)
+__SYSCALL(__NR_riscv_flush_icache, sys_riscv_flush_icache)
+
+#endif
+
+#endif /* _ASM_RISCV_VDSO_H */
(void __user *)((unsigned long)(base) + __vdso_##name); \
})
+#ifdef CONFIG_SMP
+asmlinkage long sys_riscv_flush_icache(uintptr_t, uintptr_t, uintptr_t);
+#endif
+
#endif /* _ASM_RISCV_VDSO_H */
__PAGE_ALIGNED_BSS
/* Empty zero page */
.balign PAGE_SIZE
-ENTRY(empty_zero_page)
- .fill (empty_zero_page + PAGE_SIZE) - ., 1, 0x00
-END(empty_zero_page)
/*
* Assembly functions that may be used (directly or indirectly) by modules
*/
+EXPORT_SYMBOL(__clear_user);
EXPORT_SYMBOL(__copy_user);
+EXPORT_SYMBOL(memset);
+EXPORT_SYMBOL(memcpy);
#endif /* CONFIG_CMDLINE_BOOL */
unsigned long va_pa_offset;
+EXPORT_SYMBOL(va_pa_offset);
unsigned long pfn_base;
+EXPORT_SYMBOL(pfn_base);
+
+unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)] __page_aligned_bss;
+EXPORT_SYMBOL(empty_zero_page);
/* The lucky hart to first increment this variable will boot the other cores */
atomic_t hart_lottery;
IPI_MAX
};
+
+/* Unsupported */
+int setup_profiling_timer(unsigned int multiplier)
+{
+ return -EINVAL;
+}
+
irqreturn_t handle_ipi(void)
{
unsigned long *pending_ipis = &ipi_data[smp_processor_id()].bits;
{
send_ipi_message(cpumask_of(cpu), IPI_RESCHEDULE);
}
+
+/*
+ * Performs an icache flush for the given MM context. RISC-V has no direct
+ * mechanism for instruction cache shoot downs, so instead we send an IPI that
+ * informs the remote harts they need to flush their local instruction caches.
+ * To avoid pathologically slow behavior in a common case (a bunch of
+ * single-hart processes on a many-hart machine, ie 'make -j') we avoid the
+ * IPIs for harts that are not currently executing a MM context and instead
+ * schedule a deferred local instruction cache flush to be performed before
+ * execution resumes on each hart.
+ */
+void flush_icache_mm(struct mm_struct *mm, bool local)
+{
+ unsigned int cpu;
+ cpumask_t others, *mask;
+
+ preempt_disable();
+
+ /* Mark every hart's icache as needing a flush for this MM. */
+ mask = &mm->context.icache_stale_mask;
+ cpumask_setall(mask);
+ /* Flush this hart's I$ now, and mark it as flushed. */
+ cpu = smp_processor_id();
+ cpumask_clear_cpu(cpu, mask);
+ local_flush_icache_all();
+
+ /*
+ * Flush the I$ of other harts concurrently executing, and mark them as
+ * flushed.
+ */
+ cpumask_andnot(&others, mm_cpumask(mm), cpumask_of(cpu));
+ local |= cpumask_empty(&others);
+ if (mm != current->active_mm || !local)
+ sbi_remote_fence_i(others.bits);
+ else {
+ /*
+ * It's assumed that at least one strongly ordered operation is
+ * performed on this hart between setting a hart's cpumask bit
+ * and scheduling this MM context on that hart. Sending an SBI
+ * remote message will do this, but in the case where no
+ * messages are sent we still need to order this hart's writes
+ * with flush_icache_deferred().
+ */
+ smp_mb();
+ }
+
+ preempt_enable();
+}
*/
#include <linux/syscalls.h>
-#include <asm/cmpxchg.h>
#include <asm/unistd.h>
+#include <asm/cacheflush.h>
static long riscv_sys_mmap(unsigned long addr, unsigned long len,
unsigned long prot, unsigned long flags,
return riscv_sys_mmap(addr, len, prot, flags, fd, offset, 12);
}
#endif /* !CONFIG_64BIT */
+
+#ifdef CONFIG_SMP
+/*
+ * Allows the instruction cache to be flushed from userspace. Despite RISC-V
+ * having a direct 'fence.i' instruction available to userspace (which we
+ * can't trap!), that's not actually viable when running on Linux because the
+ * kernel might schedule a process on another hart. There is no way for
+ * userspace to handle this without invoking the kernel (as it doesn't know the
+ * thread->hart mappings), so we've defined a RISC-V specific system call to
+ * flush the instruction cache.
+ *
+ * sys_riscv_flush_icache() is defined to flush the instruction cache over an
+ * address range, with the flush applying to either all threads or just the
+ * caller. We don't currently do anything with the address range, that's just
+ * in there for forwards compatibility.
+ */
+SYSCALL_DEFINE3(riscv_flush_icache, uintptr_t, start, uintptr_t, end,
+ uintptr_t, flags)
+{
+ struct mm_struct *mm = current->mm;
+ bool local = (flags & SYS_RISCV_FLUSH_ICACHE_LOCAL) != 0;
+
+ /* Check the reserved flags. */
+ if (unlikely(flags & !SYS_RISCV_FLUSH_ICACHE_ALL))
+ return -EINVAL;
+
+ flush_icache_mm(mm, local);
+
+ return 0;
+}
+#endif
#include <linux/linkage.h>
#include <linux/syscalls.h>
#include <asm-generic/syscalls.h>
+#include <asm/vdso.h>
#undef __SYSCALL
#define __SYSCALL(nr, call) [nr] = (call),
void *sys_call_table[__NR_syscalls] = {
[0 ... __NR_syscalls - 1] = sys_ni_syscall,
#include <asm/unistd.h>
+#include <asm/vdso-syscalls.h>
};
# Copied from arch/tile/kernel/vdso/Makefile
# Symbols present in the vdso
-vdso-syms = rt_sigreturn
+vdso-syms = rt_sigreturn
+vdso-syms += gettimeofday
+vdso-syms += clock_gettime
+vdso-syms += clock_getres
+vdso-syms += getcpu
+vdso-syms += flush_icache
# Files to link into the vdso
obj-vdso = $(patsubst %, %.o, $(vdso-syms))
--- /dev/null
+/*
+ * Copyright (C) 2017 SiFive
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation, version 2.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/linkage.h>
+#include <asm/unistd.h>
+
+ .text
+/* int __vdso_clock_getres(clockid_t clock_id, struct timespec *res); */
+ENTRY(__vdso_clock_getres)
+ .cfi_startproc
+ /* For now, just do the syscall. */
+ li a7, __NR_clock_getres
+ ecall
+ ret
+ .cfi_endproc
+ENDPROC(__vdso_clock_getres)
--- /dev/null
+/*
+ * Copyright (C) 2017 SiFive
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation, version 2.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/linkage.h>
+#include <asm/unistd.h>
+
+ .text
+/* int __vdso_clock_gettime(clockid_t clock_id, struct timespec *tp); */
+ENTRY(__vdso_clock_gettime)
+ .cfi_startproc
+ /* For now, just do the syscall. */
+ li a7, __NR_clock_gettime
+ ecall
+ ret
+ .cfi_endproc
+ENDPROC(__vdso_clock_gettime)
--- /dev/null
+/*
+ * Copyright (C) 2017 SiFive
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation, version 2.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/linkage.h>
+#include <asm/unistd.h>
+#include <asm/vdso-syscalls.h>
+
+ .text
+/* int __vdso_flush_icache(void *start, void *end, unsigned long flags); */
+ENTRY(__vdso_flush_icache)
+ .cfi_startproc
+#ifdef CONFIG_SMP
+ li a7, __NR_riscv_flush_icache
+ ecall
+#else
+ fence.i
+ li a0, 0
+#endif
+ ret
+ .cfi_endproc
+ENDPROC(__vdso_flush_icache)
--- /dev/null
+/*
+ * Copyright (C) 2017 SiFive
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation, version 2.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/linkage.h>
+#include <asm/unistd.h>
+
+ .text
+/* int __vdso_getcpu(unsigned *cpu, unsigned *node, void *unused); */
+ENTRY(__vdso_getcpu)
+ .cfi_startproc
+ /* For now, just do the syscall. */
+ li a7, __NR_getcpu
+ ecall
+ ret
+ .cfi_endproc
+ENDPROC(__vdso_getcpu)
--- /dev/null
+/*
+ * Copyright (C) 2017 SiFive
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation, version 2.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/linkage.h>
+#include <asm/unistd.h>
+
+ .text
+/* int __vdso_gettimeofday(struct timeval *tv, struct timezone *tz); */
+ENTRY(__vdso_gettimeofday)
+ .cfi_startproc
+ /* For now, just do the syscall. */
+ li a7, __NR_gettimeofday
+ ecall
+ ret
+ .cfi_endproc
+ENDPROC(__vdso_gettimeofday)
LINUX_4.15 {
global:
__vdso_rt_sigreturn;
- __vdso_cmpxchg32;
- __vdso_cmpxchg64;
+ __vdso_gettimeofday;
+ __vdso_clock_gettime;
+ __vdso_clock_getres;
+ __vdso_getcpu;
+ __vdso_flush_icache;
local: *;
};
}
while ((unsigned long)(get_cycles() - t0) < cycles)
cpu_relax();
}
+EXPORT_SYMBOL(__delay);
void udelay(unsigned long usecs)
{
obj-y += fault.o
obj-y += extable.o
obj-y += ioremap.o
+obj-y += cacheflush.o
--- /dev/null
+/*
+ * Copyright (C) 2017 SiFive
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation, version 2.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#include <asm/pgtable.h>
+#include <asm/cacheflush.h>
+
+void flush_icache_pte(pte_t pte)
+{
+ struct page *page = pte_page(pte);
+
+ if (!test_and_set_bit(PG_dcache_clean, &page->flags))
+ flush_icache_all();
+}
*
* Caller must ensure there is only one unmapping for the same pointer.
*/
-void iounmap(void __iomem *addr)
+void iounmap(volatile void __iomem *addr)
{
vunmap((void *)((unsigned long)addr & PAGE_MASK));
}
+# SPDX-License-Identifier: GPL-2.0
#
# s390/Makefile
#
# for "archclean" and "archdep" for cleaning up and making dependencies for
# this architecture
#
-# This file is subject to the terms and conditions of the GNU General Public
-# License. See the file "COPYING" in the main directory of this archive
-# for more details.
-#
# Copyright (C) 1994 by Linus Torvalds
#
+// SPDX-License-Identifier: GPL-2.0
/*
* Base infrastructure for Linux-z/VM Monitor Stream, Stage 1.
* Exports appldata_register_ops() and appldata_unregister_ops() for the
+// SPDX-License-Identifier: GPL-2.0
/*
* Data gathering module for Linux-VM Monitor Stream, Stage 1.
* Collects data related to memory management.
+// SPDX-License-Identifier: GPL-2.0
/*
* Data gathering module for Linux-VM Monitor Stream, Stage 1.
* Collects accumulated network statistics (Packets received/transmitted,
+// SPDX-License-Identifier: GPL-2.0
/*
* Data gathering module for Linux-VM Monitor Stream, Stage 1.
* Collects misc. OS related data (CPU utilization, running processes).
#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
#
# arch/s390x/boot/install.sh
#
-# This file is subject to the terms and conditions of the GNU General Public
-# License. See the file "COPYING" in the main directory of this archive
-# for more details.
-#
# Copyright (C) 1995 by Linus Torvalds
#
# Adapted from code in arch/i386/boot/Makefile by H. Peter Anvin
+// SPDX-License-Identifier: GPL-2.0+
/*
* Cryptographic API.
*
* Harald Freudenberger <freude@de.ibm.com>
*
* Derived from "crypto/aes_generic.c"
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the Free
- * Software Foundation; either version 2 of the License, or (at your option)
- * any later version.
- *
*/
#define KMSG_COMPONENT "aes_s390"
+// SPDX-License-Identifier: GPL-2.0
/*
* s390 arch random implementation.
*
* Copyright IBM Corp. 2017
* Author(s): Harald Freudenberger <freude@de.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
- *
*/
#include <linux/kernel.h>
+// SPDX-License-Identifier: GPL-2.0
/*
* Crypto-API module for CRC-32 algorithms implemented with the
* z/Architecture Vector Extension Facility.
+// SPDX-License-Identifier: GPL-2.0+
/*
* Cryptographic API.
*
* Copyright IBM Corp. 2003, 2011
* Author(s): Thomas Spatzier
* Jan Glauber (jan.glauber@de.ibm.com)
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
*/
#include <linux/init.h>
+// SPDX-License-Identifier: GPL-2.0
/*
* Cryptographic API.
*
+// SPDX-License-Identifier: GPL-2.0
/*
* Cryptographic API.
*
* Copyright IBM Corp. 2017
* Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>
* Harald Freudenberger <freude@de.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
- *
*/
#define KMSG_COMPONENT "paes_s390"
+// SPDX-License-Identifier: GPL-2.0
/*
* Copyright IBM Corp. 2006, 2015
* Author(s): Jan Glauber <jan.glauber@de.ibm.com>
+/* SPDX-License-Identifier: GPL-2.0+ */
/*
* Cryptographic API.
*
*
* Copyright IBM Corp. 2007
* Author(s): Jan Glauber (jang@de.ibm.com)
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the Free
- * Software Foundation; either version 2 of the License, or (at your option)
- * any later version.
- *
*/
#ifndef _CRYPTO_ARCH_S390_SHA_H
#define _CRYPTO_ARCH_S390_SHA_H
+// SPDX-License-Identifier: GPL-2.0+
/*
* Cryptographic API.
*
* s390 Version:
* Copyright IBM Corp. 2005, 2011
* Author(s): Jan Glauber (jang@de.ibm.com)
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the Free
- * Software Foundation; either version 2 of the License, or (at your option)
- * any later version.
- *
*/
#include <crypto/internal/hash.h>
#include <linux/init.h>
+// SPDX-License-Identifier: GPL-2.0+
/*
* Cryptographic API.
*
*
* Copyright IBM Corp. 2007
* Author(s): Jan Glauber (jang@de.ibm.com)
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the Free
- * Software Foundation; either version 2 of the License, or (at your option)
- * any later version.
- *
*/
#include <crypto/internal/hash.h>
#include <crypto/sha.h>
+// SPDX-License-Identifier: GPL-2.0+
/*
* Cryptographic API.
*
*
* Copyright IBM Corp. 2007
* Author(s): Jan Glauber (jang@de.ibm.com)
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the Free
- * Software Foundation; either version 2 of the License, or (at your option)
- * any later version.
- *
*/
#include <crypto/internal/hash.h>
+// SPDX-License-Identifier: GPL-1.0+
/*
* Hypervisor filesystem for Linux on s390.
*
* Copyright IBM Corp. 2006, 2008
* Author(s): Michael Holzheu <holzheu@de.ibm.com>
- * License: GPL
*/
#define KMSG_COMPONENT "hypfs"
+/* SPDX-License-Identifier: GPL-2.0 */
/*
* CPU-measurement facilities
*
* Copyright IBM Corp. 2012
* Author(s): Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
* Jan Glauber <jang@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
*/
#ifndef _ASM_S390_CPU_MF_H
#define _ASM_S390_CPU_MF_H
#define CORE_DUMP_USE_REGSET
#define ELF_EXEC_PAGESIZE PAGE_SIZE
-/*
- * This is the base location for PIE (ET_DYN with INTERP) loads. On
- * 64-bit, this is raised to 4GB to leave the entire 32-bit address
- * space open for things that want to use the area for 32-bit pointers.
- */
-#define ELF_ET_DYN_BASE (is_compat_task() ? 0x000400000UL : \
- 0x100000000UL)
+/* This is the location that an ET_DYN program is loaded if exec'ed. Typical
+ use of this is to invoke "./ld.so someprog" to test out a new version of
+ the loader. We need to make sure that it is out of the way of the program
+ that it will "exec", and that there is sufficient room for the brk. 64-bit
+ tasks are aligned to 4GB. */
+#define ELF_ET_DYN_BASE (is_compat_task() ? \
+ (STACK_TOP / 3 * 2) : \
+ (STACK_TOP / 3 * 2) & ~((1UL << 32) - 1))
/* This yields a mask that user programs can use to figure out what
instruction set this CPU supports. */
+/* SPDX-License-Identifier: GPL-2.0+ */
#ifndef _ASM_S390_KPROBES_H
#define _ASM_S390_KPROBES_H
/*
* Kernel Probes (KProbes)
*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
- *
* Copyright IBM Corp. 2002, 2006
*
* 2002-Oct Created by Vamsi Krishna S <vamsi_krishna@in.ibm.com> Kernel
+/* SPDX-License-Identifier: GPL-2.0 */
/*
* definition for kernel virtual machines on s390
*
* Copyright IBM Corp. 2008, 2009
*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
- *
* Author(s): Carsten Otte <cotte@de.ibm.com>
*/
+/* SPDX-License-Identifier: GPL-2.0 */
/*
* definition for paravirtual devices on s390
*
* Copyright IBM Corp. 2008
*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
- *
* Author(s): Christian Borntraeger <borntraeger@de.ibm.com>
*/
/*
*
* Copyright IBM Corp. 2007,2008
* Author(s): Christian Borntraeger <borntraeger@de.ibm.com>
- *
- * This work is licensed under the terms of the GNU GPL, version 2.
*/
#ifndef __S390_KVM_PARA_H
#define __S390_KVM_PARA_H
+/* SPDX-License-Identifier: GPL-2.0+ */
/*
* livepatch.h - s390-specific Kernel Live Patching Core
*
* Jiri Slaby
*/
-/*
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the Free
- * Software Foundation; either version 2 of the License, or (at your option)
- * any later version.
- */
-
#ifndef ASM_LIVEPATCH_H
#define ASM_LIVEPATCH_H
#ifdef CONFIG_PGSTE
mm->context.alloc_pgste = page_table_allocate_pgste ||
test_thread_flag(TIF_PGSTE) ||
- current->mm->context.alloc_pgste;
+ (current->mm && current->mm->context.alloc_pgste);
mm->context.has_pgste = 0;
mm->context.use_skey = 0;
mm->context.use_cmma = 0;
return (pmd_val(pmd) & origin_mask) >> PAGE_SHIFT;
}
-#define __HAVE_ARCH_PMD_WRITE
+#define pmd_write pmd_write
static inline int pmd_write(pmd_t pmd)
{
return (pmd_val(pmd) & _SEGMENT_ENTRY_WRITE) != 0;
return pud;
}
+#define pud_write pud_write
+static inline int pud_write(pud_t pud)
+{
+ return (pud_val(pud) & _REGION3_ENTRY_WRITE) != 0;
+}
+
static inline pud_t pud_mkclean(pud_t pud)
{
if (pud_large(pud)) {
+/* SPDX-License-Identifier: GPL-2.0 */
/*
* Access to user system call parameters and results
*
* Copyright IBM Corp. 2008
* Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com)
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
*/
#ifndef _ASM_SYSCALL_H
+/* SPDX-License-Identifier: GPL-2.0 */
/*
* definition for store system information stsi
*
* Copyright IBM Corp. 2001, 2008
*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
- *
* Author(s): Ulrich Weigand <weigand@de.ibm.com>
* Christian Borntraeger <borntraeger@de.ibm.com>
*/
static inline void topology_init_early(void) { }
static inline void topology_schedule_update(void) { }
static inline int topology_cpu_init(struct cpu *cpu) { return 0; }
+static inline int topology_cpu_dedicated(int cpu_nr) { return 0; }
static inline void topology_expect_change(void) { }
#endif /* CONFIG_SCHED_TOPOLOGY */
*
* Copyright IBM Corp. 2008
*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
- *
* Author(s): Carsten Otte <cotte@de.ibm.com>
* Christian Borntraeger <borntraeger@de.ibm.com>
*/
*
* Copyright IBM Corp. 2008
*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
- *
* Author(s): Christian Borntraeger <borntraeger@de.ibm.com>
*/
*
* Copyright 2014 IBM Corp.
* Author(s): Alexander Yarygin <yarygin@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
*/
#ifndef __LINUX_KVM_PERF_S390_H
*
* Copyright IBM Corp. 2013
*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
- *
* Author(s): Cornelia Huck <cornelia.huck@de.ibm.com>
*/
#ifndef __KVM_VIRTIO_CCW_H
* Eric Rossman (edrossma@us.ibm.com)
*
* Hotplug & misc device support: Jochen Roehrig (roehrig@de.ibm.com)
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
*/
#ifndef __ASM_S390_ZCRYPT_H
else
except_str = "-";
caller = (unsigned long) entry->caller;
- rc += sprintf(out_buf, "%02i %011ld:%06lu %1u %1s %02i %p ",
+ rc += sprintf(out_buf, "%02i %011ld:%06lu %1u %1s %02i %pK ",
area, sec, usec, level, except_str,
entry->id.fields.cpuid, (void *)caller);
return rc;
+// SPDX-License-Identifier: GPL-2.0
/*
* Disassemble s390 instructions.
*
unsigned char opfrag;
int i;
+ /* Search the opcode offset table to find an entry which
+ * matches the beginning of the opcode. If there is no match
+ * the last entry will be used, which is the default entry for
+ * unknown instructions as well as 1-byte opcode instructions.
+ */
for (i = 0; i < ARRAY_SIZE(opcode_offset); i++) {
entry = &opcode_offset[i];
- if (entry->opcode == code[0] || entry->opcode == 0)
+ if (entry->opcode == code[0])
break;
}
start += opsize;
pr_cont("%s", buffer);
ptr = buffer;
- ptr += sprintf(ptr, "\n\t ");
+ ptr += sprintf(ptr, "\n ");
hops++;
}
pr_cont("\n");
+// SPDX-License-Identifier: GPL-2.0
/*
* Stack dumping functions
*
*/
ENTRY(__switch_to)
stmg %r6,%r15,__SF_GPRS(%r15) # store gprs of prev task
- lgr %r1,%r2
- aghi %r1,__TASK_thread # thread_struct of prev task
- lg %r5,__TASK_stack(%r3) # start of kernel stack of next
- stg %r15,__THREAD_ksp(%r1) # store kernel stack of prev
- lgr %r1,%r3
- aghi %r1,__TASK_thread # thread_struct of next task
+ lghi %r4,__TASK_stack
+ lghi %r1,__TASK_thread
+ lg %r5,0(%r4,%r3) # start of kernel stack of next
+ stg %r15,__THREAD_ksp(%r1,%r2) # store kernel stack of prev
lgr %r15,%r5
aghi %r15,STACK_INIT # end of kernel stack of next
stg %r3,__LC_CURRENT # store task struct of next
stg %r15,__LC_KERNEL_STACK # store end of kernel stack
- lg %r15,__THREAD_ksp(%r1) # load kernel stack of next
- mvc __LC_CURRENT_PID(4,%r0),__TASK_pid(%r3) # store pid of next
+ lg %r15,__THREAD_ksp(%r1,%r3) # load kernel stack of next
+ aghi %r3,__TASK_pid
+ mvc __LC_CURRENT_PID(4,%r0),0(%r3) # store pid of next
lmg %r6,%r15,__SF_GPRS(%r15) # load gprs of next task
TSTMSK __LC_MACHINE_FLAGS,MACHINE_FLAG_LPP
bzr %r14
+// SPDX-License-Identifier: GPL-2.0
/*
* ipl/reipl/dump support for Linux on s390.
*
+// SPDX-License-Identifier: GPL-2.0+
/*
* Kernel Probes (KProbes)
*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
- *
* Copyright IBM Corp. 2002, 2006
*
* s390 port, used ppc64 as template. Mike Grundy <grundym@us.ibm.com>
+// SPDX-License-Identifier: GPL-2.0
/*
* Linux Guest Relocation (LGR) detection
*
+// SPDX-License-Identifier: GPL-2.0+
/*
* Kernel module help for s390.
*
*
* based on i386 version
* Copyright (C) 2001 Rusty Russell.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*/
#include <linux/module.h>
#include <linux/elf.h>
+// SPDX-License-Identifier: GPL-2.0
/*
* Machine check handler
*
+// SPDX-License-Identifier: GPL-2.0
/*
* Performance event support for s390x - CPU-measurement Counter Facility
*
* Copyright IBM Corp. 2012, 2017
* Author(s): Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
*/
#define KMSG_COMPONENT "cpum_cf"
#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+// SPDX-License-Identifier: GPL-2.0
/*
* Performance event support for the System z CPU-measurement Sampling Facility
*
* Copyright IBM Corp. 2013
* Author(s): Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
*/
#define KMSG_COMPONENT "cpum_sf"
#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+// SPDX-License-Identifier: GPL-2.0
/*
* Performance event support for s390x
*
* Copyright IBM Corp. 2012, 2013
* Author(s): Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
*/
#define KMSG_COMPONENT "perf"
#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
.set = s390_gs_cb_set,
},
{
+ .core_note_type = NT_S390_GS_BC,
+ .n = sizeof(struct gs_cb) / sizeof(__u64),
+ .size = sizeof(__u64),
+ .align = sizeof(__u64),
+ .get = s390_gs_bc_get,
+ .set = s390_gs_bc_set,
+ },
+ {
.core_note_type = NT_S390_RI_CB,
.n = sizeof(struct runtime_instr_cb) / sizeof(__u64),
.size = sizeof(__u64),
+// SPDX-License-Identifier: GPL-2.0
/*
* S390 version
* Copyright IBM Corp. 1999, 2012
#include <asm/sigp.h>
#include <asm/idle.h>
#include <asm/nmi.h>
+#include <asm/topology.h>
#include "entry.h"
enum {
+// SPDX-License-Identifier: GPL-2.0
/*
* Stack trace management functions
*
+// SPDX-License-Identifier: GPL-2.0
/*
* store hypervisor information instruction emulation functions.
*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
- *
* Copyright IBM Corp. 2016
* Author(s): Janosch Frank <frankja@linux.vnet.ibm.com>
*/
+// SPDX-License-Identifier: GPL-2.0
/*
* Time of day based timer functions.
*
+// SPDX-License-Identifier: GPL-2.0
/*
* Copyright IBM Corp. 2007, 2011
* Author(s): Heiko Carstens <heiko.carstens@de.ibm.com>
+// SPDX-License-Identifier: GPL-2.0
/*
* vdso setup for s390
*
* Copyright IBM Corp. 2008
* Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com)
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
*/
#include <linux/init.h>
+/* SPDX-License-Identifier: GPL-2.0 */
/*
* Userland implementation of clock_getres() for 32 bits processes in a
* s390 kernel for use in the vDSO
*
* Copyright IBM Corp. 2008
* Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com)
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
*/
#include <asm/vdso.h>
#include <asm/asm-offsets.h>
+/* SPDX-License-Identifier: GPL-2.0 */
/*
* Userland implementation of clock_gettime() for 32 bits processes in a
* s390 kernel for use in the vDSO
*
* Copyright IBM Corp. 2008
* Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com)
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
*/
#include <asm/vdso.h>
#include <asm/asm-offsets.h>
+/* SPDX-License-Identifier: GPL-2.0 */
/*
* Userland implementation of gettimeofday() for 32 bits processes in a
* s390 kernel for use in the vDSO
*
* Copyright IBM Corp. 2008
* Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com)
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
*/
#include <asm/vdso.h>
#include <asm/asm-offsets.h>
+/* SPDX-License-Identifier: GPL-2.0 */
/*
* Userland implementation of clock_getres() for 64 bits processes in a
* s390 kernel for use in the vDSO
*
* Copyright IBM Corp. 2008
* Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com)
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
*/
#include <asm/vdso.h>
#include <asm/asm-offsets.h>
+/* SPDX-License-Identifier: GPL-2.0 */
/*
* Userland implementation of clock_gettime() for 64 bits processes in a
* s390 kernel for use in the vDSO
*
* Copyright IBM Corp. 2008
* Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com)
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
*/
#include <asm/vdso.h>
#include <asm/asm-offsets.h>
+/* SPDX-License-Identifier: GPL-2.0 */
/*
* Userland implementation of gettimeofday() for 64 bits processes in a
* s390 kernel for use in the vDSO
*
* Copyright IBM Corp. 2008
* Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com)
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
*/
#include <asm/vdso.h>
#include <asm/asm-offsets.h>
+// SPDX-License-Identifier: GPL-2.0
/*
* Virtual cpu timer based timer functions.
*
int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
{
int rc;
- sigset_t sigsaved;
if (kvm_run->immediate_exit)
return -EINTR;
return 0;
}
- if (vcpu->sigset_active)
- sigprocmask(SIG_SETMASK, &vcpu->sigset, &sigsaved);
+ kvm_sigset_activate(vcpu);
if (!kvm_s390_user_cpu_state_ctrl(vcpu->kvm)) {
kvm_s390_vcpu_start(vcpu);
disable_cpu_timer_accounting(vcpu);
store_regs(vcpu, kvm_run);
- if (vcpu->sigset_active)
- sigprocmask(SIG_SETMASK, &sigsaved, NULL);
+ kvm_sigset_deactivate(vcpu);
vcpu->stat.exit_userspace++;
return rc;
+// SPDX-License-Identifier: GPL-2.0
/*
* Collaborative memory management interface.
*
+// SPDX-License-Identifier: GPL-2.0
/*
* KVM guest address space mapping code
*
+// SPDX-License-Identifier: GPL-2.0+
/*
* flexible mmap layout support
*
* Copyright 2003-2004 Red Hat Inc., Durham, North Carolina.
* All Rights Reserved.
*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
- *
- *
* Started by Ingo Molnar <mingo@elte.hu>
*/
+// SPDX-License-Identifier: GPL-2.0
/*
* Copyright IBM Corp. 2007, 2011
* Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>
+// SPDX-License-Identifier: GPL-2.0
/*
* Copyright IBM Corp. 2012
*
+// SPDX-License-Identifier: GPL-2.0
/*
* Copyright IBM Corp. 2012,2015
*
+// SPDX-License-Identifier: GPL-2.0
/*
* Copyright IBM Corp. 2012
*
+// SPDX-License-Identifier: GPL-2.0
/*
* s390 specific pci instructions
*
return pte_pfn(pte);
}
-#define __HAVE_ARCH_PMD_WRITE
+#define pmd_write pmd_write
static inline unsigned long pmd_write(pmd_t pmd)
{
pte_t pte = __pte(pmd_val(pmd));
lib-$(CONFIG_SPARC64) += multi3.o
lib-$(CONFIG_SPARC64) += fls.o
lib-$(CONFIG_SPARC64) += fls64.o
-obj-$(CONFIG_SPARC64) += NG4fls.o
+lib-$(CONFIG_SPARC64) += NG4fls.o
lib-$(CONFIG_SPARC64) += copy_page.o clear_page.o bzero.o
lib-$(CONFIG_SPARC64) += csum_copy.o csum_copy_from_user.o csum_copy_to_user.o
if (!(pmd_val(pmd) & _PAGE_VALID))
return 0;
- if (write && !pmd_write(pmd))
+ if (!pmd_access_permitted(pmd, write))
return 0;
refs = 0;
if (!(pud_val(pud) & _PAGE_VALID))
return 0;
- if (write && !pud_write(pud))
+ if (!pud_access_permitted(pud, write))
return 0;
refs = 0;
#define pmd_mkdirty(pmd) pte_pmd(pte_mkdirty(pmd_pte(pmd)))
#define pmd_huge_page(pmd) pte_huge(pmd_pte(pmd))
#define pmd_mkhuge(pmd) pte_pmd(pte_mkhuge(pmd_pte(pmd)))
-#define __HAVE_ARCH_PMD_WRITE
#define pfn_pmd(pfn, pgprot) pte_pmd(pfn_pte((pfn), (pgprot)))
#define pmd_pfn(pmd) pte_pfn(pmd_pte(pmd))
static inline int emulate_instruction(struct kvm_vcpu *vcpu,
int emulation_type)
{
- return x86_emulate_instruction(vcpu, 0, emulation_type, NULL, 0);
+ return x86_emulate_instruction(vcpu, 0,
+ emulation_type | EMULTYPE_NO_REEXECUTE, NULL, 0);
}
void kvm_enable_efer_bits(u64);
unsigned long address, pmd_t *pmdp);
-#define __HAVE_ARCH_PMD_WRITE
+#define pmd_write pmd_write
static inline int pmd_write(pmd_t pmd)
{
return pmd_flags(pmd) & _PAGE_RW;
clear_bit(_PAGE_BIT_RW, (unsigned long *)pmdp);
}
+#define pud_write pud_write
+static inline int pud_write(pud_t pud)
+{
+ return pud_flags(pud) & _PAGE_RW;
+}
+
/*
* clone_pgd_range(pgd_t *dst, pgd_t *src, int count);
*
[CPUID_8086_0001_EDX] = {0x80860001, 0, CPUID_EDX},
[CPUID_1_ECX] = { 1, 0, CPUID_ECX},
[CPUID_C000_0001_EDX] = {0xc0000001, 0, CPUID_EDX},
- [CPUID_8000_0001_ECX] = {0xc0000001, 0, CPUID_ECX},
+ [CPUID_8000_0001_ECX] = {0x80000001, 0, CPUID_ECX},
[CPUID_7_0_EBX] = { 7, 0, CPUID_EBX},
[CPUID_D_1_EAX] = { 0xd, 1, CPUID_EAX},
[CPUID_F_0_EDX] = { 0xf, 0, CPUID_EDX},
fxstate_size(ctxt));
}
+/*
+ * FXRSTOR might restore XMM registers not provided by the guest. Fill
+ * in the host registers (via FXSAVE) instead, so they won't be modified.
+ * (preemption has to stay disabled until FXRSTOR).
+ *
+ * Use noinline to keep the stack for other functions called by callers small.
+ */
+static noinline int fxregs_fixup(struct fxregs_state *fx_state,
+ const size_t used_size)
+{
+ struct fxregs_state fx_tmp;
+ int rc;
+
+ rc = asm_safe("fxsave %[fx]", , [fx] "+m"(fx_tmp));
+ memcpy((void *)fx_state + used_size, (void *)&fx_tmp + used_size,
+ __fxstate_size(16) - used_size);
+
+ return rc;
+}
+
static int em_fxrstor(struct x86_emulate_ctxt *ctxt)
{
struct fxregs_state fx_state;
if (rc != X86EMUL_CONTINUE)
return rc;
+ size = fxstate_size(ctxt);
+ rc = segmented_read_std(ctxt, ctxt->memop.addr.mem, &fx_state, size);
+ if (rc != X86EMUL_CONTINUE)
+ return rc;
+
ctxt->ops->get_fpu(ctxt);
- size = fxstate_size(ctxt);
if (size < __fxstate_size(16)) {
- rc = asm_safe("fxsave %[fx]", , [fx] "+m"(fx_state));
+ rc = fxregs_fixup(&fx_state, size);
if (rc != X86EMUL_CONTINUE)
goto out;
}
- rc = segmented_read_std(ctxt, ctxt->memop.addr.mem, &fx_state, size);
- if (rc != X86EMUL_CONTINUE)
- goto out;
-
if (fx_state.mxcsr >> 16) {
rc = emulate_gp(ctxt, 0);
goto out;
bool op_prefix = false;
bool has_seg_override = false;
struct opcode opcode;
+ u16 dummy;
+ struct desc_struct desc;
ctxt->memop.type = OP_NONE;
ctxt->memopp = NULL;
switch (mode) {
case X86EMUL_MODE_REAL:
case X86EMUL_MODE_VM86:
+ def_op_bytes = def_ad_bytes = 2;
+ ctxt->ops->get_segment(ctxt, &dummy, &desc, NULL, VCPU_SREG_CS);
+ if (desc.d)
+ def_op_bytes = def_ad_bytes = 4;
+ break;
case X86EMUL_MODE_PROT16:
def_op_bytes = def_ad_bytes = 2;
break;
old_irr = ioapic->irr;
ioapic->irr |= mask;
- if (edge)
+ if (edge) {
ioapic->irr_delivered &= ~mask;
- if ((edge && old_irr == ioapic->irr) ||
- (!edge && entry.fields.remote_irr)) {
- ret = 0;
- goto out;
+ if (old_irr == ioapic->irr) {
+ ret = 0;
+ goto out;
+ }
}
ret = ioapic_service(ioapic, irq, line_status);
index == RTC_GSI) {
if (kvm_apic_match_dest(vcpu, NULL, 0,
e->fields.dest_id, e->fields.dest_mode) ||
- (e->fields.trig_mode == IOAPIC_EDGE_TRIG &&
- kvm_apic_pending_eoi(vcpu, e->fields.vector)))
+ kvm_apic_pending_eoi(vcpu, e->fields.vector))
__set_bit(e->fields.vector,
ioapic_handled_vectors);
}
{
unsigned index;
bool mask_before, mask_after;
+ int old_remote_irr, old_delivery_status;
union kvm_ioapic_redirect_entry *e;
switch (ioapic->ioregsel) {
return;
e = &ioapic->redirtbl[index];
mask_before = e->fields.mask;
+ /* Preserve read-only fields */
+ old_remote_irr = e->fields.remote_irr;
+ old_delivery_status = e->fields.delivery_status;
if (ioapic->ioregsel & 1) {
e->bits &= 0xffffffff;
e->bits |= (u64) val << 32;
} else {
e->bits &= ~0xffffffffULL;
e->bits |= (u32) val;
- e->fields.remote_irr = 0;
}
+ e->fields.remote_irr = old_remote_irr;
+ e->fields.delivery_status = old_delivery_status;
+
+ /*
+ * Some OSes (Linux, Xen) assume that Remote IRR bit will
+ * be cleared by IOAPIC hardware when the entry is configured
+ * as edge-triggered. This behavior is used to simulate an
+ * explicit EOI on IOAPICs that don't have the EOI register.
+ */
+ if (e->fields.trig_mode == IOAPIC_EDGE_TRIG)
+ e->fields.remote_irr = 0;
+
mask_after = e->fields.mask;
if (mask_before != mask_after)
kvm_fire_mask_notifiers(ioapic->kvm, KVM_IRQCHIP_IOAPIC, index, mask_after);
struct kvm_lapic_irq irqe;
int ret;
- if (entry->fields.mask)
+ if (entry->fields.mask ||
+ (entry->fields.trig_mode == IOAPIC_LEVEL_TRIG &&
+ entry->fields.remote_irr))
return -1;
ioapic_debug("dest=%x dest_mode=%x delivery_mode=%x "
recalculate_apic_map(apic->vcpu->kvm);
}
+static inline u32 kvm_apic_calc_x2apic_ldr(u32 id)
+{
+ return ((id >> 4) << 16) | (1 << (id & 0xf));
+}
+
static inline void kvm_apic_set_x2apic_id(struct kvm_lapic *apic, u32 id)
{
- u32 ldr = ((id >> 4) << 16) | (1 << (id & 0xf));
+ u32 ldr = kvm_apic_calc_x2apic_ldr(id);
WARN_ON_ONCE(id != apic->vcpu->vcpu_id);
{
if (apic_x2apic_mode(vcpu->arch.apic)) {
u32 *id = (u32 *)(s->regs + APIC_ID);
+ u32 *ldr = (u32 *)(s->regs + APIC_LDR);
if (vcpu->kvm->arch.x2apic_format) {
if (*id != vcpu->vcpu_id)
else
*id <<= 24;
}
+
+ /* In x2APIC mode, the LDR is fixed and based on the id */
+ if (set)
+ *ldr = kvm_apic_calc_x2apic_ldr(*id);
}
return 0;
{
struct vmcb_control_area *c, *h;
struct nested_state *g;
+ u32 h_intercept_exceptions;
mark_dirty(svm->vmcb, VMCB_INTERCEPTS);
h = &svm->nested.hsave->control;
g = &svm->nested;
+ /* No need to intercept #UD if L1 doesn't intercept it */
+ h_intercept_exceptions =
+ h->intercept_exceptions & ~(1U << UD_VECTOR);
+
c->intercept_cr = h->intercept_cr | g->intercept_cr;
c->intercept_dr = h->intercept_dr | g->intercept_dr;
- c->intercept_exceptions = h->intercept_exceptions | g->intercept_exceptions;
+ c->intercept_exceptions =
+ h_intercept_exceptions | g->intercept_exceptions;
c->intercept = h->intercept | g->intercept;
}
{
int er;
+ WARN_ON_ONCE(is_guest_mode(&svm->vcpu));
er = emulate_instruction(&svm->vcpu, EMULTYPE_TRAP_UD);
+ if (er == EMULATE_USER_EXIT)
+ return 0;
if (er != EMULATE_DONE)
kvm_queue_exception(&svm->vcpu, UD_VECTOR);
return 1;
{
u32 eb;
- eb = (1u << PF_VECTOR) | (1u << UD_VECTOR) | (1u << MC_VECTOR) |
+ eb = (1u << PF_VECTOR) | (1u << MC_VECTOR) |
(1u << DB_VECTOR) | (1u << AC_VECTOR);
if ((vcpu->guest_debug &
(KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_USE_SW_BP)) ==
*/
if (is_guest_mode(vcpu))
eb |= get_vmcs12(vcpu)->exception_bitmap;
+ else
+ eb |= 1u << UD_VECTOR;
vmcs_write32(EXCEPTION_BITMAP, eb);
}
vmcs_write64(GUEST_IA32_DEBUGCTL, 0);
}
- vmcs_writel(GUEST_RFLAGS, 0x02);
+ kvm_set_rflags(vcpu, X86_EFLAGS_FIXED);
kvm_rip_write(vcpu, 0xfff0);
vmcs_writel(GUEST_GDTR_BASE, 0);
return 1; /* already handled by vmx_vcpu_run() */
if (is_invalid_opcode(intr_info)) {
- if (is_guest_mode(vcpu)) {
- kvm_queue_exception(vcpu, UD_VECTOR);
- return 1;
- }
+ WARN_ON_ONCE(is_guest_mode(vcpu));
er = emulate_instruction(vcpu, EMULTYPE_TRAP_UD);
+ if (er == EMULATE_USER_EXIT)
+ return 0;
if (er != EMULATE_DONE)
kvm_queue_exception(vcpu, UD_VECTOR);
return 1;
if (kvm_test_request(KVM_REQ_EVENT, vcpu))
return 1;
- err = emulate_instruction(vcpu, EMULTYPE_NO_REEXECUTE);
+ err = emulate_instruction(vcpu, 0);
if (err == EMULATE_USER_EXIT) {
++vcpu->stat.mmio_exits;
*/
static void free_nested(struct vcpu_vmx *vmx)
{
- if (!vmx->nested.vmxon)
+ if (!vmx->nested.vmxon && !vmx->nested.smm.vmxon)
return;
vmx->nested.vmxon = false;
+ vmx->nested.smm.vmxon = false;
free_vpid(vmx->nested.vpid02);
vmx->nested.posted_intr_nv = -1;
vmx->nested.current_vmptr = -1ull;
cr4_fixed1_update(X86_CR4_SMEP, ebx, bit(X86_FEATURE_SMEP));
cr4_fixed1_update(X86_CR4_SMAP, ebx, bit(X86_FEATURE_SMAP));
cr4_fixed1_update(X86_CR4_PKE, ecx, bit(X86_FEATURE_PKU));
- /* TODO: Use X86_CR4_UMIP and X86_FEATURE_UMIP macros */
- cr4_fixed1_update(bit(11), ecx, bit(2));
+ cr4_fixed1_update(X86_CR4_UMIP, ecx, bit(X86_FEATURE_UMIP));
#undef cr4_fixed1_update
}
return 1;
}
+ if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS) &&
+ (is_noncanonical_address(vmcs12->guest_bndcfgs & PAGE_MASK, vcpu) ||
+ (vmcs12->guest_bndcfgs & MSR_IA32_BNDCFGS_RSVD)))
+ return 1;
+
return 0;
}
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
unsigned long exit_qual;
-
- if (kvm_event_needs_reinjection(vcpu))
- return -EBUSY;
+ bool block_nested_events =
+ vmx->nested.nested_run_pending || kvm_event_needs_reinjection(vcpu);
if (vcpu->arch.exception.pending &&
nested_vmx_check_exception(vcpu, &exit_qual)) {
- if (vmx->nested.nested_run_pending)
+ if (block_nested_events)
return -EBUSY;
nested_vmx_inject_exception_vmexit(vcpu, exit_qual);
vcpu->arch.exception.pending = false;
if (nested_cpu_has_preemption_timer(get_vmcs12(vcpu)) &&
vmx->nested.preemption_timer_expired) {
- if (vmx->nested.nested_run_pending)
+ if (block_nested_events)
return -EBUSY;
nested_vmx_vmexit(vcpu, EXIT_REASON_PREEMPTION_TIMER, 0, 0);
return 0;
}
if (vcpu->arch.nmi_pending && nested_exit_on_nmi(vcpu)) {
- if (vmx->nested.nested_run_pending)
+ if (block_nested_events)
return -EBUSY;
nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI,
NMI_VECTOR | INTR_TYPE_NMI_INTR |
if ((kvm_cpu_has_interrupt(vcpu) || external_intr) &&
nested_exit_on_intr(vcpu)) {
- if (vmx->nested.nested_run_pending)
+ if (block_nested_events)
return -EBUSY;
nested_vmx_vmexit(vcpu, EXIT_REASON_EXTERNAL_INTERRUPT, 0, 0);
return 0;
kvm_clear_interrupt_queue(vcpu);
}
+static void load_vmcs12_mmu_host_state(struct kvm_vcpu *vcpu,
+ struct vmcs12 *vmcs12)
+{
+ u32 entry_failure_code;
+
+ nested_ept_uninit_mmu_context(vcpu);
+
+ /*
+ * Only PDPTE load can fail as the value of cr3 was checked on entry and
+ * couldn't have changed.
+ */
+ if (nested_vmx_load_cr3(vcpu, vmcs12->host_cr3, false, &entry_failure_code))
+ nested_vmx_abort(vcpu, VMX_ABORT_LOAD_HOST_PDPTE_FAIL);
+
+ if (!enable_ept)
+ vcpu->arch.walk_mmu->inject_page_fault = kvm_inject_page_fault;
+}
+
/*
* A part of what we need to when the nested L2 guest exits and we want to
* run its L1 parent, is to reset L1's guest state to the host state specified
struct vmcs12 *vmcs12)
{
struct kvm_segment seg;
- u32 entry_failure_code;
if (vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_EFER)
vcpu->arch.efer = vmcs12->host_ia32_efer;
vcpu->arch.cr4_guest_owned_bits = ~vmcs_readl(CR4_GUEST_HOST_MASK);
vmx_set_cr4(vcpu, vmcs12->host_cr4);
- nested_ept_uninit_mmu_context(vcpu);
-
- /*
- * Only PDPTE load can fail as the value of cr3 was checked on entry and
- * couldn't have changed.
- */
- if (nested_vmx_load_cr3(vcpu, vmcs12->host_cr3, false, &entry_failure_code))
- nested_vmx_abort(vcpu, VMX_ABORT_LOAD_HOST_PDPTE_FAIL);
-
- if (!enable_ept)
- vcpu->arch.walk_mmu->inject_page_fault = kvm_inject_page_fault;
+ load_vmcs12_mmu_host_state(vcpu, vmcs12);
if (enable_vpid) {
/*
* accordingly.
*/
nested_vmx_failValid(vcpu, VMXERR_ENTRY_INVALID_CONTROL_FIELD);
+
+ load_vmcs12_mmu_host_state(vcpu, vmcs12);
+
/*
* The emulated instruction was already skipped in
* nested_vmx_run, but the updated RIP was never
static bool __read_mostly ignore_msrs = 0;
module_param(ignore_msrs, bool, S_IRUGO | S_IWUSR);
+static bool __read_mostly report_ignored_msrs = true;
+module_param(report_ignored_msrs, bool, S_IRUGO | S_IWUSR);
+
unsigned int min_timer_period_us = 500;
module_param(min_timer_period_us, uint, S_IRUGO | S_IWUSR);
/* both __this_cpu_read() and rdtsc() should be on the same cpu */
get_cpu();
- kvm_get_time_scale(NSEC_PER_SEC, __this_cpu_read(cpu_tsc_khz) * 1000LL,
- &hv_clock.tsc_shift,
- &hv_clock.tsc_to_system_mul);
- ret = __pvclock_read_cycles(&hv_clock, rdtsc());
+ if (__this_cpu_read(cpu_tsc_khz)) {
+ kvm_get_time_scale(NSEC_PER_SEC, __this_cpu_read(cpu_tsc_khz) * 1000LL,
+ &hv_clock.tsc_shift,
+ &hv_clock.tsc_to_system_mul);
+ ret = __pvclock_read_cycles(&hv_clock, rdtsc());
+ } else
+ ret = ktime_get_boot_ns() + ka->kvmclock_offset;
put_cpu();
*/
BUILD_BUG_ON(offsetof(struct pvclock_vcpu_time_info, version) != 0);
+ if (guest_hv_clock.version & 1)
+ ++guest_hv_clock.version; /* first time write, random junk */
+
vcpu->hv_clock.version = guest_hv_clock.version + 1;
kvm_write_guest_cached(v->kvm, &vcpu->pv_time,
&vcpu->hv_clock,
/* Drop writes to this legacy MSR -- see rdmsr
* counterpart for further detail.
*/
- vcpu_unimpl(vcpu, "ignored wrmsr: 0x%x data 0x%llx\n", msr, data);
+ if (report_ignored_msrs)
+ vcpu_unimpl(vcpu, "ignored wrmsr: 0x%x data 0x%llx\n",
+ msr, data);
break;
case MSR_AMD64_OSVW_ID_LENGTH:
if (!guest_cpuid_has(vcpu, X86_FEATURE_OSVW))
msr, data);
return 1;
} else {
- vcpu_unimpl(vcpu, "ignored wrmsr: 0x%x data 0x%llx\n",
- msr, data);
+ if (report_ignored_msrs)
+ vcpu_unimpl(vcpu,
+ "ignored wrmsr: 0x%x data 0x%llx\n",
+ msr, data);
break;
}
}
msr_info->index);
return 1;
} else {
- vcpu_unimpl(vcpu, "ignored rdmsr: 0x%x\n", msr_info->index);
+ if (report_ignored_msrs)
+ vcpu_unimpl(vcpu, "ignored rdmsr: 0x%x\n",
+ msr_info->index);
msr_info->data = 0;
}
break;
vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION;
vcpu->run->internal.ndata = 0;
- r = EMULATE_FAIL;
+ r = EMULATE_USER_EXIT;
}
kvm_queue_exception(vcpu, UD_VECTOR);
if (reexecute_instruction(vcpu, cr2, write_fault_to_spt,
emulation_type))
return EMULATE_DONE;
+ if (ctxt->have_exception && inject_emulated_exception(vcpu))
+ return EMULATE_DONE;
if (emulation_type & EMULTYPE_SKIP)
return EMULATE_FAIL;
return handle_emulation_failure(vcpu);
{
struct fpu *fpu = ¤t->thread.fpu;
int r;
- sigset_t sigsaved;
fpu__initialize(fpu);
- if (vcpu->sigset_active)
- sigprocmask(SIG_SETMASK, &vcpu->sigset, &sigsaved);
+ kvm_sigset_activate(vcpu);
if (unlikely(vcpu->arch.mp_state == KVM_MP_STATE_UNINITIALIZED)) {
if (kvm_run->immediate_exit) {
out:
post_kvm_run_save(vcpu);
- if (vcpu->sigset_active)
- sigprocmask(SIG_SETMASK, &sigsaved, NULL);
+ kvm_sigset_deactivate(vcpu);
return r;
}
struct bio *bio_split(struct bio *bio, int sectors,
gfp_t gfp, struct bio_set *bs)
{
- struct bio *split = NULL;
+ struct bio *split;
BUG_ON(sectors <= 0);
BUG_ON(sectors >= bio_sectors(bio));
ret = wbt_init(q);
if (ret)
return ret;
-
- rwb = q->rq_wb;
- if (!rwb)
- return -EINVAL;
}
+ rwb = q->rq_wb;
if (val == -1)
rwb->min_lat_nsec = wbt_default_latency_nsec(q);
else if (val >= 0)
if (wbt_is_read(stat))
wb_timestamp(rwb, &rwb->last_comp);
- wbt_clear_state(stat);
} else {
WARN_ON_ONCE(stat == rwb->sync_cookie);
__wbt_done(rwb, wbt_stat_to_mask(stat));
- wbt_clear_state(stat);
}
+ wbt_clear_state(stat);
}
/*
/*
* At this point we know it's a buffered write. If this is
- * kswapd trying to free memory, or REQ_SYNC is set, set, then
+ * kswapd trying to free memory, or REQ_SYNC is set, then
* it's WB_SYNC_ALL writeback, and we'll use the max limit for
* that. If the write is marked as a background write, then use
* the idle limit, or go to normal if we haven't had competing
init_waitqueue_head(&rwb->rq_wait[i].wait);
}
- rwb->wc = 1;
- rwb->queue_depth = RWB_DEF_DEPTH;
rwb->last_comp = rwb->last_issue = jiffies;
rwb->queue = q;
rwb->win_nsec = RWB_WINDOW_NSEC;
disk->flags |= GENHD_FL_SUPPRESS_PARTITION_INFO;
disk->flags |= GENHD_FL_NO_PART_SCAN;
} else {
+ int ret;
+
/* Register BDI before referencing it from bdev */
disk_to_dev(disk)->devt = devt;
- bdi_register_owner(disk->queue->backing_dev_info,
- disk_to_dev(disk));
+ ret = bdi_register_owner(disk->queue->backing_dev_info,
+ disk_to_dev(disk));
+ WARN_ON(ret);
blk_register_region(disk_devt(disk), disk->minors, NULL,
exact_match, exact_lock, disk);
}
if (minors > DISK_MAX_PARTS) {
printk(KERN_ERR
- "block: can't allocated more than %d partitions\n",
+ "block: can't allocate more than %d partitions\n",
DISK_MAX_PARTS);
minors = DISK_MAX_PARTS;
}
EXPORT_SYMBOL_GPL(af_alg_sendpage);
/**
+ * af_alg_free_resources - release resources required for crypto request
+ */
+void af_alg_free_resources(struct af_alg_async_req *areq)
+{
+ struct sock *sk = areq->sk;
+
+ af_alg_free_areq_sgls(areq);
+ sock_kfree_s(sk, areq, areq->areqlen);
+}
+EXPORT_SYMBOL_GPL(af_alg_free_resources);
+
+/**
* af_alg_async_cb - AIO callback handler
*
* This handler cleans up the struct af_alg_async_req upon completion of the
struct kiocb *iocb = areq->iocb;
unsigned int resultlen;
- lock_sock(sk);
-
/* Buffer size written by crypto operation. */
resultlen = areq->outlen;
- af_alg_free_areq_sgls(areq);
- sock_kfree_s(sk, areq, areq->areqlen);
- __sock_put(sk);
+ af_alg_free_resources(areq);
+ sock_put(sk);
iocb->ki_complete(iocb, err ? err : resultlen, 0);
-
- release_sock(sk);
}
EXPORT_SYMBOL_GPL(af_alg_async_cb);
struct aead_tfm *aeadc = pask->private;
struct crypto_aead *tfm = aeadc->aead;
struct crypto_skcipher *null_tfm = aeadc->null_tfm;
- unsigned int as = crypto_aead_authsize(tfm);
+ unsigned int i, as = crypto_aead_authsize(tfm);
struct af_alg_async_req *areq;
- struct af_alg_tsgl *tsgl;
- struct scatterlist *src;
+ struct af_alg_tsgl *tsgl, *tmp;
+ struct scatterlist *rsgl_src, *tsgl_src = NULL;
int err = 0;
size_t used = 0; /* [in] TX bufs to be en/decrypted */
size_t outlen = 0; /* [out] RX bufs produced by kernel */
}
processed = used + ctx->aead_assoclen;
- tsgl = list_first_entry(&ctx->tsgl_list, struct af_alg_tsgl, list);
+ list_for_each_entry_safe(tsgl, tmp, &ctx->tsgl_list, list) {
+ for (i = 0; i < tsgl->cur; i++) {
+ struct scatterlist *process_sg = tsgl->sg + i;
+
+ if (!(process_sg->length) || !sg_page(process_sg))
+ continue;
+ tsgl_src = process_sg;
+ break;
+ }
+ if (tsgl_src)
+ break;
+ }
+ if (processed && !tsgl_src) {
+ err = -EFAULT;
+ goto free;
+ }
/*
* Copy of AAD from source to destination
*/
/* Use the RX SGL as source (and destination) for crypto op. */
- src = areq->first_rsgl.sgl.sg;
+ rsgl_src = areq->first_rsgl.sgl.sg;
if (ctx->enc) {
/*
* v v
* RX SGL: AAD || PT || Tag
*/
- err = crypto_aead_copy_sgl(null_tfm, tsgl->sg,
+ err = crypto_aead_copy_sgl(null_tfm, tsgl_src,
areq->first_rsgl.sgl.sg, processed);
if (err)
goto free;
*/
/* Copy AAD || CT to RX SGL buffer for in-place operation. */
- err = crypto_aead_copy_sgl(null_tfm, tsgl->sg,
+ err = crypto_aead_copy_sgl(null_tfm, tsgl_src,
areq->first_rsgl.sgl.sg, outlen);
if (err)
goto free;
areq->tsgl);
} else
/* no RX SGL present (e.g. authentication only) */
- src = areq->tsgl;
+ rsgl_src = areq->tsgl;
}
/* Initialize the crypto operation */
- aead_request_set_crypt(&areq->cra_u.aead_req, src,
+ aead_request_set_crypt(&areq->cra_u.aead_req, rsgl_src,
areq->first_rsgl.sgl.sg, used, ctx->iv);
aead_request_set_ad(&areq->cra_u.aead_req, ctx->aead_assoclen);
aead_request_set_tfm(&areq->cra_u.aead_req, tfm);
if (msg->msg_iocb && !is_sync_kiocb(msg->msg_iocb)) {
/* AIO operation */
+ sock_hold(sk);
areq->iocb = msg->msg_iocb;
aead_request_set_callback(&areq->cra_u.aead_req,
CRYPTO_TFM_REQ_MAY_BACKLOG,
af_alg_async_cb, areq);
err = ctx->enc ? crypto_aead_encrypt(&areq->cra_u.aead_req) :
crypto_aead_decrypt(&areq->cra_u.aead_req);
+
+ /* AIO operation in progress */
+ if (err == -EINPROGRESS || err == -EBUSY) {
+ /* Remember output size that will be generated. */
+ areq->outlen = outlen;
+
+ return -EIOCBQUEUED;
+ }
+
+ sock_put(sk);
} else {
/* Synchronous operation */
aead_request_set_callback(&areq->cra_u.aead_req,
&ctx->wait);
}
- /* AIO operation in progress */
- if (err == -EINPROGRESS) {
- sock_hold(sk);
-
- /* Remember output size that will be generated. */
- areq->outlen = outlen;
-
- return -EIOCBQUEUED;
- }
free:
- af_alg_free_areq_sgls(areq);
- sock_kfree_s(sk, areq, areq->areqlen);
+ af_alg_free_resources(areq);
return err ? err : outlen;
}
if (msg->msg_iocb && !is_sync_kiocb(msg->msg_iocb)) {
/* AIO operation */
+ sock_hold(sk);
areq->iocb = msg->msg_iocb;
skcipher_request_set_callback(&areq->cra_u.skcipher_req,
CRYPTO_TFM_REQ_MAY_SLEEP,
err = ctx->enc ?
crypto_skcipher_encrypt(&areq->cra_u.skcipher_req) :
crypto_skcipher_decrypt(&areq->cra_u.skcipher_req);
+
+ /* AIO operation in progress */
+ if (err == -EINPROGRESS || err == -EBUSY) {
+ /* Remember output size that will be generated. */
+ areq->outlen = len;
+
+ return -EIOCBQUEUED;
+ }
+
+ sock_put(sk);
} else {
/* Synchronous operation */
skcipher_request_set_callback(&areq->cra_u.skcipher_req,
&ctx->wait);
}
- /* AIO operation in progress */
- if (err == -EINPROGRESS) {
- sock_hold(sk);
-
- /* Remember output size that will be generated. */
- areq->outlen = len;
-
- return -EIOCBQUEUED;
- }
free:
- af_alg_free_areq_sgls(areq);
- sock_kfree_s(sk, areq, areq->areqlen);
+ af_alg_free_resources(areq);
return err ? err : len;
}
scatterwalk_copychunks(NULL, &walk->in, req->assoclen, 2);
scatterwalk_copychunks(NULL, &walk->out, req->assoclen, 2);
+ scatterwalk_done(&walk->in, 0, walk->total);
+ scatterwalk_done(&walk->out, 0, walk->total);
+
walk->iv = req->iv;
walk->oiv = req->iv;
int count;
struct acpi_hardware_id *id;
+ /* Avoid unnecessarily loading modules for non present devices. */
+ if (!acpi_device_is_present(acpi_dev))
+ return 0;
+
/*
* Since we skip ACPI_DT_NAMESPACE_HID from the modalias below, 0 should
* be returned if ACPI_DT_NAMESPACE_HID is the only ACPI/PNP ID in the
{
struct acpi_ec *ec = NULL;
int ret;
+ bool is_ecdt = false;
+ acpi_status status;
strcpy(acpi_device_name(device), ACPI_EC_DEVICE_NAME);
strcpy(acpi_device_class(device), ACPI_EC_CLASS);
- ec = acpi_ec_alloc();
- if (!ec)
- return -ENOMEM;
- if (ec_parse_device(device->handle, 0, ec, NULL) !=
- AE_CTRL_TERMINATE) {
+ if (!strcmp(acpi_device_hid(device), ACPI_ECDT_HID)) {
+ is_ecdt = true;
+ ec = boot_ec;
+ } else {
+ ec = acpi_ec_alloc();
+ if (!ec)
+ return -ENOMEM;
+ status = ec_parse_device(device->handle, 0, ec, NULL);
+ if (status != AE_CTRL_TERMINATE) {
ret = -EINVAL;
goto err_alloc;
+ }
}
if (acpi_is_boot_ec(ec)) {
- boot_ec_is_ecdt = false;
- /*
- * Trust PNP0C09 namespace location rather than ECDT ID.
- *
- * But trust ECDT GPE rather than _GPE because of ASUS quirks,
- * so do not change boot_ec->gpe to ec->gpe.
- */
- boot_ec->handle = ec->handle;
- acpi_handle_debug(ec->handle, "duplicated.\n");
- acpi_ec_free(ec);
- ec = boot_ec;
- ret = acpi_config_boot_ec(ec, ec->handle, true, false);
+ boot_ec_is_ecdt = is_ecdt;
+ if (!is_ecdt) {
+ /*
+ * Trust PNP0C09 namespace location rather than
+ * ECDT ID. But trust ECDT GPE rather than _GPE
+ * because of ASUS quirks, so do not change
+ * boot_ec->gpe to ec->gpe.
+ */
+ boot_ec->handle = ec->handle;
+ acpi_handle_debug(ec->handle, "duplicated.\n");
+ acpi_ec_free(ec);
+ ec = boot_ec;
+ }
+ ret = acpi_config_boot_ec(ec, ec->handle, true, is_ecdt);
} else
ret = acpi_ec_setup(ec, true);
if (ret)
ret = !!request_region(ec->command_addr, 1, "EC cmd");
WARN(!ret, "Could not request EC cmd io port 0x%lx", ec->command_addr);
- /* Reprobe devices depending on the EC */
- acpi_walk_dep_device_list(ec->handle);
+ if (!is_ecdt) {
+ /* Reprobe devices depending on the EC */
+ acpi_walk_dep_device_list(ec->handle);
+ }
acpi_handle_debug(ec->handle, "enumerated.\n");
return 0;
static const struct acpi_device_id ec_device_ids[] = {
{"PNP0C09", 0},
+ {ACPI_ECDT_HID, 0},
{"", 0},
};
* Note: ec->handle can be valid if this function is called after
* acpi_ec_add(), hence the fast path.
*/
- if (boot_ec->handle != ACPI_ROOT_OBJECT)
- handle = boot_ec->handle;
- else if (!acpi_ec_ecdt_get_handle(&handle))
- return -ENODEV;
- return acpi_config_boot_ec(boot_ec, handle, true, true);
+ if (boot_ec->handle == ACPI_ROOT_OBJECT) {
+ if (!acpi_ec_ecdt_get_handle(&handle))
+ return -ENODEV;
+ boot_ec->handle = handle;
+ }
+
+ /* Register to ACPI bus with PM ops attached */
+ return acpi_bus_register_early_device(ACPI_BUS_TYPE_ECDT_EC);
}
#if 0
/* Drivers must be started after acpi_ec_query_init() */
dsdt_fail = acpi_bus_register_driver(&acpi_ec_driver);
+ /*
+ * Register ECDT to ACPI bus only when PNP0C09 probe fails. This is
+ * useful for platforms (confirmed on ASUS X550ZE) with valid ECDT
+ * settings but invalid DSDT settings.
+ * https://bugzilla.kernel.org/show_bug.cgi?id=196847
+ */
ecdt_fail = acpi_ec_ecdt_start();
return ecdt_fail && dsdt_fail ? -ENODEV : 0;
}
bool acpi_device_is_battery(struct acpi_device *adev);
bool acpi_device_is_first_physical_node(struct acpi_device *adev,
const struct device *dev);
+int acpi_bus_register_early_device(int type);
/* --------------------------------------------------------------------------
Device Matching and Notification
case ACPI_BUS_TYPE_SLEEP_BUTTON:
strcpy(device->pnp.bus_id, "SLPF");
break;
+ case ACPI_BUS_TYPE_ECDT_EC:
+ strcpy(device->pnp.bus_id, "ECDT");
+ break;
default:
acpi_get_name(device->handle, ACPI_SINGLE_NAME, &buffer);
/* Clean up trailing underscores (if any) */
case ACPI_BUS_TYPE_SLEEP_BUTTON:
acpi_add_id(pnp, ACPI_BUTTON_HID_SLEEPF);
break;
+ case ACPI_BUS_TYPE_ECDT_EC:
+ acpi_add_id(pnp, ACPI_ECDT_HID);
+ break;
}
}
}
EXPORT_SYMBOL_GPL(acpi_bus_trim);
+int acpi_bus_register_early_device(int type)
+{
+ struct acpi_device *device = NULL;
+ int result;
+
+ result = acpi_add_single_object(&device, NULL,
+ type, ACPI_STA_DEFAULT);
+ if (result)
+ return result;
+
+ device->flags.match_driver = true;
+ return device_attach(&device->dev);
+}
+EXPORT_SYMBOL_GPL(acpi_bus_register_early_device);
+
static int acpi_bus_scan_fixed(void)
{
int result = 0;
PRINTD (DBG_INFO, "registered Madge ATM adapter (no. %d) (%p) at %p",
dev->atm_dev->number, dev, dev->atm_dev);
- dev->atm_dev->dev_data = (void *) dev;
+ dev->atm_dev->dev_data = (void *) dev;
// register our address
amb_esi (dev, dev->atm_dev->esi);
ASSERT(fore200e_vcc);
len = sprintf(page,
- " %08x %03d %05d %1d %09lu %05d/%05d %09lu %05d/%05d\n",
- (u32)(unsigned long)vcc,
+ " %pK %03d %05d %1d %09lu %05d/%05d %09lu %05d/%05d\n",
+ vcc,
vcc->vpi, vcc->vci, fore200e_atm2fore_aal(vcc->qos.aal),
fore200e_vcc->tx_pdu,
fore200e_vcc->tx_min_pdu > 0xFFFF ? 0 : fore200e_vcc->tx_min_pdu,
lanai->pci);
if (unlikely(lanai->service.start == NULL))
return -ENOMEM;
- DPRINTK("allocated service buffer at 0x%08lX, size %zu(%d)\n",
- (unsigned long) lanai->service.start,
+ DPRINTK("allocated service buffer at %p, size %zu(%d)\n",
+ lanai->service.start,
lanai_buf_size(&lanai->service),
lanai_buf_size_cardorder(&lanai->service));
/* Clear ServWrite register to be safe */
#endif
memcpy(atmdev->esi, eeprom_mac(lanai), ESI_LEN);
lanai_timed_poll_start(lanai);
- printk(KERN_NOTICE DEV_LABEL "(itf %d): rev.%d, base=0x%lx, irq=%u "
+ printk(KERN_NOTICE DEV_LABEL "(itf %d): rev.%d, base=%p, irq=%u "
"(%pMF)\n", lanai->number, (int) lanai->pci->revision,
- (unsigned long) lanai->base, lanai->pci->irq, atmdev->esi);
+ lanai->base, lanai->pci->irq, atmdev->esi);
printk(KERN_NOTICE DEV_LABEL "(itf %d): LANAI%s, serialno=%u(0x%X), "
"board_rev=%d\n", lanai->number,
lanai->type==lanai2 ? "2" : "HB", (unsigned int) lanai->serialno,
default:
return -EINVAL;
}
- dev->ops->phy_put(dev, control, reg);
+ dev->ops->phy_put(dev, control, reg);
PRIV(dev)->loop_mode = mode;
return 0;
}
config IMG_ASCII_LCD
tristate "Imagination Technologies ASCII LCD Display"
+ depends on HAS_IOMEM
default y if MIPS_MALTA || MIPS_SEAD3
select SYSCON
help
{
struct nullb_device *dev = to_nullb_device(item);
- badblocks_exit(&dev->badblocks);
null_free_device_storage(dev, false);
null_free_dev(dev);
}
static void null_free_dev(struct nullb_device *dev)
{
+ if (!dev)
+ return;
+
+ badblocks_exit(&dev->badblocks);
kfree(dev);
}
config LOONGSON2_CPUFREQ
tristate "Loongson2 CPUFreq Driver"
+ depends on LEMOTE_MACH2F
help
This option adds a CPUFreq driver for loongson processors which
support software configurable cpu frequency.
config LOONGSON1_CPUFREQ
tristate "Loongson1 CPUFreq Driver"
+ depends on LOONGSON1_LS1B
help
This option adds a CPUFreq driver for loongson1 processors which
support software configurable cpu frequency.
return 0;
}
device_initcall(mtk_cpufreq_driver_init);
+
+MODULE_DESCRIPTION("MediaTek CPUFreq driver");
+MODULE_AUTHOR("Pi-Cheng Chen <pi-cheng.chen@linaro.org>");
+MODULE_LICENSE("GPL v2");
return dev_dax_huge_fault(vmf, PE_SIZE_PTE);
}
+static int dev_dax_split(struct vm_area_struct *vma, unsigned long addr)
+{
+ struct file *filp = vma->vm_file;
+ struct dev_dax *dev_dax = filp->private_data;
+ struct dax_region *dax_region = dev_dax->region;
+
+ if (!IS_ALIGNED(addr, dax_region->align))
+ return -EINVAL;
+ return 0;
+}
+
static const struct vm_operations_struct dax_vm_ops = {
.fault = dev_dax_fault,
.huge_fault = dev_dax_huge_fault,
+ .split = dev_dax_split,
};
static int dax_mmap(struct file *filp, struct vm_area_struct *vma)
struct amdgpu_queue_mgr *mgr);
int amdgpu_queue_mgr_map(struct amdgpu_device *adev,
struct amdgpu_queue_mgr *mgr,
- int hw_ip, int instance, int ring,
+ u32 hw_ip, u32 instance, u32 ring,
struct amdgpu_ring **out_ring);
/*
/* sdma */
struct amdgpu_sdma sdma;
- union {
- struct {
- /* uvd */
- struct amdgpu_uvd uvd;
+ /* uvd */
+ struct amdgpu_uvd uvd;
- /* vce */
- struct amdgpu_vce vce;
- };
+ /* vce */
+ struct amdgpu_vce vce;
- /* vcn */
- struct amdgpu_vcn vcn;
- };
+ /* vcn */
+ struct amdgpu_vcn vcn;
/* firmwares */
struct amdgpu_firmware firmware;
{
struct amdgpu_device *adev = get_amdgpu_device(kgd);
struct cik_sdma_rlc_registers *m;
+ unsigned long end_jiffies;
uint32_t sdma_base_addr;
+ uint32_t data;
m = get_sdma_mqd(mqd);
sdma_base_addr = get_sdma_base_addr(m);
- WREG32(sdma_base_addr + mmSDMA0_RLC0_VIRTUAL_ADDR,
- m->sdma_rlc_virtual_addr);
+ WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_CNTL,
+ m->sdma_rlc_rb_cntl & (~SDMA0_RLC0_RB_CNTL__RB_ENABLE_MASK));
- WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_BASE,
- m->sdma_rlc_rb_base);
+ end_jiffies = msecs_to_jiffies(2000) + jiffies;
+ while (true) {
+ data = RREG32(sdma_base_addr + mmSDMA0_RLC0_CONTEXT_STATUS);
+ if (data & SDMA0_RLC0_CONTEXT_STATUS__IDLE_MASK)
+ break;
+ if (time_after(jiffies, end_jiffies))
+ return -ETIME;
+ usleep_range(500, 1000);
+ }
+ if (m->sdma_engine_id) {
+ data = RREG32(mmSDMA1_GFX_CONTEXT_CNTL);
+ data = REG_SET_FIELD(data, SDMA1_GFX_CONTEXT_CNTL,
+ RESUME_CTX, 0);
+ WREG32(mmSDMA1_GFX_CONTEXT_CNTL, data);
+ } else {
+ data = RREG32(mmSDMA0_GFX_CONTEXT_CNTL);
+ data = REG_SET_FIELD(data, SDMA0_GFX_CONTEXT_CNTL,
+ RESUME_CTX, 0);
+ WREG32(mmSDMA0_GFX_CONTEXT_CNTL, data);
+ }
+ WREG32(sdma_base_addr + mmSDMA0_RLC0_DOORBELL,
+ m->sdma_rlc_doorbell);
+ WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_RPTR, 0);
+ WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_WPTR, 0);
+ WREG32(sdma_base_addr + mmSDMA0_RLC0_VIRTUAL_ADDR,
+ m->sdma_rlc_virtual_addr);
+ WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_BASE, m->sdma_rlc_rb_base);
WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_BASE_HI,
m->sdma_rlc_rb_base_hi);
-
WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_RPTR_ADDR_LO,
m->sdma_rlc_rb_rptr_addr_lo);
-
WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_RPTR_ADDR_HI,
m->sdma_rlc_rb_rptr_addr_hi);
-
- WREG32(sdma_base_addr + mmSDMA0_RLC0_DOORBELL,
- m->sdma_rlc_doorbell);
-
WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_CNTL,
m->sdma_rlc_rb_cntl);
}
WREG32(sdma_base_addr + mmSDMA0_RLC0_DOORBELL, 0);
- WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_RPTR, 0);
- WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_WPTR, 0);
- WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_BASE, 0);
+ WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_CNTL,
+ RREG32(sdma_base_addr + mmSDMA0_RLC0_RB_CNTL) |
+ SDMA0_RLC0_RB_CNTL__RB_ENABLE_MASK);
return 0;
}
if (candidate->robj == validated)
break;
+ /* We can't move pinned BOs here */
+ if (bo->pin_count)
+ continue;
+
other = amdgpu_mem_type_to_domain(bo->tbo.mem.mem_type);
/* Check if this BO is in one of the domains we need space for */
adev->ip_blocks[i].status.hw = false;
}
- if (adev->firmware.load_type == AMDGPU_FW_LOAD_SMU)
- amdgpu_ucode_fini_bo(adev);
-
for (i = adev->num_ip_blocks - 1; i >= 0; i--) {
if (!adev->ip_blocks[i].status.sw)
continue;
{0x1002, 0x686c, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VEGA10},
{0x1002, 0x687f, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VEGA10},
/* Raven */
- {0x1002, 0x15dd, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RAVEN|AMD_IS_APU|AMD_EXP_HW_SUPPORT},
+ {0x1002, 0x15dd, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RAVEN|AMD_IS_APU},
{0, 0, 0}
};
ret = adev->powerplay.ip_funcs->hw_fini(
adev->powerplay.pp_handle);
+ if (adev->firmware.load_type == AMDGPU_FW_LOAD_SMU)
+ amdgpu_ucode_fini_bo(adev);
+
return ret;
}
if (adev->firmware.load_type != AMDGPU_FW_LOAD_PSP)
return 0;
+ amdgpu_ucode_fini_bo(adev);
+
psp_ring_destroy(psp, PSP_RING_TYPE__KM);
amdgpu_bo_free_kernel(&psp->tmr_bo, &psp->tmr_mc_addr, &psp->tmr_buf);
static int amdgpu_identity_map(struct amdgpu_device *adev,
struct amdgpu_queue_mapper *mapper,
- int ring,
+ u32 ring,
struct amdgpu_ring **out_ring)
{
switch (mapper->hw_ip) {
static int amdgpu_lru_map(struct amdgpu_device *adev,
struct amdgpu_queue_mapper *mapper,
- int user_ring, bool lru_pipe_order,
+ u32 user_ring, bool lru_pipe_order,
struct amdgpu_ring **out_ring)
{
int r, i, j;
*/
int amdgpu_queue_mgr_map(struct amdgpu_device *adev,
struct amdgpu_queue_mgr *mgr,
- int hw_ip, int instance, int ring,
+ u32 hw_ip, u32 instance, u32 ring,
struct amdgpu_ring **out_ring)
{
int r, ip_num_rings;
{mmPA_SC_RASTER_CONFIG_1, true},
};
-static uint32_t cik_read_indexed_register(struct amdgpu_device *adev,
- u32 se_num, u32 sh_num,
- u32 reg_offset)
+
+static uint32_t cik_get_register_value(struct amdgpu_device *adev,
+ bool indexed, u32 se_num,
+ u32 sh_num, u32 reg_offset)
{
- uint32_t val;
+ if (indexed) {
+ uint32_t val;
+ unsigned se_idx = (se_num == 0xffffffff) ? 0 : se_num;
+ unsigned sh_idx = (sh_num == 0xffffffff) ? 0 : sh_num;
+
+ switch (reg_offset) {
+ case mmCC_RB_BACKEND_DISABLE:
+ return adev->gfx.config.rb_config[se_idx][sh_idx].rb_backend_disable;
+ case mmGC_USER_RB_BACKEND_DISABLE:
+ return adev->gfx.config.rb_config[se_idx][sh_idx].user_rb_backend_disable;
+ case mmPA_SC_RASTER_CONFIG:
+ return adev->gfx.config.rb_config[se_idx][sh_idx].raster_config;
+ case mmPA_SC_RASTER_CONFIG_1:
+ return adev->gfx.config.rb_config[se_idx][sh_idx].raster_config_1;
+ }
- mutex_lock(&adev->grbm_idx_mutex);
- if (se_num != 0xffffffff || sh_num != 0xffffffff)
- amdgpu_gfx_select_se_sh(adev, se_num, sh_num, 0xffffffff);
+ mutex_lock(&adev->grbm_idx_mutex);
+ if (se_num != 0xffffffff || sh_num != 0xffffffff)
+ amdgpu_gfx_select_se_sh(adev, se_num, sh_num, 0xffffffff);
- val = RREG32(reg_offset);
+ val = RREG32(reg_offset);
- if (se_num != 0xffffffff || sh_num != 0xffffffff)
- amdgpu_gfx_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff);
- mutex_unlock(&adev->grbm_idx_mutex);
- return val;
+ if (se_num != 0xffffffff || sh_num != 0xffffffff)
+ amdgpu_gfx_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff);
+ mutex_unlock(&adev->grbm_idx_mutex);
+ return val;
+ } else {
+ unsigned idx;
+
+ switch (reg_offset) {
+ case mmGB_ADDR_CONFIG:
+ return adev->gfx.config.gb_addr_config;
+ case mmMC_ARB_RAMCFG:
+ return adev->gfx.config.mc_arb_ramcfg;
+ case mmGB_TILE_MODE0:
+ case mmGB_TILE_MODE1:
+ case mmGB_TILE_MODE2:
+ case mmGB_TILE_MODE3:
+ case mmGB_TILE_MODE4:
+ case mmGB_TILE_MODE5:
+ case mmGB_TILE_MODE6:
+ case mmGB_TILE_MODE7:
+ case mmGB_TILE_MODE8:
+ case mmGB_TILE_MODE9:
+ case mmGB_TILE_MODE10:
+ case mmGB_TILE_MODE11:
+ case mmGB_TILE_MODE12:
+ case mmGB_TILE_MODE13:
+ case mmGB_TILE_MODE14:
+ case mmGB_TILE_MODE15:
+ case mmGB_TILE_MODE16:
+ case mmGB_TILE_MODE17:
+ case mmGB_TILE_MODE18:
+ case mmGB_TILE_MODE19:
+ case mmGB_TILE_MODE20:
+ case mmGB_TILE_MODE21:
+ case mmGB_TILE_MODE22:
+ case mmGB_TILE_MODE23:
+ case mmGB_TILE_MODE24:
+ case mmGB_TILE_MODE25:
+ case mmGB_TILE_MODE26:
+ case mmGB_TILE_MODE27:
+ case mmGB_TILE_MODE28:
+ case mmGB_TILE_MODE29:
+ case mmGB_TILE_MODE30:
+ case mmGB_TILE_MODE31:
+ idx = (reg_offset - mmGB_TILE_MODE0);
+ return adev->gfx.config.tile_mode_array[idx];
+ case mmGB_MACROTILE_MODE0:
+ case mmGB_MACROTILE_MODE1:
+ case mmGB_MACROTILE_MODE2:
+ case mmGB_MACROTILE_MODE3:
+ case mmGB_MACROTILE_MODE4:
+ case mmGB_MACROTILE_MODE5:
+ case mmGB_MACROTILE_MODE6:
+ case mmGB_MACROTILE_MODE7:
+ case mmGB_MACROTILE_MODE8:
+ case mmGB_MACROTILE_MODE9:
+ case mmGB_MACROTILE_MODE10:
+ case mmGB_MACROTILE_MODE11:
+ case mmGB_MACROTILE_MODE12:
+ case mmGB_MACROTILE_MODE13:
+ case mmGB_MACROTILE_MODE14:
+ case mmGB_MACROTILE_MODE15:
+ idx = (reg_offset - mmGB_MACROTILE_MODE0);
+ return adev->gfx.config.macrotile_mode_array[idx];
+ default:
+ return RREG32(reg_offset);
+ }
+ }
}
static int cik_read_register(struct amdgpu_device *adev, u32 se_num,
*value = 0;
for (i = 0; i < ARRAY_SIZE(cik_allowed_read_registers); i++) {
+ bool indexed = cik_allowed_read_registers[i].grbm_indexed;
+
if (reg_offset != cik_allowed_read_registers[i].reg_offset)
continue;
- *value = cik_allowed_read_registers[i].grbm_indexed ?
- cik_read_indexed_register(adev, se_num,
- sh_num, reg_offset) :
- RREG32(reg_offset);
+ *value = cik_get_register_value(adev, indexed, se_num, sh_num,
+ reg_offset);
return 0;
}
return -EINVAL;
adev->gfx.config.backend_enable_mask,
num_rb_pipes);
}
+
+ /* cache the values for userspace */
+ for (i = 0; i < adev->gfx.config.max_shader_engines; i++) {
+ for (j = 0; j < adev->gfx.config.max_sh_per_se; j++) {
+ gfx_v7_0_select_se_sh(adev, i, j, 0xffffffff);
+ adev->gfx.config.rb_config[i][j].rb_backend_disable =
+ RREG32(mmCC_RB_BACKEND_DISABLE);
+ adev->gfx.config.rb_config[i][j].user_rb_backend_disable =
+ RREG32(mmGC_USER_RB_BACKEND_DISABLE);
+ adev->gfx.config.rb_config[i][j].raster_config =
+ RREG32(mmPA_SC_RASTER_CONFIG);
+ adev->gfx.config.rb_config[i][j].raster_config_1 =
+ RREG32(mmPA_SC_RASTER_CONFIG_1);
+ }
+ }
+ gfx_v7_0_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff);
mutex_unlock(&adev->grbm_idx_mutex);
}
static void vcn_v1_0_set_irq_funcs(struct amdgpu_device *adev)
{
- adev->uvd.irq.num_types = adev->vcn.num_enc_rings + 1;
+ adev->vcn.irq.num_types = adev->vcn.num_enc_rings + 1;
adev->vcn.irq.funcs = &vcn_v1_0_irq_funcs;
}
#include <linux/sched.h>
#include <linux/moduleparam.h>
#include <linux/device.h>
+#include <linux/printk.h>
#include "kfd_priv.h"
#define KFD_DRIVER_AUTHOR "AMD Inc. and others"
kfd_process_destroy_wq();
kfd_topology_shutdown();
kfd_chardev_exit();
- dev_info(kfd_device, "Removed module\n");
+ pr_info("amdkfd: Removed module\n");
}
module_init(kfd_module_init);
struct cik_sdma_rlc_registers *m;
m = get_sdma_mqd(mqd);
- m->sdma_rlc_rb_cntl = ffs(q->queue_size / sizeof(unsigned int)) <<
- SDMA0_RLC0_RB_CNTL__RB_SIZE__SHIFT |
+ m->sdma_rlc_rb_cntl = (ffs(q->queue_size / sizeof(unsigned int)) - 1)
+ << SDMA0_RLC0_RB_CNTL__RB_SIZE__SHIFT |
q->vmid << SDMA0_RLC0_RB_CNTL__RB_VMID__SHIFT |
1 << SDMA0_RLC0_RB_CNTL__RPTR_WRITEBACK_ENABLE__SHIFT |
6 << SDMA0_RLC0_RB_CNTL__RPTR_WRITEBACK_TIMER__SHIFT;
switch (type) {
case KFD_QUEUE_TYPE_SDMA:
+ if (dev->dqm->queue_count >=
+ CIK_SDMA_QUEUES_PER_ENGINE * CIK_SDMA_ENGINE_NUM) {
+ pr_err("Over-subscription is not allowed for SDMA.\n");
+ retval = -EPERM;
+ goto err_create_queue;
+ }
+
+ retval = create_cp_queue(pqm, dev, &q, properties, f, *qid);
+ if (retval != 0)
+ goto err_create_queue;
+ pqn->q = q;
+ pqn->kq = NULL;
+ retval = dev->dqm->ops.create_queue(dev->dqm, q, &pdd->qpd,
+ &q->properties.vmid);
+ pr_debug("DQM returned %d for create_queue\n", retval);
+ print_queue(q);
+ break;
+
case KFD_QUEUE_TYPE_COMPUTE:
/* check if there is over subscription */
if ((sched_policy == KFD_SCHED_POLICY_HWS_NO_OVERSUBSCRIPTION) &&
list_for_each_entry(connector, &dev->mode_config.connector_list, head) {
aconnector = to_amdgpu_dm_connector(connector);
- if (aconnector->dc_link->type == dc_connection_mst_branch) {
+ if (aconnector->dc_link->type == dc_connection_mst_branch &&
+ aconnector->mst_mgr.aux) {
DRM_DEBUG_DRIVER("DM_MST: starting TM on aconnector: %p [id: %d]\n",
aconnector, aconnector->base.base.id);
mutex_lock(&aconnector->hpd_lock);
dc_link_detect(aconnector->dc_link, DETECT_REASON_HPD);
+
+ if (aconnector->fake_enable && aconnector->dc_link->local_sink)
+ aconnector->fake_enable = false;
+
aconnector->dc_sink = NULL;
amdgpu_dm_update_connector_after_detect(aconnector);
mutex_unlock(&aconnector->hpd_lock);
ret = drm_atomic_helper_resume(ddev, adev->dm.cached_state);
- drm_atomic_state_put(adev->dm.cached_state);
adev->dm.cached_state = NULL;
amdgpu_dm_irq_resume_late(adev);
.link = aconnector->dc_link,
.sink_signal = SIGNAL_TYPE_VIRTUAL
};
- struct edid *edid = (struct edid *) aconnector->base.edid_blob_ptr->data;
+ struct edid *edid;
if (!aconnector->base.edid_blob_ptr ||
!aconnector->base.edid_blob_ptr->data) {
return;
}
+ edid = (struct edid *) aconnector->base.edid_blob_ptr->data;
+
aconnector->edid = edid;
aconnector->dc_em_sink = dc_link_add_remote_sink(
update_stream_scaling_settings(&dm_new_con_state->base.crtc->mode,
dm_new_con_state, (struct dc_stream_state *)dm_new_crtc_state->stream);
+ if (!dm_new_crtc_state->stream)
+ continue;
+
status = dc_stream_get_status(dm_new_crtc_state->stream);
WARN_ON(!status);
WARN_ON(!status->plane_count);
- if (!dm_new_crtc_state->stream)
- continue;
-
/*TODO How it works with MPO ?*/
if (!dc_commit_planes_to_stream(
dm->dc,
drm_atomic_helper_commit_hw_done(state);
if (wait_for_vblank)
- drm_atomic_helper_wait_for_vblanks(dev, state);
+ drm_atomic_helper_wait_for_flip_done(dev, state);
drm_atomic_helper_cleanup_planes(dev, state);
}
return;
disconnected_acrtc = to_amdgpu_crtc(connector->encoder->crtc);
- acrtc_state = to_dm_crtc_state(disconnected_acrtc->base.state);
+ if (!disconnected_acrtc)
+ return;
- if (!disconnected_acrtc || !acrtc_state->stream)
+ acrtc_state = to_dm_crtc_state(disconnected_acrtc->base.state);
+ if (!acrtc_state->stream)
return;
/*
}
}
- if (dc_is_stream_unchanged(new_stream, dm_old_crtc_state->stream) &&
+ if (enable && dc_is_stream_unchanged(new_stream, dm_old_crtc_state->stream) &&
dc_is_stream_scaling_unchanged(new_stream, dm_old_crtc_state->stream)) {
new_crtc_state->mode_changed = false;
}
} else {
for_each_oldnew_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i) {
- if (!drm_atomic_crtc_needs_modeset(new_crtc_state))
+ if (!drm_atomic_crtc_needs_modeset(new_crtc_state) &&
+ !new_crtc_state->color_mgmt_changed)
continue;
if (!new_crtc_state->enable)
if (signal == signal_type_info_tbl[i].type)
break;
+ if (i == NUM_ELEMENTS(signal_type_info_tbl))
+ goto fail;
+
dm_logger_append(&entry, "[%s][ConnIdx:%d] ",
signal_type_info_tbl[i].name,
link->link_index);
dm_logger_append(&entry, "^\n");
dm_helpers_dc_conn_log(ctx, &entry, event);
+
+fail:
dm_logger_close(&entry);
va_end(args);
struct graphics_object_id *dest_object_id)
{
uint32_t number;
- uint16_t *id;
+ uint16_t *id = NULL;
ATOM_OBJECT *object;
struct bios_parser *bp = BP_FROM_DCB(dcb);
number = get_dest_obj_list(bp, object, &id);
- if (number <= index)
+ if (number <= index || !id)
return BP_RESULT_BADINPUT;
*dest_object_id = object_id_from_bios_object_id(id[index]);
goto failed_alloc;
}
+ link->link_index = dc->link_count;
+ dc->links[dc->link_count] = link;
+ dc->link_count++;
+
link->ctx = dc->ctx;
link->dc = dc;
link->connector_signal = SIGNAL_TYPE_VIRTUAL;
link->link_id.enum_id = ENUM_ID_1;
link->link_enc = kzalloc(sizeof(*link->link_enc), GFP_KERNEL);
+ if (!link->link_enc) {
+ BREAK_TO_DEBUGGER();
+ goto failed_alloc;
+ }
+
+ link->link_status.dpcd_caps = &link->dpcd_caps;
+
enc_init.ctx = dc->ctx;
enc_init.channel = CHANNEL_ID_UNKNOWN;
enc_init.hpd_source = HPD_SOURCEID_UNKNOWN;
enc_init.encoder.id = ENCODER_ID_INTERNAL_VIRTUAL;
enc_init.encoder.enum_id = ENUM_ID_1;
virtual_link_encoder_construct(link->link_enc, &enc_init);
-
- link->link_index = dc->link_count;
- dc->links[dc->link_count] = link;
- dc->link_count++;
}
return true;
sink_caps->signal = SIGNAL_TYPE_DISPLAY_PORT;
detect_dp_sink_caps(link);
- /* DP active dongles */
- if (is_dp_active_dongle(link)) {
- link->type = dc_connection_active_dongle;
- if (!link->dpcd_caps.sink_count.bits.SINK_COUNT) {
- /*
- * active dongle unplug processing for short irq
- */
- link_disconnect_sink(link);
- return;
- }
-
- if (link->dpcd_caps.dongle_type !=
- DISPLAY_DONGLE_DP_HDMI_CONVERTER) {
- *converter_disable_audio = true;
- }
- }
if (is_mst_supported(link)) {
sink_caps->signal = SIGNAL_TYPE_DISPLAY_PORT_MST;
link->type = dc_connection_mst_branch;
sink_caps->signal = SIGNAL_TYPE_DISPLAY_PORT;
}
}
+
+ if (link->type != dc_connection_mst_branch &&
+ is_dp_active_dongle(link)) {
+ /* DP active dongles */
+ link->type = dc_connection_active_dongle;
+ if (!link->dpcd_caps.sink_count.bits.SINK_COUNT) {
+ /*
+ * active dongle unplug processing for short irq
+ */
+ link_disconnect_sink(link);
+ return;
+ }
+
+ if (link->dpcd_caps.dongle_type != DISPLAY_DONGLE_DP_HDMI_CONVERTER)
+ *converter_disable_audio = true;
+ }
} else {
/* DP passive dongles */
sink_caps->signal = dp_passive_dongle_detection(link->ddc,
link->link_enc->funcs->disable_output(link->link_enc, signal, link);
}
+bool dp_active_dongle_validate_timing(
+ const struct dc_crtc_timing *timing,
+ const struct dc_dongle_caps *dongle_caps)
+{
+ unsigned int required_pix_clk = timing->pix_clk_khz;
+
+ if (dongle_caps->dongle_type != DISPLAY_DONGLE_DP_HDMI_CONVERTER ||
+ dongle_caps->extendedCapValid == false)
+ return true;
+
+ /* Check Pixel Encoding */
+ switch (timing->pixel_encoding) {
+ case PIXEL_ENCODING_RGB:
+ case PIXEL_ENCODING_YCBCR444:
+ break;
+ case PIXEL_ENCODING_YCBCR422:
+ if (!dongle_caps->is_dp_hdmi_ycbcr422_pass_through)
+ return false;
+ break;
+ case PIXEL_ENCODING_YCBCR420:
+ if (!dongle_caps->is_dp_hdmi_ycbcr420_pass_through)
+ return false;
+ break;
+ default:
+ /* Invalid Pixel Encoding*/
+ return false;
+ }
+
+
+ /* Check Color Depth and Pixel Clock */
+ if (timing->pixel_encoding == PIXEL_ENCODING_YCBCR420)
+ required_pix_clk /= 2;
+
+ switch (timing->display_color_depth) {
+ case COLOR_DEPTH_666:
+ case COLOR_DEPTH_888:
+ /*888 and 666 should always be supported*/
+ break;
+ case COLOR_DEPTH_101010:
+ if (dongle_caps->dp_hdmi_max_bpc < 10)
+ return false;
+ required_pix_clk = required_pix_clk * 10 / 8;
+ break;
+ case COLOR_DEPTH_121212:
+ if (dongle_caps->dp_hdmi_max_bpc < 12)
+ return false;
+ required_pix_clk = required_pix_clk * 12 / 8;
+ break;
+
+ case COLOR_DEPTH_141414:
+ case COLOR_DEPTH_161616:
+ default:
+ /* These color depths are currently not supported */
+ return false;
+ }
+
+ if (required_pix_clk > dongle_caps->dp_hdmi_max_pixel_clk)
+ return false;
+
+ return true;
+}
+
enum dc_status dc_link_validate_mode_timing(
const struct dc_stream_state *stream,
struct dc_link *link,
const struct dc_crtc_timing *timing)
{
uint32_t max_pix_clk = stream->sink->dongle_max_pix_clk;
+ struct dc_dongle_caps *dongle_caps = &link->link_status.dpcd_caps->dongle_caps;
/* A hack to avoid failing any modes for EDID override feature on
* topology change such as lower quality cable for DP or different dongle
if (link->remote_sinks[0])
return DC_OK;
+ /* Passive Dongle */
if (0 != max_pix_clk && timing->pix_clk_khz > max_pix_clk)
- return DC_EXCEED_DONGLE_MAX_CLK;
+ return DC_EXCEED_DONGLE_CAP;
+
+ /* Active Dongle*/
+ if (!dp_active_dongle_validate_timing(timing, dongle_caps))
+ return DC_EXCEED_DONGLE_CAP;
switch (stream->signal) {
case SIGNAL_TYPE_EDP:
struct dc_link *link,
union hpd_irq_data *hpd_irq_dpcd_data)
{
- uint8_t irq_reg_rx_power_state;
+ uint8_t irq_reg_rx_power_state = 0;
enum dc_status dpcd_result = DC_ERROR_UNEXPECTED;
union lane_status lane_status;
uint32_t lane;
if (link->cur_link_settings.lane_count == 0)
return return_code;
- /*1. Check that we can handle interrupt: Not in FS DOS,
- * Not in "Display Timeout" state, Link is trained.
- */
- dpcd_result = core_link_read_dpcd(link,
- DP_SET_POWER,
- &irq_reg_rx_power_state,
- sizeof(irq_reg_rx_power_state));
+ /*1. Check that Link Status changed, before re-training.*/
- if (dpcd_result != DC_OK) {
- irq_reg_rx_power_state = DP_SET_POWER_D0;
- dm_logger_write(link->ctx->logger, LOG_HW_HPD_IRQ,
- "%s: DPCD read failed to obtain power state.\n",
- __func__);
+ /*parse lane status*/
+ for (lane = 0; lane < link->cur_link_settings.lane_count; lane++) {
+ /* check status of lanes 0,1
+ * changed DpcdAddress_Lane01Status (0x202)
+ */
+ lane_status.raw = get_nibble_at_index(
+ &hpd_irq_dpcd_data->bytes.lane01_status.raw,
+ lane);
+
+ if (!lane_status.bits.CHANNEL_EQ_DONE_0 ||
+ !lane_status.bits.CR_DONE_0 ||
+ !lane_status.bits.SYMBOL_LOCKED_0) {
+ /* if one of the channel equalization, clock
+ * recovery or symbol lock is dropped
+ * consider it as (link has been
+ * dropped) dp sink status has changed
+ */
+ sink_status_changed = true;
+ break;
+ }
}
- if (irq_reg_rx_power_state == DP_SET_POWER_D0) {
-
- /*2. Check that Link Status changed, before re-training.*/
-
- /*parse lane status*/
- for (lane = 0;
- lane < link->cur_link_settings.lane_count;
- lane++) {
+ /* Check interlane align.*/
+ if (sink_status_changed ||
+ !hpd_irq_dpcd_data->bytes.lane_status_updated.bits.INTERLANE_ALIGN_DONE) {
- /* check status of lanes 0,1
- * changed DpcdAddress_Lane01Status (0x202)*/
- lane_status.raw = get_nibble_at_index(
- &hpd_irq_dpcd_data->bytes.lane01_status.raw,
- lane);
-
- if (!lane_status.bits.CHANNEL_EQ_DONE_0 ||
- !lane_status.bits.CR_DONE_0 ||
- !lane_status.bits.SYMBOL_LOCKED_0) {
- /* if one of the channel equalization, clock
- * recovery or symbol lock is dropped
- * consider it as (link has been
- * dropped) dp sink status has changed*/
- sink_status_changed = true;
- break;
- }
+ dm_logger_write(link->ctx->logger, LOG_HW_HPD_IRQ,
+ "%s: Link Status changed.\n", __func__);
- }
+ return_code = true;
- /* Check interlane align.*/
- if (sink_status_changed ||
- !hpd_irq_dpcd_data->bytes.lane_status_updated.bits.
- INTERLANE_ALIGN_DONE) {
+ /*2. Check that we can handle interrupt: Not in FS DOS,
+ * Not in "Display Timeout" state, Link is trained.
+ */
+ dpcd_result = core_link_read_dpcd(link,
+ DP_SET_POWER,
+ &irq_reg_rx_power_state,
+ sizeof(irq_reg_rx_power_state));
+ if (dpcd_result != DC_OK) {
dm_logger_write(link->ctx->logger, LOG_HW_HPD_IRQ,
- "%s: Link Status changed.\n",
+ "%s: DPCD read failed to obtain power state.\n",
__func__);
-
- return_code = true;
+ } else {
+ if (irq_reg_rx_power_state != DP_SET_POWER_D0)
+ return_code = false;
}
}
(dongle_type == DISPLAY_DONGLE_DP_HDMI_CONVERTER);
}
+static int translate_dpcd_max_bpc(enum dpcd_downstream_port_max_bpc bpc)
+{
+ switch (bpc) {
+ case DOWN_STREAM_MAX_8BPC:
+ return 8;
+ case DOWN_STREAM_MAX_10BPC:
+ return 10;
+ case DOWN_STREAM_MAX_12BPC:
+ return 12;
+ case DOWN_STREAM_MAX_16BPC:
+ return 16;
+ default:
+ break;
+ }
+
+ return -1;
+}
+
static void get_active_converter_info(
uint8_t data, struct dc_link *link)
{
hdmi_caps.bits.YCrCr420_CONVERSION;
link->dpcd_caps.dongle_caps.dp_hdmi_max_bpc =
- hdmi_color_caps.bits.MAX_BITS_PER_COLOR_COMPONENT;
+ translate_dpcd_max_bpc(
+ hdmi_color_caps.bits.MAX_BITS_PER_COLOR_COMPONENT);
link->dpcd_caps.dongle_caps.extendedCapValid = true;
}
right_view = (plane_state->rotation == ROTATION_ANGLE_270) != sec_split;
if (right_view) {
- data->viewport.width /= 2;
- data->viewport_c.width /= 2;
- data->viewport.x += data->viewport.width;
- data->viewport_c.x += data->viewport_c.width;
+ data->viewport.x += data->viewport.width / 2;
+ data->viewport_c.x += data->viewport_c.width / 2;
/* Ceil offset pipe */
- data->viewport.width += data->viewport.width % 2;
- data->viewport_c.width += data->viewport_c.width % 2;
+ data->viewport.width = (data->viewport.width + 1) / 2;
+ data->viewport_c.width = (data->viewport_c.width + 1) / 2;
} else {
data->viewport.width /= 2;
data->viewport_c.width /= 2;
if (pipe_ctx->top_pipe && pipe_ctx->top_pipe->plane_state ==
pipe_ctx->plane_state) {
if (stream->view_format == VIEW_3D_FORMAT_TOP_AND_BOTTOM) {
- pipe_ctx->plane_res.scl_data.recout.height /= 2;
- pipe_ctx->plane_res.scl_data.recout.y += pipe_ctx->plane_res.scl_data.recout.height;
+ pipe_ctx->plane_res.scl_data.recout.y += pipe_ctx->plane_res.scl_data.recout.height / 2;
/* Floor primary pipe, ceil 2ndary pipe */
- pipe_ctx->plane_res.scl_data.recout.height += pipe_ctx->plane_res.scl_data.recout.height % 2;
+ pipe_ctx->plane_res.scl_data.recout.height = (pipe_ctx->plane_res.scl_data.recout.height + 1) / 2;
} else {
- pipe_ctx->plane_res.scl_data.recout.width /= 2;
- pipe_ctx->plane_res.scl_data.recout.x += pipe_ctx->plane_res.scl_data.recout.width;
- pipe_ctx->plane_res.scl_data.recout.width += pipe_ctx->plane_res.scl_data.recout.width % 2;
+ pipe_ctx->plane_res.scl_data.recout.x += pipe_ctx->plane_res.scl_data.recout.width / 2;
+ pipe_ctx->plane_res.scl_data.recout.width = (pipe_ctx->plane_res.scl_data.recout.width + 1) / 2;
}
} else if (pipe_ctx->bottom_pipe &&
pipe_ctx->bottom_pipe->plane_state == pipe_ctx->plane_state) {
pipe_ctx->plane_res.scl_data.h_active = timing->h_addressable + timing->h_border_left + timing->h_border_right;
pipe_ctx->plane_res.scl_data.v_active = timing->v_addressable + timing->v_border_top + timing->v_border_bottom;
+
/* Taps calculations */
if (pipe_ctx->plane_res.xfm != NULL)
res = pipe_ctx->plane_res.xfm->funcs->transform_get_optimal_number_of_taps(
if (pipe_ctx->plane_res.dpp != NULL)
res = pipe_ctx->plane_res.dpp->funcs->dpp_get_optimal_number_of_taps(
pipe_ctx->plane_res.dpp, &pipe_ctx->plane_res.scl_data, &plane_state->scaling_quality);
-
if (!res) {
/* Try 24 bpp linebuffer */
pipe_ctx->plane_res.scl_data.lb_params.depth = LB_PIXEL_DEPTH_24BPP;
- res = pipe_ctx->plane_res.xfm->funcs->transform_get_optimal_number_of_taps(
- pipe_ctx->plane_res.xfm, &pipe_ctx->plane_res.scl_data, &plane_state->scaling_quality);
+ if (pipe_ctx->plane_res.xfm != NULL)
+ res = pipe_ctx->plane_res.xfm->funcs->transform_get_optimal_number_of_taps(
+ pipe_ctx->plane_res.xfm,
+ &pipe_ctx->plane_res.scl_data,
+ &plane_state->scaling_quality);
- res = pipe_ctx->plane_res.dpp->funcs->dpp_get_optimal_number_of_taps(
- pipe_ctx->plane_res.dpp, &pipe_ctx->plane_res.scl_data, &plane_state->scaling_quality);
+ if (pipe_ctx->plane_res.dpp != NULL)
+ res = pipe_ctx->plane_res.dpp->funcs->dpp_get_optimal_number_of_taps(
+ pipe_ctx->plane_res.dpp,
+ &pipe_ctx->plane_res.scl_data,
+ &plane_state->scaling_quality);
}
if (res)
head_pipe = resource_get_head_pipe_for_stream(res_ctx, stream);
- if (!head_pipe)
+ if (!head_pipe) {
ASSERT(0);
+ return NULL;
+ }
if (!head_pipe->plane_state)
return head_pipe;
static struct audio *find_first_free_audio(
struct resource_context *res_ctx,
- const struct resource_pool *pool)
+ const struct resource_pool *pool,
+ enum engine_id id)
{
int i;
for (i = 0; i < pool->audio_count; i++) {
if ((res_ctx->is_audio_acquired[i] == false) && (res_ctx->is_stream_enc_acquired[i] == true)) {
+ /*we have enough audio endpoint, find the matching inst*/
+ if (id != i)
+ continue;
+
return pool->audios[i];
}
}
dc_is_audio_capable_signal(pipe_ctx->stream->signal) &&
stream->audio_info.mode_count) {
pipe_ctx->stream_res.audio = find_first_free_audio(
- &context->res_ctx, pool);
+ &context->res_ctx, pool, pipe_ctx->stream_res.stream_enc->id);
/*
* Audio assigned in order first come first get.
enum dc_status result = DC_ERROR_UNEXPECTED;
int i, j;
+ if (!new_ctx)
+ return DC_ERROR_UNEXPECTED;
+
if (dc->res_pool->funcs->validate_global) {
result = dc->res_pool->funcs->validate_global(dc, new_ctx);
if (result != DC_OK)
return result;
}
- for (i = 0; new_ctx && i < new_ctx->stream_count; i++) {
+ for (i = 0; i < new_ctx->stream_count; i++) {
struct dc_stream_state *stream = new_ctx->streams[i];
for (j = 0; j < dc->res_pool->pipe_count; j++) {
struct input_pixel_processor *ipp = pipe_ctx->plane_res.ipp;
struct mem_input *mi = pipe_ctx->plane_res.mi;
struct hubp *hubp = pipe_ctx->plane_res.hubp;
- struct transform *xfm = pipe_ctx->plane_res.xfm;
struct dpp *dpp = pipe_ctx->plane_res.dpp;
struct dc_cursor_position pos_cpy = *position;
struct dc_cursor_mi_param param = {
if (mi != NULL && mi->funcs->set_cursor_position != NULL)
mi->funcs->set_cursor_position(mi, &pos_cpy, ¶m);
- if (hubp != NULL && hubp->funcs->set_cursor_position != NULL)
- hubp->funcs->set_cursor_position(hubp, &pos_cpy, ¶m);
+ if (!hubp)
+ continue;
- if (xfm != NULL && xfm->funcs->set_cursor_position != NULL)
- xfm->funcs->set_cursor_position(xfm, &pos_cpy, ¶m, hubp->curs_attr.width);
+ if (hubp->funcs->set_cursor_position != NULL)
+ hubp->funcs->set_cursor_position(hubp, &pos_cpy, ¶m);
if (dpp != NULL && dpp->funcs->set_cursor_position != NULL)
dpp->funcs->set_cursor_position(dpp, &pos_cpy, ¶m, hubp->curs_attr.width);
uint32_t value = AZ_REG_READ(AZALIA_F0_CODEC_PIN_CONTROL_HOT_PLUG_CONTROL);
set_reg_field_value(value, 1,
- AZALIA_F0_CODEC_PIN_CONTROL_HOT_PLUG_CONTROL,
- CLOCK_GATING_DISABLE);
- set_reg_field_value(value, 1,
- AZALIA_F0_CODEC_PIN_CONTROL_HOT_PLUG_CONTROL,
- AUDIO_ENABLED);
+ AZALIA_F0_CODEC_PIN_CONTROL_HOT_PLUG_CONTROL,
+ CLOCK_GATING_DISABLE);
+ set_reg_field_value(value, 1,
+ AZALIA_F0_CODEC_PIN_CONTROL_HOT_PLUG_CONTROL,
+ AUDIO_ENABLED);
AZ_REG_WRITE(AZALIA_F0_CODEC_PIN_CONTROL_HOT_PLUG_CONTROL, value);
value = AZ_REG_READ(AZALIA_F0_CODEC_PIN_CONTROL_HOT_PLUG_CONTROL);
*/
uint32_t max_retries = 50;
+ /*we need turn on clock before programming AFMT block*/
+ REG_UPDATE(AFMT_CNTL, AFMT_AUDIO_CLOCK_EN, 1);
+
if (REG(AFMT_VBI_PACKET_CONTROL1)) {
if (packet_index >= 8)
ASSERT(0);
struct dc_link *link = stream->sink->link;
struct dc *dc = pipe_ctx->stream->ctx->dc;
+ if (dc_is_hdmi_signal(pipe_ctx->stream->signal))
+ pipe_ctx->stream_res.stream_enc->funcs->stop_hdmi_info_packets(
+ pipe_ctx->stream_res.stream_enc);
+
+ if (dc_is_dp_signal(pipe_ctx->stream->signal))
+ pipe_ctx->stream_res.stream_enc->funcs->stop_dp_info_packets(
+ pipe_ctx->stream_res.stream_enc);
+
+ pipe_ctx->stream_res.stream_enc->funcs->audio_mute_control(
+ pipe_ctx->stream_res.stream_enc, true);
if (pipe_ctx->stream_res.audio) {
pipe_ctx->stream_res.audio->funcs->az_disable(pipe_ctx->stream_res.audio);
*/
}
- if (dc_is_hdmi_signal(pipe_ctx->stream->signal))
- pipe_ctx->stream_res.stream_enc->funcs->stop_hdmi_info_packets(
- pipe_ctx->stream_res.stream_enc);
-
- if (dc_is_dp_signal(pipe_ctx->stream->signal))
- pipe_ctx->stream_res.stream_enc->funcs->stop_dp_info_packets(
- pipe_ctx->stream_res.stream_enc);
-
- pipe_ctx->stream_res.stream_enc->funcs->audio_mute_control(
- pipe_ctx->stream_res.stream_enc, true);
-
-
/* blank at encoder level */
if (dc_is_dp_signal(pipe_ctx->stream->signal)) {
if (pipe_ctx->stream->sink->link->connector_signal == SIGNAL_TYPE_EDP)
if (pipe_ctx->stream->sink->link->psr_enabled)
return DC_ERROR_UNEXPECTED;
+ /* Nothing to compress */
+ if (!pipe_ctx->plane_state)
+ return DC_ERROR_UNEXPECTED;
+
/* Only for non-linear tiling */
if (pipe_ctx->plane_state->tiling_info.gfx8.array_mode == DC_ARRAY_LINEAR_GENERAL)
return DC_ERROR_UNEXPECTED;
pipe_need_reprogram(pipe_ctx_old, pipe_ctx)) {
struct clock_source *old_clk = pipe_ctx_old->clock_source;
- /* disable already, no need to disable again */
- if (pipe_ctx->stream && !pipe_ctx->stream->dpms_off)
+ /* Disable if new stream is null. O/w, if stream is
+ * disabled already, no need to disable again.
+ */
+ if (!pipe_ctx->stream || !pipe_ctx->stream->dpms_off)
core_link_disable_stream(pipe_ctx_old, FREE_ACQUIRED_RESOURCE);
pipe_ctx_old->stream_res.tg->funcs->set_blank(pipe_ctx_old->stream_res.tg, true);
struct dce110_opp *dce110_oppv = kzalloc(sizeof(*dce110_oppv),
GFP_KERNEL);
- if ((dce110_tgv == NULL) ||
- (dce110_xfmv == NULL) ||
- (dce110_miv == NULL) ||
- (dce110_oppv == NULL))
- return false;
+ if (!dce110_tgv || !dce110_xfmv || !dce110_miv || !dce110_oppv) {
+ kfree(dce110_tgv);
+ kfree(dce110_xfmv);
+ kfree(dce110_miv);
+ kfree(dce110_oppv);
+ return false;
+ }
dce110_opp_v_construct(dce110_oppv, ctx);
enum signal_type signal)
{
uint32_t h_blank;
- uint32_t h_back_porch;
- uint32_t hsync_offset = timing->h_border_right +
- timing->h_front_porch;
- uint32_t h_sync_start = timing->h_addressable + hsync_offset;
+ uint32_t h_back_porch, hsync_offset, h_sync_start;
struct dce110_timing_generator *tg110 = DCE110TG_FROM_TG(tg);
if (!timing)
return false;
+ hsync_offset = timing->h_border_right + timing->h_front_porch;
+ h_sync_start = timing->h_addressable + hsync_offset;
+
/* Currently we don't support 3D, so block all 3D timings */
if (timing->timing_3d_format != TIMING_3D_FORMAT_NONE)
return false;
struct pipe_ctx *head_pipe = resource_get_head_pipe_for_stream(res_ctx, stream);
struct pipe_ctx *idle_pipe = find_idle_secondary_pipe(res_ctx, pool);
- if (!head_pipe)
+ if (!head_pipe) {
ASSERT(0);
+ return NULL;
+ }
if (!idle_pipe)
- return false;
+ return NULL;
idle_pipe->stream = head_pipe->stream;
idle_pipe->stream_res.tg = head_pipe->stream_res.tg;
timing->timing_3d_format != TIMING_3D_FORMAT_INBAND_FA)
return false;
- if (timing->timing_3d_format != TIMING_3D_FORMAT_NONE &&
- tg->ctx->dc->debug.disable_stereo_support)
- return false;
/* Temporarily blocking interlacing mode until it's supported */
if (timing->flags.INTERLACE == 1)
return false;
DC_FAIL_DETACH_SURFACES = 8,
DC_FAIL_SURFACE_VALIDATE = 9,
DC_NO_DP_LINK_BANDWIDTH = 10,
- DC_EXCEED_DONGLE_MAX_CLK = 11,
+ DC_EXCEED_DONGLE_CAP = 11,
DC_SURFACE_PIXEL_FORMAT_UNSUPPORTED = 12,
DC_FAIL_BANDWIDTH_VALIDATE = 13, /* BW and Watermark validation */
DC_FAIL_SCALING = 14,
struct transform *xfm_base,
const struct dc_cursor_attributes *attr);
- void (*set_cursor_position)(
- struct transform *xfm_base,
- const struct dc_cursor_position *pos,
- const struct dc_cursor_mi_param *param,
- uint32_t width
- );
-
};
const uint16_t *get_filter_2tap_16p(void);
formats, ARRAY_SIZE(formats),
NULL,
DRM_PLANE_TYPE_PRIMARY, NULL);
- if (ret) {
+ if (ret)
return ERR_PTR(ret);
- }
drm_plane_helper_add(plane, &hdlcd_plane_helper_funcs);
hdlcd->plane = plane;
#include <linux/spinlock.h>
#include <linux/clk.h>
#include <linux/component.h>
+#include <linux/console.h>
#include <linux/list.h>
#include <linux/of_graph.h>
#include <linux/of_reserved_mem.h>
err_free:
drm_mode_config_cleanup(drm);
dev_set_drvdata(dev, NULL);
- drm_dev_unref(drm);
+ drm_dev_put(drm);
return ret;
}
pm_runtime_disable(drm->dev);
of_reserved_mem_device_release(drm->dev);
drm_mode_config_cleanup(drm);
- drm_dev_unref(drm);
+ drm_dev_put(drm);
drm->dev_private = NULL;
dev_set_drvdata(dev, NULL);
}
return 0;
drm_kms_helper_poll_disable(drm);
+ drm_fbdev_cma_set_suspend_unlocked(hdlcd->fbdev, 1);
hdlcd->state = drm_atomic_helper_suspend(drm);
if (IS_ERR(hdlcd->state)) {
+ drm_fbdev_cma_set_suspend_unlocked(hdlcd->fbdev, 0);
drm_kms_helper_poll_enable(drm);
return PTR_ERR(hdlcd->state);
}
return 0;
drm_atomic_helper_resume(drm, hdlcd->state);
+ drm_fbdev_cma_set_suspend_unlocked(hdlcd->fbdev, 0);
drm_kms_helper_poll_enable(drm);
- pm_runtime_set_active(dev);
return 0;
}
/* We rely on firmware to set mclk to a sensible level. */
clk_set_rate(hwdev->pxlclk, crtc->state->adjusted_mode.crtc_clock * 1000);
- hwdev->modeset(hwdev, &vm);
- hwdev->leave_config_mode(hwdev);
+ hwdev->hw->modeset(hwdev, &vm);
+ hwdev->hw->leave_config_mode(hwdev);
drm_crtc_vblank_on(crtc);
}
struct malidp_hw_device *hwdev = malidp->dev;
int err;
+ /* always disable planes on the CRTC that is being turned off */
+ drm_atomic_helper_disable_planes_on_crtc(old_state, false);
+
drm_crtc_vblank_off(crtc);
- hwdev->enter_config_mode(hwdev);
+ hwdev->hw->enter_config_mode(hwdev);
+
clk_disable_unprepare(hwdev->pxlclk);
err = pm_runtime_put(crtc->dev->dev);
mclk_calc:
drm_display_mode_to_videomode(&state->adjusted_mode, &vm);
- ret = hwdev->se_calc_mclk(hwdev, s, &vm);
+ ret = hwdev->hw->se_calc_mclk(hwdev, s, &vm);
if (ret < 0)
return -EINVAL;
return 0;
struct malidp_hw_device *hwdev = malidp->dev;
malidp_hw_enable_irq(hwdev, MALIDP_DE_BLOCK,
- hwdev->map.de_irq_map.vsync_irq);
+ hwdev->hw->map.de_irq_map.vsync_irq);
return 0;
}
struct malidp_hw_device *hwdev = malidp->dev;
malidp_hw_disable_irq(hwdev, MALIDP_DE_BLOCK,
- hwdev->map.de_irq_map.vsync_irq);
+ hwdev->hw->map.de_irq_map.vsync_irq);
}
static const struct drm_crtc_funcs malidp_crtc_funcs = {
* directly.
*/
malidp_hw_write(hwdev, gamma_write_mask,
- hwdev->map.coeffs_base + MALIDP_COEF_TABLE_ADDR);
+ hwdev->hw->map.coeffs_base + MALIDP_COEF_TABLE_ADDR);
for (i = 0; i < MALIDP_COEFFTAB_NUM_COEFFS; ++i)
malidp_hw_write(hwdev, data[i],
- hwdev->map.coeffs_base +
+ hwdev->hw->map.coeffs_base +
MALIDP_COEF_TABLE_DATA);
}
for (i = 0; i < MALIDP_COLORADJ_NUM_COEFFS; ++i)
malidp_hw_write(hwdev,
mc->coloradj_coeffs[i],
- hwdev->map.coeffs_base +
+ hwdev->hw->map.coeffs_base +
MALIDP_COLOR_ADJ_COEF + 4 * i);
malidp_hw_setbits(hwdev, MALIDP_DISP_FUNC_CADJ,
struct malidp_hw_device *hwdev = malidp->dev;
struct malidp_se_config *s = &cs->scaler_config;
struct malidp_se_config *old_s = &old_cs->scaler_config;
- u32 se_control = hwdev->map.se_base +
- ((hwdev->map.features & MALIDP_REGMAP_HAS_CLEARIRQ) ?
+ u32 se_control = hwdev->hw->map.se_base +
+ ((hwdev->hw->map.features & MALIDP_REGMAP_HAS_CLEARIRQ) ?
0x10 : 0xC);
u32 layer_control = se_control + MALIDP_SE_LAYER_CONTROL;
u32 scr = se_control + MALIDP_SE_SCALING_CONTROL;
return;
}
- hwdev->se_set_scaling_coeffs(hwdev, s, old_s);
+ hwdev->hw->se_set_scaling_coeffs(hwdev, s, old_s);
val = malidp_hw_read(hwdev, se_control);
val |= MALIDP_SE_SCALING_EN | MALIDP_SE_ALPHA_EN;
int ret;
atomic_set(&malidp->config_valid, 0);
- hwdev->set_config_valid(hwdev);
+ hwdev->hw->set_config_valid(hwdev);
/* don't wait for config_valid flag if we are in config mode */
- if (hwdev->in_config_mode(hwdev))
+ if (hwdev->hw->in_config_mode(hwdev))
return 0;
ret = wait_event_interruptible_timeout(malidp->wq,
struct malidp_hw_device *hwdev = malidp->dev;
/* we can only suspend if the hardware is in config mode */
- WARN_ON(!hwdev->in_config_mode(hwdev));
+ WARN_ON(!hwdev->hw->in_config_mode(hwdev));
hwdev->pm_suspended = true;
clk_disable_unprepare(hwdev->mclk);
if (!hwdev)
return -ENOMEM;
- /*
- * copy the associated data from malidp_drm_of_match to avoid
- * having to keep a reference to the OF node after binding
- */
- memcpy(hwdev, of_device_get_match_data(dev), sizeof(*hwdev));
+ hwdev->hw = (struct malidp_hw *)of_device_get_match_data(dev);
malidp->dev = hwdev;
res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
goto query_hw_fail;
}
- ret = hwdev->query_hw(hwdev);
+ ret = hwdev->hw->query_hw(hwdev);
if (ret) {
DRM_ERROR("Invalid HW configuration\n");
goto query_hw_fail;
}
- version = malidp_hw_read(hwdev, hwdev->map.dc_base + MALIDP_DE_CORE_ID);
+ version = malidp_hw_read(hwdev, hwdev->hw->map.dc_base + MALIDP_DE_CORE_ID);
DRM_INFO("found ARM Mali-DP%3x version r%dp%d\n", version >> 16,
(version >> 12) & 0xf, (version >> 8) & 0xf);
for (i = 0; i < MAX_OUTPUT_CHANNELS; i++)
out_depth = (out_depth << 8) | (output_width[i] & 0xf);
- malidp_hw_write(hwdev, out_depth, hwdev->map.out_depth_base);
+ malidp_hw_write(hwdev, out_depth, hwdev->hw->map.out_depth_base);
atomic_set(&malidp->config_valid, 0);
init_waitqueue_head(&malidp->wq);
malidp_runtime_pm_suspend(dev);
drm->dev_private = NULL;
dev_set_drvdata(dev, NULL);
- drm_dev_unref(drm);
+ drm_dev_put(drm);
alloc_fail:
of_reserved_mem_device_release(dev);
malidp_runtime_pm_suspend(dev);
drm->dev_private = NULL;
dev_set_drvdata(dev, NULL);
- drm_dev_unref(drm);
+ drm_dev_put(drm);
of_reserved_mem_device_release(dev);
}
malidp_hw_setbits(hwdev, MALIDP500_DC_CONFIG_REQ, MALIDP500_DC_CONTROL);
while (count) {
- status = malidp_hw_read(hwdev, hwdev->map.dc_base + MALIDP_REG_STATUS);
+ status = malidp_hw_read(hwdev, hwdev->hw->map.dc_base + MALIDP_REG_STATUS);
if ((status & MALIDP500_DC_CONFIG_REQ) == MALIDP500_DC_CONFIG_REQ)
break;
/*
malidp_hw_clearbits(hwdev, MALIDP_CFG_VALID, MALIDP500_CONFIG_VALID);
malidp_hw_clearbits(hwdev, MALIDP500_DC_CONFIG_REQ, MALIDP500_DC_CONTROL);
while (count) {
- status = malidp_hw_read(hwdev, hwdev->map.dc_base + MALIDP_REG_STATUS);
+ status = malidp_hw_read(hwdev, hwdev->hw->map.dc_base + MALIDP_REG_STATUS);
if ((status & MALIDP500_DC_CONFIG_REQ) == 0)
break;
usleep_range(100, 1000);
{
u32 status;
- status = malidp_hw_read(hwdev, hwdev->map.dc_base + MALIDP_REG_STATUS);
+ status = malidp_hw_read(hwdev, hwdev->hw->map.dc_base + MALIDP_REG_STATUS);
if ((status & MALIDP500_DC_CONFIG_REQ) == MALIDP500_DC_CONFIG_REQ)
return true;
malidp_hw_setbits(hwdev, MALIDP550_DC_CONFIG_REQ, MALIDP550_DC_CONTROL);
while (count) {
- status = malidp_hw_read(hwdev, hwdev->map.dc_base + MALIDP_REG_STATUS);
+ status = malidp_hw_read(hwdev, hwdev->hw->map.dc_base + MALIDP_REG_STATUS);
if ((status & MALIDP550_DC_CONFIG_REQ) == MALIDP550_DC_CONFIG_REQ)
break;
/*
malidp_hw_clearbits(hwdev, MALIDP_CFG_VALID, MALIDP550_CONFIG_VALID);
malidp_hw_clearbits(hwdev, MALIDP550_DC_CONFIG_REQ, MALIDP550_DC_CONTROL);
while (count) {
- status = malidp_hw_read(hwdev, hwdev->map.dc_base + MALIDP_REG_STATUS);
+ status = malidp_hw_read(hwdev, hwdev->hw->map.dc_base + MALIDP_REG_STATUS);
if ((status & MALIDP550_DC_CONFIG_REQ) == 0)
break;
usleep_range(100, 1000);
{
u32 status;
- status = malidp_hw_read(hwdev, hwdev->map.dc_base + MALIDP_REG_STATUS);
+ status = malidp_hw_read(hwdev, hwdev->hw->map.dc_base + MALIDP_REG_STATUS);
if ((status & MALIDP550_DC_CONFIG_REQ) == MALIDP550_DC_CONFIG_REQ)
return true;
return 0;
}
-const struct malidp_hw_device malidp_device[MALIDP_MAX_DEVICES] = {
+const struct malidp_hw malidp_device[MALIDP_MAX_DEVICES] = {
[MALIDP_500] = {
.map = {
.coeffs_base = MALIDP500_COEFFS_BASE,
{
u32 base = malidp_get_block_base(hwdev, block);
- if (hwdev->map.features & MALIDP_REGMAP_HAS_CLEARIRQ)
+ if (hwdev->hw->map.features & MALIDP_REGMAP_HAS_CLEARIRQ)
malidp_hw_write(hwdev, irq, base + MALIDP_REG_CLEARIRQ);
else
malidp_hw_write(hwdev, irq, base + MALIDP_REG_STATUS);
struct drm_device *drm = arg;
struct malidp_drm *malidp = drm->dev_private;
struct malidp_hw_device *hwdev;
+ struct malidp_hw *hw;
const struct malidp_irq_map *de;
u32 status, mask, dc_status;
irqreturn_t ret = IRQ_NONE;
hwdev = malidp->dev;
- de = &hwdev->map.de_irq_map;
+ hw = hwdev->hw;
+ de = &hw->map.de_irq_map;
/*
* if we are suspended it is likely that we were invoked because
return IRQ_NONE;
/* first handle the config valid IRQ */
- dc_status = malidp_hw_read(hwdev, hwdev->map.dc_base + MALIDP_REG_STATUS);
- if (dc_status & hwdev->map.dc_irq_map.vsync_irq) {
+ dc_status = malidp_hw_read(hwdev, hw->map.dc_base + MALIDP_REG_STATUS);
+ if (dc_status & hw->map.dc_irq_map.vsync_irq) {
/* we have a page flip event */
atomic_set(&malidp->config_valid, 1);
malidp_hw_clear_irq(hwdev, MALIDP_DC_BLOCK, dc_status);
/* first enable the DC block IRQs */
malidp_hw_enable_irq(hwdev, MALIDP_DC_BLOCK,
- hwdev->map.dc_irq_map.irq_mask);
+ hwdev->hw->map.dc_irq_map.irq_mask);
/* now enable the DE block IRQs */
malidp_hw_enable_irq(hwdev, MALIDP_DE_BLOCK,
- hwdev->map.de_irq_map.irq_mask);
+ hwdev->hw->map.de_irq_map.irq_mask);
return 0;
}
struct malidp_hw_device *hwdev = malidp->dev;
malidp_hw_disable_irq(hwdev, MALIDP_DE_BLOCK,
- hwdev->map.de_irq_map.irq_mask);
+ hwdev->hw->map.de_irq_map.irq_mask);
malidp_hw_disable_irq(hwdev, MALIDP_DC_BLOCK,
- hwdev->map.dc_irq_map.irq_mask);
+ hwdev->hw->map.dc_irq_map.irq_mask);
}
static irqreturn_t malidp_se_irq(int irq, void *arg)
struct drm_device *drm = arg;
struct malidp_drm *malidp = drm->dev_private;
struct malidp_hw_device *hwdev = malidp->dev;
+ struct malidp_hw *hw = hwdev->hw;
+ const struct malidp_irq_map *se = &hw->map.se_irq_map;
u32 status, mask;
/*
if (hwdev->pm_suspended)
return IRQ_NONE;
- status = malidp_hw_read(hwdev, hwdev->map.se_base + MALIDP_REG_STATUS);
- if (!(status & hwdev->map.se_irq_map.irq_mask))
+ status = malidp_hw_read(hwdev, hw->map.se_base + MALIDP_REG_STATUS);
+ if (!(status & se->irq_mask))
return IRQ_NONE;
- mask = malidp_hw_read(hwdev, hwdev->map.se_base + MALIDP_REG_MASKIRQ);
- status = malidp_hw_read(hwdev, hwdev->map.se_base + MALIDP_REG_STATUS);
+ mask = malidp_hw_read(hwdev, hw->map.se_base + MALIDP_REG_MASKIRQ);
+ status = malidp_hw_read(hwdev, hw->map.se_base + MALIDP_REG_STATUS);
status &= mask;
/* ToDo: status decoding and firing up of VSYNC and page flip events */
}
malidp_hw_enable_irq(hwdev, MALIDP_SE_BLOCK,
- hwdev->map.se_irq_map.irq_mask);
+ hwdev->hw->map.se_irq_map.irq_mask);
return 0;
}
struct malidp_hw_device *hwdev = malidp->dev;
malidp_hw_disable_irq(hwdev, MALIDP_SE_BLOCK,
- hwdev->map.se_irq_map.irq_mask);
+ hwdev->hw->map.se_irq_map.irq_mask);
}
/* Unlike DP550/650, DP500 has 3 stride registers in its video layer. */
#define MALIDP_DEVICE_LV_HAS_3_STRIDES BIT(0)
-struct malidp_hw_device {
- const struct malidp_hw_regmap map;
- void __iomem *regs;
+struct malidp_hw_device;
- /* APB clock */
- struct clk *pclk;
- /* AXI clock */
- struct clk *aclk;
- /* main clock for display core */
- struct clk *mclk;
- /* pixel clock for display core */
- struct clk *pxlclk;
+/*
+ * Static structure containing hardware specific data and pointers to
+ * functions that behave differently between various versions of the IP.
+ */
+struct malidp_hw {
+ const struct malidp_hw_regmap map;
/*
* Validate the driver instance against the hardware bits
struct videomode *vm);
u8 features;
-
- u8 min_line_size;
- u16 max_line_size;
-
- /* track the device PM state */
- bool pm_suspended;
-
- /* size of memory used for rotating layers, up to two banks available */
- u32 rotation_memory[2];
};
/* Supported variants of the hardware */
MALIDP_MAX_DEVICES
};
-extern const struct malidp_hw_device malidp_device[MALIDP_MAX_DEVICES];
+extern const struct malidp_hw malidp_device[MALIDP_MAX_DEVICES];
+
+/*
+ * Structure used by the driver during runtime operation.
+ */
+struct malidp_hw_device {
+ struct malidp_hw *hw;
+ void __iomem *regs;
+
+ /* APB clock */
+ struct clk *pclk;
+ /* AXI clock */
+ struct clk *aclk;
+ /* main clock for display core */
+ struct clk *mclk;
+ /* pixel clock for display core */
+ struct clk *pxlclk;
+
+ u8 min_line_size;
+ u16 max_line_size;
+
+ /* track the device PM state */
+ bool pm_suspended;
+
+ /* size of memory used for rotating layers, up to two banks available */
+ u32 rotation_memory[2];
+};
static inline u32 malidp_hw_read(struct malidp_hw_device *hwdev, u32 reg)
{
{
switch (block) {
case MALIDP_SE_BLOCK:
- return hwdev->map.se_base;
+ return hwdev->hw->map.se_base;
case MALIDP_DC_BLOCK:
- return hwdev->map.dc_base;
+ return hwdev->hw->map.dc_base;
}
return 0;
static inline bool malidp_hw_pitch_valid(struct malidp_hw_device *hwdev,
unsigned int pitch)
{
- return !(pitch & (hwdev->map.bus_align_bytes - 1));
+ return !(pitch & (hwdev->hw->map.bus_align_bytes - 1));
}
/* U16.16 */
};
u32 val = MALIDP_SE_SET_ENH_LIMIT_LOW(MALIDP_SE_ENH_LOW_LEVEL) |
MALIDP_SE_SET_ENH_LIMIT_HIGH(MALIDP_SE_ENH_HIGH_LEVEL);
- u32 image_enh = hwdev->map.se_base +
- ((hwdev->map.features & MALIDP_REGMAP_HAS_CLEARIRQ) ?
+ u32 image_enh = hwdev->hw->map.se_base +
+ ((hwdev->hw->map.features & MALIDP_REGMAP_HAS_CLEARIRQ) ?
0x10 : 0xC) + MALIDP_SE_IMAGE_ENH;
u32 enh_coeffs = image_enh + MALIDP_SE_ENH_COEFF0;
int i;
struct malidp_plane *mp = to_malidp_plane(plane);
if (mp->base.fb)
- drm_framebuffer_unreference(mp->base.fb);
+ drm_framebuffer_put(mp->base.fb);
drm_plane_helper_disable(plane);
drm_plane_cleanup(plane);
fb = state->fb;
- ms->format = malidp_hw_get_format_id(&mp->hwdev->map, mp->layer->id,
- fb->format->format);
+ ms->format = malidp_hw_get_format_id(&mp->hwdev->hw->map,
+ mp->layer->id,
+ fb->format->format);
if (ms->format == MALIDP_INVALID_FORMAT_ID)
return -EINVAL;
* third plane stride register.
*/
if (ms->n_planes == 3 &&
- !(mp->hwdev->features & MALIDP_DEVICE_LV_HAS_3_STRIDES) &&
+ !(mp->hwdev->hw->features & MALIDP_DEVICE_LV_HAS_3_STRIDES) &&
(state->fb->pitches[1] != state->fb->pitches[2]))
return -EINVAL;
if (state->rotation & MALIDP_ROTATED_MASK) {
int val;
- val = mp->hwdev->rotmem_required(mp->hwdev, state->crtc_h,
- state->crtc_w,
- fb->format->format);
+ val = mp->hwdev->hw->rotmem_required(mp->hwdev, state->crtc_h,
+ state->crtc_w,
+ fb->format->format);
if (val < 0)
return val;
return;
if (num_planes == 3)
- num_strides = (mp->hwdev->features &
+ num_strides = (mp->hwdev->hw->features &
MALIDP_DEVICE_LV_HAS_3_STRIDES) ? 3 : 2;
for (i = 0; i < num_strides; ++i)
struct drm_plane_state *old_state)
{
struct malidp_plane *mp;
- const struct malidp_hw_regmap *map;
struct malidp_plane_state *ms = to_malidp_plane_state(plane->state);
u32 src_w, src_h, dest_w, dest_h, val;
int i;
mp = to_malidp_plane(plane);
- map = &mp->hwdev->map;
/* convert src values from Q16 fixed point to integer */
src_w = plane->state->src_w >> 16;
int malidp_de_planes_init(struct drm_device *drm)
{
struct malidp_drm *malidp = drm->dev_private;
- const struct malidp_hw_regmap *map = &malidp->dev->map;
+ const struct malidp_hw_regmap *map = &malidp->dev->hw->map;
struct malidp_plane *plane = NULL;
enum drm_plane_type plane_type;
unsigned long crtcs = 1 << drm->mode_config.num_crtc;
};
#ifdef CONFIG_DRM_I2C_ADV7511_CEC
-int adv7511_cec_init(struct device *dev, struct adv7511 *adv7511,
- unsigned int offset);
+int adv7511_cec_init(struct device *dev, struct adv7511 *adv7511);
void adv7511_cec_irq_process(struct adv7511 *adv7511, unsigned int irq1);
+#else
+static inline int adv7511_cec_init(struct device *dev, struct adv7511 *adv7511)
+{
+ unsigned int offset = adv7511->type == ADV7533 ?
+ ADV7533_REG_CEC_OFFSET : 0;
+
+ regmap_write(adv7511->regmap, ADV7511_REG_CEC_CTRL + offset,
+ ADV7511_CEC_CTRL_POWER_DOWN);
+ return 0;
+}
#endif
#ifdef CONFIG_DRM_I2C_ADV7533
return 0;
}
-int adv7511_cec_init(struct device *dev, struct adv7511 *adv7511,
- unsigned int offset)
+int adv7511_cec_init(struct device *dev, struct adv7511 *adv7511)
{
+ unsigned int offset = adv7511->type == ADV7533 ?
+ ADV7533_REG_CEC_OFFSET : 0;
int ret = adv7511_cec_parse_dt(dev, adv7511);
if (ret)
- return ret;
+ goto err_cec_parse_dt;
adv7511->cec_adap = cec_allocate_adapter(&adv7511_cec_adap_ops,
adv7511, dev_name(dev), CEC_CAP_DEFAULTS, ADV7511_MAX_ADDRS);
- if (IS_ERR(adv7511->cec_adap))
- return PTR_ERR(adv7511->cec_adap);
+ if (IS_ERR(adv7511->cec_adap)) {
+ ret = PTR_ERR(adv7511->cec_adap);
+ goto err_cec_alloc;
+ }
regmap_write(adv7511->regmap, ADV7511_REG_CEC_CTRL + offset, 0);
/* cec soft reset */
((adv7511->cec_clk_freq / 750000) - 1) << 2);
ret = cec_register_adapter(adv7511->cec_adap, dev);
- if (ret) {
- cec_delete_adapter(adv7511->cec_adap);
- adv7511->cec_adap = NULL;
- }
- return ret;
+ if (ret)
+ goto err_cec_register;
+ return 0;
+
+err_cec_register:
+ cec_delete_adapter(adv7511->cec_adap);
+ adv7511->cec_adap = NULL;
+err_cec_alloc:
+ dev_info(dev, "Initializing CEC failed with error %d, disabling CEC\n",
+ ret);
+err_cec_parse_dt:
+ regmap_write(adv7511->regmap, ADV7511_REG_CEC_CTRL + offset,
+ ADV7511_CEC_CTRL_POWER_DOWN);
+ return ret == -EPROBE_DEFER ? ret : 0;
}
struct device *dev = &i2c->dev;
unsigned int main_i2c_addr = i2c->addr << 1;
unsigned int edid_i2c_addr = main_i2c_addr + 4;
- unsigned int offset;
unsigned int val;
int ret;
if (adv7511->type == ADV7511)
adv7511_set_link_config(adv7511, &link_config);
+ ret = adv7511_cec_init(dev, adv7511);
+ if (ret)
+ goto err_unregister_cec;
+
adv7511->bridge.funcs = &adv7511_bridge_funcs;
adv7511->bridge.of_node = dev->of_node;
drm_bridge_add(&adv7511->bridge);
adv7511_audio_init(dev, adv7511);
-
- offset = adv7511->type == ADV7533 ? ADV7533_REG_CEC_OFFSET : 0;
-
-#ifdef CONFIG_DRM_I2C_ADV7511_CEC
- ret = adv7511_cec_init(dev, adv7511, offset);
- if (ret)
- goto err_unregister_cec;
-#else
- regmap_write(adv7511->regmap, ADV7511_REG_CEC_CTRL + offset,
- ADV7511_CEC_CTRL_POWER_DOWN);
-#endif
-
return 0;
err_unregister_cec:
#include <linux/of_graph.h>
+struct lvds_encoder {
+ struct drm_bridge bridge;
+ struct drm_bridge *panel_bridge;
+};
+
+static int lvds_encoder_attach(struct drm_bridge *bridge)
+{
+ struct lvds_encoder *lvds_encoder = container_of(bridge,
+ struct lvds_encoder,
+ bridge);
+
+ return drm_bridge_attach(bridge->encoder, lvds_encoder->panel_bridge,
+ bridge);
+}
+
+static struct drm_bridge_funcs funcs = {
+ .attach = lvds_encoder_attach,
+};
+
static int lvds_encoder_probe(struct platform_device *pdev)
{
struct device_node *port;
struct device_node *endpoint;
struct device_node *panel_node;
struct drm_panel *panel;
- struct drm_bridge *bridge;
+ struct lvds_encoder *lvds_encoder;
+
+ lvds_encoder = devm_kzalloc(&pdev->dev, sizeof(*lvds_encoder),
+ GFP_KERNEL);
+ if (!lvds_encoder)
+ return -ENOMEM;
/* Locate the panel DT node. */
port = of_graph_get_port_by_id(pdev->dev.of_node, 1);
return -EPROBE_DEFER;
}
- bridge = drm_panel_bridge_add(panel, DRM_MODE_CONNECTOR_LVDS);
- if (IS_ERR(bridge))
- return PTR_ERR(bridge);
+ lvds_encoder->panel_bridge =
+ devm_drm_panel_bridge_add(&pdev->dev,
+ panel, DRM_MODE_CONNECTOR_LVDS);
+ if (IS_ERR(lvds_encoder->panel_bridge))
+ return PTR_ERR(lvds_encoder->panel_bridge);
+
+ /* The panel_bridge bridge is attached to the panel's of_node,
+ * but we need a bridge attached to our of_node for our user
+ * to look up.
+ */
+ lvds_encoder->bridge.of_node = pdev->dev.of_node;
+ lvds_encoder->bridge.funcs = &funcs;
+ drm_bridge_add(&lvds_encoder->bridge);
- platform_set_drvdata(pdev, bridge);
+ platform_set_drvdata(pdev, lvds_encoder);
return 0;
}
static int lvds_encoder_remove(struct platform_device *pdev)
{
- struct drm_bridge *bridge = platform_get_drvdata(pdev);
+ struct lvds_encoder *lvds_encoder = platform_get_drvdata(pdev);
- drm_bridge_remove(bridge);
+ drm_bridge_remove(&lvds_encoder->bridge);
return 0;
}
struct device *dev;
struct clk *isfr_clk;
struct clk *iahb_clk;
+ struct clk *cec_clk;
struct dw_hdmi_i2c *i2c;
struct hdmi_data_info hdmi_data;
goto err_isfr;
}
+ hdmi->cec_clk = devm_clk_get(hdmi->dev, "cec");
+ if (PTR_ERR(hdmi->cec_clk) == -ENOENT) {
+ hdmi->cec_clk = NULL;
+ } else if (IS_ERR(hdmi->cec_clk)) {
+ ret = PTR_ERR(hdmi->cec_clk);
+ if (ret != -EPROBE_DEFER)
+ dev_err(hdmi->dev, "Cannot get HDMI cec clock: %d\n",
+ ret);
+
+ hdmi->cec_clk = NULL;
+ goto err_iahb;
+ } else {
+ ret = clk_prepare_enable(hdmi->cec_clk);
+ if (ret) {
+ dev_err(hdmi->dev, "Cannot enable HDMI cec clock: %d\n",
+ ret);
+ goto err_iahb;
+ }
+ }
+
/* Product and revision IDs */
hdmi->version = (hdmi_readb(hdmi, HDMI_DESIGN_ID) << 8)
| (hdmi_readb(hdmi, HDMI_REVISION_ID) << 0);
cec_notifier_put(hdmi->cec_notifier);
clk_disable_unprepare(hdmi->iahb_clk);
+ if (hdmi->cec_clk)
+ clk_disable_unprepare(hdmi->cec_clk);
err_isfr:
clk_disable_unprepare(hdmi->isfr_clk);
err_res:
clk_disable_unprepare(hdmi->iahb_clk);
clk_disable_unprepare(hdmi->isfr_clk);
+ if (hdmi->cec_clk)
+ clk_disable_unprepare(hdmi->cec_clk);
if (hdmi->i2c)
i2c_del_adapter(&hdmi->i2c->adap);
#define DP0_ACTIVEVAL 0x0650
#define DP0_SYNCVAL 0x0654
#define DP0_MISC 0x0658
-#define TU_SIZE_RECOMMENDED (0x3f << 16) /* LSCLK cycles per TU */
+#define TU_SIZE_RECOMMENDED (63) /* LSCLK cycles per TU */
#define BPC_6 (0 << 5)
#define BPC_8 (1 << 5)
tmp = (tmp << 8) | buf[i];
i++;
if (((i % 4) == 0) || (i == size)) {
- tc_write(DP0_AUXWDATA(i >> 2), tmp);
+ tc_write(DP0_AUXWDATA((i - 1) >> 2), tmp);
tmp = 0;
}
}
ret = drm_dp_link_probe(&tc->aux, &tc->link.base);
if (ret < 0)
goto err_dpcd_read;
- if ((tc->link.base.rate != 162000) && (tc->link.base.rate != 270000))
- goto err_dpcd_inval;
+ if (tc->link.base.rate != 162000 && tc->link.base.rate != 270000) {
+ dev_dbg(tc->dev, "Falling to 2.7 Gbps rate\n");
+ tc->link.base.rate = 270000;
+ }
+
+ if (tc->link.base.num_lanes > 2) {
+ dev_dbg(tc->dev, "Falling to 2 lanes\n");
+ tc->link.base.num_lanes = 2;
+ }
ret = drm_dp_dpcd_readb(&tc->aux, DP_MAX_DOWNSPREAD, tmp);
if (ret < 0)
err_dpcd_read:
dev_err(tc->dev, "failed to read DPCD: %d\n", ret);
return ret;
-err_dpcd_inval:
- dev_err(tc->dev, "invalid DPCD\n");
- return -EINVAL;
}
static int tc_set_video_mode(struct tc_data *tc, struct drm_display_mode *mode)
int lower_margin = mode->vsync_start - mode->vdisplay;
int vsync_len = mode->vsync_end - mode->vsync_start;
+ /*
+ * Recommended maximum number of symbols transferred in a transfer unit:
+ * DIV_ROUND_UP((input active video bandwidth in bytes) * tu_size,
+ * (output active video bandwidth in bytes))
+ * Must be less than tu_size.
+ */
+ max_tu_symbol = TU_SIZE_RECOMMENDED - 1;
+
dev_dbg(tc->dev, "set mode %dx%d\n",
mode->hdisplay, mode->vdisplay);
dev_dbg(tc->dev, "H margin %d,%d sync %d\n",
dev_dbg(tc->dev, "total: %dx%d\n", mode->htotal, mode->vtotal);
- /* LCD Ctl Frame Size */
- tc_write(VPCTRL0, (0x40 << 20) /* VSDELAY */ |
+ /*
+ * LCD Ctl Frame Size
+ * datasheet is not clear of vsdelay in case of DPI
+ * assume we do not need any delay when DPI is a source of
+ * sync signals
+ */
+ tc_write(VPCTRL0, (0 << 20) /* VSDELAY */ |
OPXLFMT_RGB888 | FRMSYNC_DISABLED | MSF_DISABLED);
- tc_write(HTIM01, (left_margin << 16) | /* H back porch */
- (hsync_len << 0)); /* Hsync */
- tc_write(HTIM02, (right_margin << 16) | /* H front porch */
- (mode->hdisplay << 0)); /* width */
+ tc_write(HTIM01, (ALIGN(left_margin, 2) << 16) | /* H back porch */
+ (ALIGN(hsync_len, 2) << 0)); /* Hsync */
+ tc_write(HTIM02, (ALIGN(right_margin, 2) << 16) | /* H front porch */
+ (ALIGN(mode->hdisplay, 2) << 0)); /* width */
tc_write(VTIM01, (upper_margin << 16) | /* V back porch */
(vsync_len << 0)); /* Vsync */
tc_write(VTIM02, (lower_margin << 16) | /* V front porch */
/* DP Main Stream Attributes */
vid_sync_dly = hsync_len + left_margin + mode->hdisplay;
tc_write(DP0_VIDSYNCDELAY,
- (0x003e << 16) | /* thresh_dly */
+ (max_tu_symbol << 16) | /* thresh_dly */
(vid_sync_dly << 0));
tc_write(DP0_TOTALVAL, (mode->vtotal << 16) | (mode->htotal));
tc_write(DPIPXLFMT, VS_POL_ACTIVE_LOW | HS_POL_ACTIVE_LOW |
DE_POL_ACTIVE_HIGH | SUB_CFG_TYPE_CONFIG1 | DPI_BPP_RGB888);
- /*
- * Recommended maximum number of symbols transferred in a transfer unit:
- * DIV_ROUND_UP((input active video bandwidth in bytes) * tu_size,
- * (output active video bandwidth in bytes))
- * Must be less than tu_size.
- */
- max_tu_symbol = TU_SIZE_RECOMMENDED - 1;
- tc_write(DP0_MISC, (max_tu_symbol << 23) | TU_SIZE_RECOMMENDED | BPC_8);
+ tc_write(DP0_MISC, (max_tu_symbol << 23) | (TU_SIZE_RECOMMENDED << 16) |
+ BPC_8);
return 0;
err:
unsigned int rate;
u32 dp_phy_ctrl;
int timeout;
- bool aligned;
- bool ready;
u32 value;
int ret;
u8 tmp[8];
ret = drm_dp_dpcd_read_link_status(aux, tmp + 2);
if (ret < 0)
goto err_dpcd_read;
- ready = (tmp[2] == ((DP_CHANNEL_EQ_BITS << 4) | /* Lane1 */
- DP_CHANNEL_EQ_BITS)); /* Lane0 */
- aligned = tmp[4] & DP_INTERLANE_ALIGN_DONE;
- } while ((--timeout) && !(ready && aligned));
+ } while ((--timeout) &&
+ !(drm_dp_channel_eq_ok(tmp + 2, tc->link.base.num_lanes)));
if (timeout == 0) {
/* Read DPCD 0x200-0x201 */
ret = drm_dp_dpcd_read(aux, DP_SINK_COUNT, tmp, 2);
if (ret < 0)
goto err_dpcd_read;
+ dev_err(dev, "channel(s) EQ not ok\n");
dev_info(dev, "0x0200 SINK_COUNT: 0x%02x\n", tmp[0]);
dev_info(dev, "0x0201 DEVICE_SERVICE_IRQ_VECTOR: 0x%02x\n",
tmp[1]);
dev_info(dev, "0x0206 ADJUST_REQUEST_LANE0_1: 0x%02x\n",
tmp[6]);
- if (!ready)
- dev_err(dev, "Lane0/1 not ready\n");
- if (!aligned)
- dev_err(dev, "Lane0/1 not aligned\n");
return -EAGAIN;
}
static int tc_connector_mode_valid(struct drm_connector *connector,
struct drm_display_mode *mode)
{
- /* Accept any mode */
+ /* DPI interface clock limitation: upto 154 MHz */
+ if (mode->clock > 154000)
+ return MODE_CLOCK_HIGH;
+
return MODE_OK;
}
return;
for_each_oldnew_crtc_in_state(old_state, crtc, old_crtc_state, new_crtc_state, i) {
- if (!new_crtc_state->active || !new_crtc_state->planes_changed)
+ if (!new_crtc_state->active)
continue;
ret = drm_crtc_vblank_get(crtc);
drm_hdmi_avi_infoframe_quant_range(struct hdmi_avi_infoframe *frame,
const struct drm_display_mode *mode,
enum hdmi_quantization_range rgb_quant_range,
- bool rgb_quant_range_selectable)
+ bool rgb_quant_range_selectable,
+ bool is_hdmi2_sink)
{
/*
* CEA-861:
* YQ-field to match the RGB Quantization Range being transmitted
* (e.g., when Limited Range RGB, set YQ=0 or when Full Range RGB,
* set YQ=1) and the Sink shall ignore the YQ-field."
+ *
+ * Unfortunate certain sinks (eg. VIZ Model 67/E261VA) get confused
+ * by non-zero YQ when receiving RGB. There doesn't seem to be any
+ * good way to tell which version of CEA-861 the sink supports, so
+ * we limit non-zero YQ to HDMI 2.0 sinks only as HDMI 2.0 is based
+ * on on CEA-861-F.
*/
- if (rgb_quant_range == HDMI_QUANTIZATION_RANGE_LIMITED)
+ if (!is_hdmi2_sink ||
+ rgb_quant_range == HDMI_QUANTIZATION_RANGE_LIMITED)
frame->ycc_quantization_range =
HDMI_YCC_QUANTIZATION_RANGE_LIMITED;
else
if (crtc_count == 0 || sizes.fb_width == -1 || sizes.fb_height == -1) {
DRM_INFO("Cannot find any crtc or sizes\n");
+
+ /* First time: disable all crtc's.. */
+ if (!fb_helper->deferred_setup && !READ_ONCE(fb_helper->dev->master))
+ restore_fbdev_mode(fb_helper);
return -EAGAIN;
}
e->event.base.type = DRM_EVENT_FLIP_COMPLETE;
e->event.base.length = sizeof(e->event);
e->event.vbl.user_data = page_flip->user_data;
+ e->event.vbl.crtc_id = crtc->base.id;
ret = drm_event_reserve_init(dev, file_priv, &e->base, &e->event.base);
if (ret) {
kfree(e);
struct intel_shadow_bb_entry *entry_obj;
struct intel_vgpu *vgpu = s->vgpu;
unsigned long gma = 0;
- uint32_t bb_size;
+ int bb_size;
void *dst = NULL;
int ret = 0;
static int setup_virtual_dp_monitor(struct intel_vgpu *vgpu, int port_num,
int type, unsigned int resolution)
{
+ struct drm_i915_private *dev_priv = vgpu->gvt->dev_priv;
struct intel_vgpu_port *port = intel_vgpu_port(vgpu, port_num);
if (WARN_ON(resolution >= GVT_EDID_NUM))
port->type = type;
emulate_monitor_status_change(vgpu);
+ vgpu_vreg(vgpu, PIPECONF(PIPE_A)) |= PIPECONF_ENABLE;
return 0;
}
goto err_unpin_mm;
}
+ ret = intel_gvt_generate_request(workload);
+ if (ret) {
+ gvt_vgpu_err("fail to generate request\n");
+ goto err_unpin_mm;
+ }
+
ret = prepare_shadow_batch_buffer(workload);
if (ret) {
gvt_vgpu_err("fail to prepare_shadow_batch_buffer\n");
#define GTT_HAW 46
-#define ADDR_1G_MASK (((1UL << (GTT_HAW - 30 + 1)) - 1) << 30)
-#define ADDR_2M_MASK (((1UL << (GTT_HAW - 21 + 1)) - 1) << 21)
-#define ADDR_4K_MASK (((1UL << (GTT_HAW - 12 + 1)) - 1) << 12)
+#define ADDR_1G_MASK (((1UL << (GTT_HAW - 30)) - 1) << 30)
+#define ADDR_2M_MASK (((1UL << (GTT_HAW - 21)) - 1) << 21)
+#define ADDR_4K_MASK (((1UL << (GTT_HAW - 12)) - 1) << 12)
static unsigned long gen8_gtt_get_pfn(struct intel_gvt_gtt_entry *e)
{
return intel_vgpu_default_mmio_write(vgpu, offset, &v, bytes);
}
-static int skl_misc_ctl_write(struct intel_vgpu *vgpu, unsigned int offset,
- void *p_data, unsigned int bytes)
-{
- struct drm_i915_private *dev_priv = vgpu->gvt->dev_priv;
- u32 v = *(u32 *)p_data;
-
- if (!IS_SKYLAKE(dev_priv) && !IS_KABYLAKE(dev_priv))
- return intel_vgpu_default_mmio_write(vgpu,
- offset, p_data, bytes);
-
- switch (offset) {
- case 0x4ddc:
- /* bypass WaCompressedResourceSamplerPbeMediaNewHashMode */
- vgpu_vreg(vgpu, offset) = v & ~(1 << 31);
- break;
- case 0x42080:
- /* bypass WaCompressedResourceDisplayNewHashMode */
- vgpu_vreg(vgpu, offset) = v & ~(1 << 15);
- break;
- case 0xe194:
- /* bypass WaCompressedResourceSamplerPbeMediaNewHashMode */
- vgpu_vreg(vgpu, offset) = v & ~(1 << 8);
- break;
- case 0x7014:
- /* bypass WaCompressedResourceSamplerPbeMediaNewHashMode */
- vgpu_vreg(vgpu, offset) = v & ~(1 << 13);
- break;
- default:
- return -EINVAL;
- }
-
- return 0;
-}
-
static int skl_lcpll_write(struct intel_vgpu *vgpu, unsigned int offset,
void *p_data, unsigned int bytes)
{
MMIO_DFH(GAM_ECOCHK, D_ALL, F_CMD_ACCESS, NULL, NULL);
MMIO_DFH(GEN7_COMMON_SLICE_CHICKEN1, D_ALL, F_MODE_MASK | F_CMD_ACCESS,
NULL, NULL);
- MMIO_DFH(COMMON_SLICE_CHICKEN2, D_ALL, F_MODE_MASK | F_CMD_ACCESS, NULL,
- skl_misc_ctl_write);
+ MMIO_DFH(COMMON_SLICE_CHICKEN2, D_ALL, F_MODE_MASK | F_CMD_ACCESS,
+ NULL, NULL);
MMIO_DFH(0x9030, D_ALL, F_CMD_ACCESS, NULL, NULL);
MMIO_DFH(0x20a0, D_ALL, F_CMD_ACCESS, NULL, NULL);
MMIO_DFH(0x2420, D_ALL, F_CMD_ACCESS, NULL, NULL);
MMIO_D(0x6e570, D_BDW_PLUS);
MMIO_D(0x65f10, D_BDW_PLUS);
- MMIO_DFH(0xe194, D_BDW_PLUS, F_MODE_MASK | F_CMD_ACCESS, NULL,
- skl_misc_ctl_write);
+ MMIO_DFH(0xe194, D_BDW_PLUS, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL);
MMIO_DFH(0xe188, D_BDW_PLUS, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL);
MMIO_DFH(HALF_SLICE_CHICKEN2, D_BDW_PLUS, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL);
MMIO_DFH(0x2580, D_BDW_PLUS, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL);
MMIO_D(GEN9_MEDIA_PG_IDLE_HYSTERESIS, D_SKL_PLUS);
MMIO_D(GEN9_RENDER_PG_IDLE_HYSTERESIS, D_SKL_PLUS);
MMIO_DFH(GEN9_GAMT_ECO_REG_RW_IA, D_SKL_PLUS, F_CMD_ACCESS, NULL, NULL);
- MMIO_DH(0x4ddc, D_SKL_PLUS, NULL, skl_misc_ctl_write);
- MMIO_DH(0x42080, D_SKL_PLUS, NULL, skl_misc_ctl_write);
+ MMIO_DH(0x4ddc, D_SKL_PLUS, NULL, NULL);
+ MMIO_DH(0x42080, D_SKL_PLUS, NULL, NULL);
MMIO_D(0x45504, D_SKL_PLUS);
MMIO_D(0x45520, D_SKL_PLUS);
MMIO_D(0x46000, D_SKL_PLUS);
struct intel_gvt_workload_scheduler *scheduler = &gvt->scheduler;
enum intel_engine_id ring_id = req->engine->id;
struct intel_vgpu_workload *workload;
+ unsigned long flags;
if (!is_gvt_request(req)) {
- spin_lock_bh(&scheduler->mmio_context_lock);
+ spin_lock_irqsave(&scheduler->mmio_context_lock, flags);
if (action == INTEL_CONTEXT_SCHEDULE_IN &&
scheduler->engine_owner[ring_id]) {
/* Switch ring from vGPU to host. */
NULL, ring_id);
scheduler->engine_owner[ring_id] = NULL;
}
- spin_unlock_bh(&scheduler->mmio_context_lock);
+ spin_unlock_irqrestore(&scheduler->mmio_context_lock, flags);
return NOTIFY_OK;
}
switch (action) {
case INTEL_CONTEXT_SCHEDULE_IN:
- spin_lock_bh(&scheduler->mmio_context_lock);
+ spin_lock_irqsave(&scheduler->mmio_context_lock, flags);
if (workload->vgpu != scheduler->engine_owner[ring_id]) {
/* Switch ring from host to vGPU or vGPU to vGPU. */
intel_gvt_switch_mmio(scheduler->engine_owner[ring_id],
} else
gvt_dbg_sched("skip ring %d mmio switch for vgpu%d\n",
ring_id, workload->vgpu->id);
- spin_unlock_bh(&scheduler->mmio_context_lock);
+ spin_unlock_irqrestore(&scheduler->mmio_context_lock, flags);
atomic_set(&workload->shadow_ctx_active, 1);
break;
case INTEL_CONTEXT_SCHEDULE_OUT:
struct i915_gem_context *shadow_ctx = workload->vgpu->shadow_ctx;
struct drm_i915_private *dev_priv = workload->vgpu->gvt->dev_priv;
struct intel_engine_cs *engine = dev_priv->engine[ring_id];
- struct drm_i915_gem_request *rq;
struct intel_vgpu *vgpu = workload->vgpu;
struct intel_ring *ring;
int ret;
ret = populate_shadow_context(workload);
if (ret)
goto err_unpin;
+ workload->shadowed = true;
+ return 0;
+
+err_unpin:
+ engine->context_unpin(engine, shadow_ctx);
+err_shadow:
+ release_shadow_wa_ctx(&workload->wa_ctx);
+err_scan:
+ return ret;
+}
+
+int intel_gvt_generate_request(struct intel_vgpu_workload *workload)
+{
+ int ring_id = workload->ring_id;
+ struct drm_i915_private *dev_priv = workload->vgpu->gvt->dev_priv;
+ struct intel_engine_cs *engine = dev_priv->engine[ring_id];
+ struct drm_i915_gem_request *rq;
+ struct intel_vgpu *vgpu = workload->vgpu;
+ struct i915_gem_context *shadow_ctx = vgpu->shadow_ctx;
+ int ret;
rq = i915_gem_request_alloc(dev_priv->engine[ring_id], shadow_ctx);
if (IS_ERR(rq)) {
ret = copy_workload_to_ring_buffer(workload);
if (ret)
goto err_unpin;
- workload->shadowed = true;
return 0;
err_unpin:
engine->context_unpin(engine, shadow_ctx);
-err_shadow:
release_shadow_wa_ctx(&workload->wa_ctx);
-err_scan:
return ret;
}
void intel_vgpu_clean_gvt_context(struct intel_vgpu *vgpu);
void release_shadow_wa_ctx(struct intel_shadow_wa_ctx *wa_ctx);
+
+int intel_gvt_generate_request(struct intel_vgpu_workload *workload);
+
#endif
intel_guc_resume(dev_priv);
intel_modeset_init_hw(dev);
+ intel_init_clock_gating(dev_priv);
spin_lock_irq(&dev_priv->irq_lock);
if (dev_priv->display.hpd_irq_setup)
ret = vlv_resume_prepare(dev_priv, true);
}
+ intel_uncore_runtime_resume(dev_priv);
+
/*
* No point of rolling back things in case of an error, as the best
* we can do is to hope that things will still work (and disable RPM).
spin_lock_init(&mn->lock);
mn->mn.ops = &i915_gem_userptr_notifier;
mn->objects = RB_ROOT_CACHED;
- mn->wq = alloc_workqueue("i915-userptr-release", WQ_UNBOUND, 0);
+ mn->wq = alloc_workqueue("i915-userptr-release",
+ WQ_UNBOUND | WQ_MEM_RECLAIM,
+ 0);
if (mn->wq == NULL) {
kfree(mn);
return ERR_PTR(-ENOMEM);
dev_priv->mm.userptr_wq =
alloc_workqueue("i915-userptr-acquire",
- WQ_HIGHPRI | WQ_MEM_RECLAIM,
+ WQ_HIGHPRI | WQ_UNBOUND,
0);
if (!dev_priv->mm.userptr_wq)
return -ENOMEM;
if (has_transparent_hugepage()) {
struct super_block *sb = gemfs->mnt_sb;
- char options[] = "huge=within_size";
+ /* FIXME: Disabled until we get W/A for read BW issue. */
+ char options[] = "huge=never";
int flags = 0;
int err;
GEM_BUG_ON(RB_EMPTY_NODE(&wait->node));
rb_erase(&wait->node, &b->waiters);
+ RB_CLEAR_NODE(&wait->node);
out:
GEM_BUG_ON(b->irq_wait == wait);
int intel_backlight_device_register(struct intel_connector *connector);
void intel_backlight_device_unregister(struct intel_connector *connector);
#else /* CONFIG_BACKLIGHT_CLASS_DEVICE */
-static int intel_backlight_device_register(struct intel_connector *connector)
+static inline int intel_backlight_device_register(struct intel_connector *connector)
{
return 0;
}
/* Due to peculiar init order wrt to hpd handling this is separate. */
if (drm_fb_helper_initial_config(&ifbdev->helper,
- ifbdev->preferred_bpp)) {
+ ifbdev->preferred_bpp))
intel_fbdev_unregister(to_i915(ifbdev->helper.dev));
- intel_fbdev_fini(to_i915(ifbdev->helper.dev));
- }
}
void intel_fbdev_initial_config_async(struct drm_device *dev)
{
struct intel_fbdev *ifbdev = to_i915(dev)->fbdev;
- if (ifbdev)
+ if (!ifbdev)
+ return;
+
+ intel_fbdev_sync(ifbdev);
+ if (ifbdev->vma)
drm_fb_helper_hotplug_event(&ifbdev->helper);
}
crtc_state->limited_color_range ?
HDMI_QUANTIZATION_RANGE_LIMITED :
HDMI_QUANTIZATION_RANGE_FULL,
- intel_hdmi->rgb_quant_range_selectable);
+ intel_hdmi->rgb_quant_range_selectable,
+ is_hdmi2_sink);
/* TODO: handle pixel repetition for YCBCR420 outputs */
intel_write_infoframe(encoder, crtc_state, &frame);
gmbus_is_index_read(struct i2c_msg *msgs, int i, int num)
{
return (i + 1 < num &&
- !(msgs[i].flags & I2C_M_RD) && msgs[i].len <= 2 &&
+ msgs[i].addr == msgs[i + 1].addr &&
+ !(msgs[i].flags & I2C_M_RD) &&
+ (msgs[i].len == 1 || msgs[i].len == 2) &&
(msgs[i + 1].flags & I2C_M_RD));
}
i915_check_and_clear_faults(dev_priv);
}
+void intel_uncore_runtime_resume(struct drm_i915_private *dev_priv)
+{
+ iosf_mbi_register_pmic_bus_access_notifier(
+ &dev_priv->uncore.pmic_bus_access_nb);
+}
+
void intel_uncore_sanitize(struct drm_i915_private *dev_priv)
{
i915_modparams.enable_rc6 =
* bus, which will be busy after this notification, leading to:
* "render: timed out waiting for forcewake ack request."
* errors.
+ *
+ * The notifier is unregistered during intel_runtime_suspend(),
+ * so it's ok to access the HW here without holding a RPM
+ * wake reference -> disable wakeref asserts for the time of
+ * the access.
*/
+ disable_rpm_wakeref_asserts(dev_priv);
intel_uncore_forcewake_get(dev_priv, FORCEWAKE_ALL);
+ enable_rpm_wakeref_asserts(dev_priv);
break;
case MBI_PMIC_BUS_ACCESS_END:
intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL);
void intel_uncore_fini(struct drm_i915_private *dev_priv);
void intel_uncore_suspend(struct drm_i915_private *dev_priv);
void intel_uncore_resume_early(struct drm_i915_private *dev_priv);
+void intel_uncore_runtime_resume(struct drm_i915_private *dev_priv);
u64 intel_uncore_edram_size(struct drm_i915_private *dev_priv);
void assert_forcewakes_inactive(struct drm_i915_private *dev_priv);
plane_disabling = true;
}
- if (plane_disabling) {
- drm_atomic_helper_wait_for_vblanks(dev, state);
+ /*
+ * The flip done wait is only strictly required by imx-drm if a deferred
+ * plane disable is in-flight. As the core requires blocking commits
+ * to wait for the flip it is done here unconditionally. This keeps the
+ * workitem around a bit longer than required for the majority of
+ * non-blocking commits, but we accept that for the sake of simplicity.
+ */
+ drm_atomic_helper_wait_for_flip_done(dev, state);
+ if (plane_disabling) {
for_each_old_plane_in_state(state, plane, old_plane_state, i)
ipu_plane_disable_deferred(plane);
config DRM_OMAP_PANEL_DPI
tristate "Generic DPI panel"
+ depends on BACKLIGHT_CLASS_DEVICE
help
Driver for generic DPI panels.
}
static const struct soc_device_attribute dpi_soc_devices[] = {
- { .family = "OMAP3[456]*" },
- { .family = "[AD]M37*" },
+ { .machine = "OMAP3[456]*" },
+ { .machine = "[AD]M37*" },
{ /* sentinel */ }
};
{
const u32 caps = CEC_CAP_TRANSMIT | CEC_CAP_LOG_ADDRS |
CEC_CAP_PASSTHROUGH | CEC_CAP_RC;
- unsigned int ret;
+ int ret;
core->adap = cec_allocate_adapter(&hdmi_cec_adap_ops, core,
"omap4", caps, CEC_MAX_LOG_ADDRS);
bool audio_use_mclk;
};
-static const struct hdmi4_features hdmi4_es1_features = {
+static const struct hdmi4_features hdmi4430_es1_features = {
.cts_swmode = false,
.audio_use_mclk = false,
};
-static const struct hdmi4_features hdmi4_es2_features = {
+static const struct hdmi4_features hdmi4430_es2_features = {
.cts_swmode = true,
.audio_use_mclk = false,
};
-static const struct hdmi4_features hdmi4_es3_features = {
+static const struct hdmi4_features hdmi4_features = {
.cts_swmode = true,
.audio_use_mclk = true,
};
static const struct soc_device_attribute hdmi4_soc_devices[] = {
- { .family = "OMAP4", .revision = "ES1.?", .data = &hdmi4_es1_features },
- { .family = "OMAP4", .revision = "ES2.?", .data = &hdmi4_es2_features },
- { .family = "OMAP4", .data = &hdmi4_es3_features },
+ {
+ .machine = "OMAP4430",
+ .revision = "ES1.?",
+ .data = &hdmi4430_es1_features,
+ },
+ {
+ .machine = "OMAP4430",
+ .revision = "ES2.?",
+ .data = &hdmi4430_es2_features,
+ },
+ {
+ .family = "OMAP4",
+ .data = &hdmi4_features,
+ },
{ /* sentinel */ }
};
match = of_match_node(dmm_of_match, dev->dev.of_node);
if (!match) {
dev_err(&dev->dev, "failed to find matching device node\n");
- return -ENODEV;
+ ret = -ENODEV;
+ goto fail;
}
omap_dmm->plat_data = match->data;
WREG32(VM_INVALIDATE_REQUEST, 0x1);
}
-static void cik_pcie_init_compute_vmid(struct radeon_device *rdev)
-{
- int i;
- uint32_t sh_mem_bases, sh_mem_config;
-
- sh_mem_bases = 0x6000 | 0x6000 << 16;
- sh_mem_config = ALIGNMENT_MODE(SH_MEM_ALIGNMENT_MODE_UNALIGNED);
- sh_mem_config |= DEFAULT_MTYPE(MTYPE_NONCACHED);
-
- mutex_lock(&rdev->srbm_mutex);
- for (i = 8; i < 16; i++) {
- cik_srbm_select(rdev, 0, 0, 0, i);
- /* CP and shaders */
- WREG32(SH_MEM_CONFIG, sh_mem_config);
- WREG32(SH_MEM_APE1_BASE, 1);
- WREG32(SH_MEM_APE1_LIMIT, 0);
- WREG32(SH_MEM_BASES, sh_mem_bases);
- }
- cik_srbm_select(rdev, 0, 0, 0, 0);
- mutex_unlock(&rdev->srbm_mutex);
-}
-
/**
* cik_pcie_gart_enable - gart enable
*
cik_srbm_select(rdev, 0, 0, 0, 0);
mutex_unlock(&rdev->srbm_mutex);
- cik_pcie_init_compute_vmid(rdev);
-
cik_pcie_gart_tlb_flush(rdev);
DRM_INFO("PCIE GART of %uM enabled (table at 0x%016llX).\n",
(unsigned)(rdev->mc.gtt_size >> 20),
goto err_pllref;
}
- pm_runtime_enable(dev);
-
dsi->dsi_host.ops = &dw_mipi_dsi_host_ops;
dsi->dsi_host.dev = dev;
ret = mipi_dsi_host_register(&dsi->dsi_host);
}
dev_set_drvdata(dev, dsi);
+ pm_runtime_enable(dev);
return 0;
err_mipi_dsi_host:
}
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
- for (j = 0; j < HPAGE_PMD_NR; ++j)
- if (p++ != pages[i + j])
- break;
+ if (!(flags & TTM_PAGE_FLAG_DMA32)) {
+ for (j = 0; j < HPAGE_PMD_NR; ++j)
+ if (p++ != pages[i + j])
+ break;
- if (j == HPAGE_PMD_NR)
- order = HPAGE_PMD_ORDER;
+ if (j == HPAGE_PMD_NR)
+ order = HPAGE_PMD_ORDER;
+ }
#endif
if (page_count(pages[i]) != 1)
i = 0;
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
- while (npages >= HPAGE_PMD_NR) {
- gfp_t huge_flags = gfp_flags;
+ if (!(gfp_flags & GFP_DMA32)) {
+ while (npages >= HPAGE_PMD_NR) {
+ gfp_t huge_flags = gfp_flags;
- huge_flags |= GFP_TRANSHUGE;
- huge_flags &= ~__GFP_MOVABLE;
- huge_flags &= ~__GFP_COMP;
- p = alloc_pages(huge_flags, HPAGE_PMD_ORDER);
- if (!p)
- break;
+ huge_flags |= GFP_TRANSHUGE;
+ huge_flags &= ~__GFP_MOVABLE;
+ huge_flags &= ~__GFP_COMP;
+ p = alloc_pages(huge_flags, HPAGE_PMD_ORDER);
+ if (!p)
+ break;
- for (j = 0; j < HPAGE_PMD_NR; ++j)
- pages[i++] = p++;
+ for (j = 0; j < HPAGE_PMD_NR; ++j)
+ pages[i++] = p++;
- npages -= HPAGE_PMD_NR;
+ npages -= HPAGE_PMD_NR;
+ }
}
#endif
}
EXPORT_SYMBOL(ttm_pool_unpopulate);
-#if defined(CONFIG_SWIOTLB) || defined(CONFIG_INTEL_IOMMU)
int ttm_populate_and_map_pages(struct device *dev, struct ttm_dma_tt *tt)
{
unsigned i, j;
ttm_pool_unpopulate(&tt->ttm);
}
EXPORT_SYMBOL(ttm_unmap_and_unpopulate_pages);
-#endif
int ttm_page_alloc_debugfs(struct seq_file *m, void *data)
{
vc4_encoder->limited_rgb_range ?
HDMI_QUANTIZATION_RANGE_LIMITED :
HDMI_QUANTIZATION_RANGE_FULL,
- vc4_encoder->rgb_range_selectable);
+ vc4_encoder->rgb_range_selectable,
+ false);
vc4_hdmi_write_infoframe(encoder, &frame);
}
{
struct vc4_dev *vc4 = to_vc4_dev(dev);
+ /* Undo the effects of a previous vc4_irq_uninstall. */
+ enable_irq(dev->irq);
+
/* Enable both the render done and out of memory interrupts. */
V3D_WRITE(V3D_INTENA, V3D_DRIVER_IRQS);
/* Clear any pending interrupts we might have left. */
V3D_WRITE(V3D_INTCTL, V3D_DRIVER_IRQS);
+ /* Finish any interrupt handler still in flight. */
+ disable_irq(dev->irq);
+
cancel_work_sync(&vc4->overflow_mem_work);
}
sg_list_start = umem->sg_head.sgl;
while (npages) {
- ret = get_user_pages(cur_base,
+ ret = get_user_pages_longterm(cur_base,
min_t(unsigned long, npages,
PAGE_SIZE / sizeof (struct page *)),
gup_flags, page_list, vma_list);
if (b == -1)
goto err;
- k->ptr[i] = PTR(ca->buckets[b].gen,
+ k->ptr[i] = MAKE_PTR(ca->buckets[b].gen,
bucket_to_sector(c, b),
ca->sb.nr_this_dev);
c->shrink.scan_objects = bch_mca_scan;
c->shrink.seeks = 4;
c->shrink.batch = c->btree_pages * 2;
- register_shrinker(&c->shrink);
+
+ if (register_shrinker(&c->shrink))
+ pr_warn("bcache: %s: could not register shrinker",
+ __func__);
return 0;
}
return false;
for (i = 0; i < KEY_PTRS(l); i++)
- if (l->ptr[i] + PTR(0, KEY_SIZE(l), 0) != r->ptr[i] ||
+ if (l->ptr[i] + MAKE_PTR(0, KEY_SIZE(l), 0) != r->ptr[i] ||
PTR_BUCKET_NR(b->c, l, i) != PTR_BUCKET_NR(b->c, r, i))
return false;
* find a sequence of buckets with valid journal entries
*/
for (i = 0; i < ca->sb.njournal_buckets; i++) {
+ /*
+ * We must try the index l with ZERO first for
+ * correctness due to the scenario that the journal
+ * bucket is circular buffer which might have wrapped
+ */
l = (i * 2654435769U) % ca->sb.njournal_buckets;
if (test_bit(l, bitmap))
continue;
ja->cur_idx = next;
- k->ptr[n++] = PTR(0,
+ k->ptr[n++] = MAKE_PTR(0,
bucket_to_sector(c, ca->sb.d[ja->cur_idx]),
ca->sb.nr_this_dev);
}
{
struct search *s = container_of(cl, struct search, cl);
struct bio *bio = &s->bio.bio;
- struct cached_dev *dc = container_of(s->d, struct cached_dev, disk);
/*
- * If cache device is dirty (dc->has_dirty is non-zero), then
- * recovery a failed read request from cached device may get a
- * stale data back. So read failure recovery is only permitted
- * when cache device is clean.
+ * If read request hit dirty data (s->read_dirty_data is true),
+ * then recovery a failed read request from cached device may
+ * get a stale data back. So read failure recovery is only
+ * permitted when read request hit clean data in cache device,
+ * or when cache read race happened.
*/
- if (s->recoverable &&
- (dc && !atomic_read(&dc->has_dirty))) {
+ if (s->recoverable && !s->read_dirty_data) {
/* Retry from the backing device: */
trace_bcache_read_retry(s->orig_bio);
dprintk(1, "init user [0x%lx+0x%lx => %d pages]\n",
data, size, dma->nr_pages);
- err = get_user_pages(data & PAGE_MASK, dma->nr_pages,
+ err = get_user_pages_longterm(data & PAGE_MASK, dma->nr_pages,
flags, dma->pages, NULL);
if (err != dma->nr_pages) {
dma->nr_pages = (err >= 0) ? err : 0;
- dprintk(1, "get_user_pages: err=%d [%d]\n", err, dma->nr_pages);
+ dprintk(1, "get_user_pages_longterm: err=%d [%d]\n", err,
+ dma->nr_pages);
return err < 0 ? err : -EINVAL;
}
return 0;
/* There should only be one entry, but go through the list
* anyway
*/
+ if (afu->phb == NULL)
+ return result;
+
list_for_each_entry(afu_dev, &afu->phb->bus->devices, bus_list) {
if (!afu_dev->driver)
continue;
* Tell the AFU drivers; but we don't care what they
* say, we're going away.
*/
- if (afu->phb != NULL)
- cxl_vphb_error_detected(afu, state);
+ cxl_vphb_error_detected(afu, state);
}
return PCI_ERS_RESULT_DISCONNECT;
}
if (cxl_afu_select_best_mode(afu))
goto err;
+ if (afu->phb == NULL)
+ continue;
+
list_for_each_entry(afu_dev, &afu->phb->bus->devices, bus_list) {
/* Reset the device context.
* TODO: make this less disruptive
for (i = 0; i < adapter->slices; i++) {
afu = adapter->afu[i];
+ if (afu->phb == NULL)
+ continue;
+
list_for_each_entry(afu_dev, &afu->phb->bus->devices, bus_list) {
if (afu_dev->driver && afu_dev->driver->err_handler &&
afu_dev->driver->err_handler->resume)
struct device_attribute force_ro;
struct device_attribute power_ro_lock;
int area_type;
+
+ /* debugfs files (only in main mmc_blk_data) */
+ struct dentry *status_dentry;
+ struct dentry *ext_csd_dentry;
};
/* Device type for RPMB character devices */
/* Dispatch locking to the block layer */
req = blk_get_request(mq->queue, REQ_OP_DRV_OUT, __GFP_RECLAIM);
+ if (IS_ERR(req)) {
+ count = PTR_ERR(req);
+ goto out_put;
+ }
req_to_mmc_queue_req(req)->drv_op = MMC_DRV_OP_BOOT_WP;
blk_execute_rq(mq->queue, NULL, req, 0);
ret = req_to_mmc_queue_req(req)->drv_op_result;
+ blk_put_request(req);
if (!ret) {
pr_info("%s: Locking boot partition ro until next power on\n",
set_disk_ro(part_md->disk, 1);
}
}
-
+out_put:
mmc_blk_put(md);
return count;
}
req = blk_get_request(mq->queue,
idata->ic.write_flag ? REQ_OP_DRV_OUT : REQ_OP_DRV_IN,
__GFP_RECLAIM);
+ if (IS_ERR(req)) {
+ err = PTR_ERR(req);
+ goto cmd_done;
+ }
idatas[0] = idata;
req_to_mmc_queue_req(req)->drv_op =
rpmb ? MMC_DRV_OP_IOCTL_RPMB : MMC_DRV_OP_IOCTL;
req = blk_get_request(mq->queue,
idata[0]->ic.write_flag ? REQ_OP_DRV_OUT : REQ_OP_DRV_IN,
__GFP_RECLAIM);
+ if (IS_ERR(req)) {
+ err = PTR_ERR(req);
+ goto cmd_err;
+ }
req_to_mmc_queue_req(req)->drv_op =
rpmb ? MMC_DRV_OP_IOCTL_RPMB : MMC_DRV_OP_IOCTL;
req_to_mmc_queue_req(req)->drv_op_data = idata;
/* Ask the block layer about the card status */
req = blk_get_request(mq->queue, REQ_OP_DRV_IN, __GFP_RECLAIM);
+ if (IS_ERR(req))
+ return PTR_ERR(req);
req_to_mmc_queue_req(req)->drv_op = MMC_DRV_OP_GET_CARD_STATUS;
blk_execute_rq(mq->queue, NULL, req, 0);
ret = req_to_mmc_queue_req(req)->drv_op_result;
*val = ret;
ret = 0;
}
+ blk_put_request(req);
return ret;
}
/* Ask the block layer for the EXT CSD */
req = blk_get_request(mq->queue, REQ_OP_DRV_IN, __GFP_RECLAIM);
+ if (IS_ERR(req)) {
+ err = PTR_ERR(req);
+ goto out_free;
+ }
req_to_mmc_queue_req(req)->drv_op = MMC_DRV_OP_GET_EXT_CSD;
req_to_mmc_queue_req(req)->drv_op_data = &ext_csd;
blk_execute_rq(mq->queue, NULL, req, 0);
err = req_to_mmc_queue_req(req)->drv_op_result;
+ blk_put_request(req);
if (err) {
pr_err("FAILED %d\n", err);
goto out_free;
.llseek = default_llseek,
};
-static int mmc_blk_add_debugfs(struct mmc_card *card)
+static int mmc_blk_add_debugfs(struct mmc_card *card, struct mmc_blk_data *md)
{
struct dentry *root;
root = card->debugfs_root;
if (mmc_card_mmc(card) || mmc_card_sd(card)) {
- if (!debugfs_create_file("status", S_IRUSR, root, card,
- &mmc_dbg_card_status_fops))
+ md->status_dentry =
+ debugfs_create_file("status", S_IRUSR, root, card,
+ &mmc_dbg_card_status_fops);
+ if (!md->status_dentry)
return -EIO;
}
if (mmc_card_mmc(card)) {
- if (!debugfs_create_file("ext_csd", S_IRUSR, root, card,
- &mmc_dbg_ext_csd_fops))
+ md->ext_csd_dentry =
+ debugfs_create_file("ext_csd", S_IRUSR, root, card,
+ &mmc_dbg_ext_csd_fops);
+ if (!md->ext_csd_dentry)
return -EIO;
}
return 0;
}
+static void mmc_blk_remove_debugfs(struct mmc_card *card,
+ struct mmc_blk_data *md)
+{
+ if (!card->debugfs_root)
+ return;
+
+ if (!IS_ERR_OR_NULL(md->status_dentry)) {
+ debugfs_remove(md->status_dentry);
+ md->status_dentry = NULL;
+ }
+
+ if (!IS_ERR_OR_NULL(md->ext_csd_dentry)) {
+ debugfs_remove(md->ext_csd_dentry);
+ md->ext_csd_dentry = NULL;
+ }
+}
#else
-static int mmc_blk_add_debugfs(struct mmc_card *card)
+static int mmc_blk_add_debugfs(struct mmc_card *card, struct mmc_blk_data *md)
{
return 0;
}
+static void mmc_blk_remove_debugfs(struct mmc_card *card,
+ struct mmc_blk_data *md)
+{
+}
+
#endif /* CONFIG_DEBUG_FS */
static int mmc_blk_probe(struct mmc_card *card)
}
/* Add two debugfs entries */
- mmc_blk_add_debugfs(card);
+ mmc_blk_add_debugfs(card, md);
pm_runtime_set_autosuspend_delay(&card->dev, 3000);
pm_runtime_use_autosuspend(&card->dev);
{
struct mmc_blk_data *md = dev_get_drvdata(&card->dev);
+ mmc_blk_remove_debugfs(card, md);
mmc_blk_remove_parts(card, md);
pm_runtime_get_sync(&card->dev);
mmc_claim_host(card->host);
return ret;
ret = host->bus_ops->suspend(host);
+ if (ret)
+ pm_generic_resume(dev);
+
return ret;
}
void mmc_remove_card_debugfs(struct mmc_card *card)
{
debugfs_remove_recursive(card->debugfs_root);
+ card->debugfs_root = NULL;
}
MMC_DEV_ATTR(oemid, "0x%04x\n", card->cid.oemid);
MMC_DEV_ATTR(prv, "0x%x\n", card->cid.prv);
MMC_DEV_ATTR(rev, "0x%x\n", card->ext_csd.rev);
-MMC_DEV_ATTR(pre_eol_info, "%02x\n", card->ext_csd.pre_eol_info);
+MMC_DEV_ATTR(pre_eol_info, "0x%02x\n", card->ext_csd.pre_eol_info);
MMC_DEV_ATTR(life_time, "0x%02x 0x%02x\n",
card->ext_csd.device_life_time_est_typ_a,
card->ext_csd.device_life_time_est_typ_b);
MMC_DEV_ATTR(enhanced_area_size, "%u\n", card->ext_csd.enhanced_area_size);
MMC_DEV_ATTR(raw_rpmb_size_mult, "%#x\n", card->ext_csd.raw_rpmb_size_mult);
MMC_DEV_ATTR(rel_sectors, "%#x\n", card->ext_csd.rel_sectors);
-MMC_DEV_ATTR(ocr, "%08x\n", card->ocr);
+MMC_DEV_ATTR(ocr, "0x%08x\n", card->ocr);
MMC_DEV_ATTR(cmdq_en, "%d\n", card->ext_csd.cmdq_en);
static ssize_t mmc_fwrev_show(struct device *dev,
MMC_DEV_ATTR(name, "%s\n", card->cid.prod_name);
MMC_DEV_ATTR(oemid, "0x%04x\n", card->cid.oemid);
MMC_DEV_ATTR(serial, "0x%08x\n", card->cid.serial);
-MMC_DEV_ATTR(ocr, "%08x\n", card->ocr);
+MMC_DEV_ATTR(ocr, "0x%08x\n", card->ocr);
static ssize_t mmc_dsr_show(struct device *dev,
#define CORE_VERSION_MAJOR_MASK (0xf << CORE_VERSION_MAJOR_SHIFT)
#define CORE_VERSION_MINOR_MASK 0xff
+#define CORE_MCI_GENERICS 0x70
+#define SWITCHABLE_SIGNALING_VOLTAGE BIT(29)
+
#define CORE_HC_MODE 0x78
#define HC_MODE_EN 0x1
#define CORE_POWER 0x0
struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
struct sdhci_msm_host *msm_host = sdhci_pltfm_priv(pltfm_host);
bool done = false;
+ u32 val;
pr_debug("%s: %s: request %d curr_pwr_state %x curr_io_level %x\n",
mmc_hostname(host->mmc), __func__, req_type,
msm_host->curr_pwr_state, msm_host->curr_io_level);
/*
+ * The power interrupt will not be generated for signal voltage
+ * switches if SWITCHABLE_SIGNALING_VOLTAGE in MCI_GENERICS is not set.
+ */
+ val = readl(msm_host->core_mem + CORE_MCI_GENERICS);
+ if ((req_type & REQ_IO_HIGH || req_type & REQ_IO_LOW) &&
+ !(val & SWITCHABLE_SIGNALING_VOLTAGE)) {
+ return;
+ }
+
+ /*
* The IRQ for request type IO High/LOW will be generated when -
* there is a state change in 1.8V enable bit (bit 3) of
* SDHCI_HOST_CONTROL2 register. The reset state of that bit is 0
#include <linux/dma-mapping.h>
#include <linux/slab.h>
#include <linux/scatterlist.h>
+#include <linux/swiotlb.h>
#include <linux/regulator/consumer.h>
#include <linux/pm_runtime.h>
#include <linux/of.h>
spin_lock_init(&host->lock);
/*
+ * Maximum number of sectors in one transfer. Limited by SDMA boundary
+ * size (512KiB). Note some tuning modes impose a 4MiB limit, but this
+ * is less anyway.
+ */
+ mmc->max_req_size = 524288;
+
+ /*
* Maximum number of segments. Depends on if the hardware
* can do scatter/gather or not.
*/
- if (host->flags & SDHCI_USE_ADMA)
+ if (host->flags & SDHCI_USE_ADMA) {
mmc->max_segs = SDHCI_MAX_SEGS;
- else if (host->flags & SDHCI_USE_SDMA)
+ } else if (host->flags & SDHCI_USE_SDMA) {
mmc->max_segs = 1;
- else /* PIO */
+ if (swiotlb_max_segment()) {
+ unsigned int max_req_size = (1 << IO_TLB_SHIFT) *
+ IO_TLB_SEGSIZE;
+ mmc->max_req_size = min(mmc->max_req_size,
+ max_req_size);
+ }
+ } else { /* PIO */
mmc->max_segs = SDHCI_MAX_SEGS;
-
- /*
- * Maximum number of sectors in one transfer. Limited by SDMA boundary
- * size (512KiB). Note some tuning modes impose a 4MiB limit, but this
- * is less anyway.
- */
- mmc->max_req_size = 524288;
+ }
/*
* Maximum segment size. Could be one segment with the maximum number
pr_debug("MTDSB: New superblock for device %d (\"%s\")\n",
mtd->index, mtd->name);
- ret = fill_super(sb, data, flags & MS_SILENT ? 1 : 0);
+ ret = fill_super(sb, data, flags & SB_SILENT ? 1 : 0);
if (ret < 0) {
deactivate_locked_super(sb);
return ERR_PTR(ret);
}
/* go */
- sb->s_flags |= MS_ACTIVE;
+ sb->s_flags |= SB_ACTIVE;
return dget(sb->s_root);
/* new mountpoint for an already mounted superblock */
not_an_MTD_device:
#endif /* CONFIG_BLOCK */
- if (!(flags & MS_SILENT))
+ if (!(flags & SB_SILENT))
printk(KERN_NOTICE
"MTD: Attempt to mount non-MTD device \"%s\"\n",
dev_name);
return -EINVAL;
bond_opt_initval(&newval,
- nla_get_be64(data[IFLA_BOND_AD_ACTOR_SYSTEM]));
+ nla_get_u64(data[IFLA_BOND_AD_ACTOR_SYSTEM]));
err = __bond_opt_set(bond, BOND_OPT_AD_ACTOR_SYSTEM, &newval);
if (err)
return err;
/* Read A2 portion of the EEPROM */
if (length) {
start -= ETH_MODULE_SFF_8436_LEN;
- bnxt_read_sfp_module_eeprom_info(bp, I2C_DEV_ADDR_A2, 1, start,
- length, data);
+ rc = bnxt_read_sfp_module_eeprom_info(bp, I2C_DEV_ADDR_A2, 1,
+ start, length, data);
}
return rc;
}
/* Offload checksum calculation to HW */
if (skb->ip_summed == CHECKSUM_PARTIAL) {
- hdr->csum_l3 = 1; /* Enable IP csum calculation */
hdr->l3_offset = skb_network_offset(skb);
hdr->l4_offset = skb_transport_offset(skb);
rar_num = E1000_RAR_ENTRIES;
- /* Zero out the other 15 receive addresses. */
- e_dbg("Clearing RAR[1-15]\n");
+ /* Zero out the following 14 receive addresses. RAR[15] is for
+ * manageability
+ */
+ e_dbg("Clearing RAR[1-14]\n");
for (i = 1; i < rar_num; i++) {
E1000_WRITE_REG_ARRAY(hw, RA, (i << 1), 0);
E1000_WRITE_FLUSH();
#define NVM_SIZE_MULTIPLIER 4096 /*multiplier for NVMS field */
#define E1000_FLASH_BASE_ADDR 0xE000 /*offset of NVM access regs */
#define E1000_CTRL_EXT_NVMVS 0x3 /*NVM valid sector */
-#define E1000_TARC0_CB_MULTIQ_3_REQ (1 << 28 | 1 << 29)
+#define E1000_TARC0_CB_MULTIQ_3_REQ 0x30000000
+#define E1000_TARC0_CB_MULTIQ_2_REQ 0x20000000
#define PCIE_ICH8_SNOOP_ALL PCIE_NO_SNOOP_ALL
#define E1000_ICH_RAR_ENTRIES 7
ew32(IOSFPC, reg_val);
reg_val = er32(TARC(0));
- /* SPT and KBL Si errata workaround to avoid Tx hang */
- reg_val &= ~BIT(28);
- reg_val |= BIT(29);
+ /* SPT and KBL Si errata workaround to avoid Tx hang.
+ * Dropping the number of outstanding requests from
+ * 3 to 2 in order to avoid a buffer overrun.
+ */
+ reg_val &= ~E1000_TARC0_CB_MULTIQ_3_REQ;
+ reg_val |= E1000_TARC0_CB_MULTIQ_2_REQ;
ew32(TARC(0), reg_val);
}
}
dev_err(&pf->pdev->dev,
"Failed to add cloud filter, err %s\n",
i40e_stat_str(&pf->hw, err));
- err = i40e_aq_rc_to_posix(err, pf->hw.aq.asq_last_status);
goto err;
}
}
return i40e_vc_send_msg_to_vf(vf, VIRTCHNL_OP_REQUEST_QUEUES, 0,
- (u8 *)vfres, sizeof(vfres));
+ (u8 *)vfres, sizeof(*vfres));
}
/**
MVPP22_CTRL4_QSGMII_BYPASS_ACTIVE;
val &= ~MVPP22_CTRL4_EXT_PIN_GMII_SEL;
writel(val, port->base + MVPP22_GMAC_CTRL_4_REG);
-
- val = readl(port->base + MVPP2_GMAC_CTRL_2_REG);
- val |= MVPP2_GMAC_DISABLE_PADDING;
- val &= ~MVPP2_GMAC_FLOW_CTRL_MASK;
- writel(val, port->base + MVPP2_GMAC_CTRL_2_REG);
} else if (phy_interface_mode_is_rgmii(port->phy_interface)) {
val = readl(port->base + MVPP22_GMAC_CTRL_4_REG);
val |= MVPP22_CTRL4_EXT_PIN_GMII_SEL |
MVPP22_CTRL4_QSGMII_BYPASS_ACTIVE;
val &= ~MVPP22_CTRL4_DP_CLK_SEL;
writel(val, port->base + MVPP22_GMAC_CTRL_4_REG);
-
- val = readl(port->base + MVPP2_GMAC_CTRL_2_REG);
- val &= ~MVPP2_GMAC_DISABLE_PADDING;
- writel(val, port->base + MVPP2_GMAC_CTRL_2_REG);
}
/* The port is connected to a copper PHY */
sizeof(*txq_pcpu->buffs),
GFP_KERNEL);
if (!txq_pcpu->buffs)
- goto cleanup;
+ return -ENOMEM;
txq_pcpu->count = 0;
txq_pcpu->reserved_num = 0;
&txq_pcpu->tso_headers_dma,
GFP_KERNEL);
if (!txq_pcpu->tso_headers)
- goto cleanup;
+ return -ENOMEM;
}
return 0;
-cleanup:
- for_each_present_cpu(cpu) {
- txq_pcpu = per_cpu_ptr(txq->pcpu, cpu);
- kfree(txq_pcpu->buffs);
-
- dma_free_coherent(port->dev->dev.parent,
- txq_pcpu->size * TSO_HEADER_SIZE,
- txq_pcpu->tso_headers,
- txq_pcpu->tso_headers_dma);
- }
-
- dma_free_coherent(port->dev->dev.parent,
- txq->size * MVPP2_DESC_ALIGNED_SIZE,
- txq->descs, txq->descs_dma);
-
- return -ENOMEM;
}
/* Free allocated TXQ resources */
else if (!IS_ALIGNED(ring->tx_pending, 32))
new_tx_pending = ALIGN(ring->tx_pending, 32);
+ /* The Tx ring size cannot be smaller than the minimum number of
+ * descriptors needed for TSO.
+ */
+ if (new_tx_pending < MVPP2_MAX_SKB_DESCS)
+ new_tx_pending = ALIGN(MVPP2_MAX_SKB_DESCS, 32);
+
if (ring->rx_pending != new_rx_pending) {
netdev_info(dev, "illegal Rx ring size value %d, round to %d\n",
ring->rx_pending, new_rx_pending);
for_each_available_child_of_node(dn, port_node) {
err = mvpp2_port_probe(pdev, port_node, priv, i);
if (err < 0)
- goto err_mg_clk;
+ goto err_port_probe;
i++;
}
priv->stats_queue = create_singlethread_workqueue(priv->queue_name);
if (!priv->stats_queue) {
err = -ENOMEM;
- goto err_mg_clk;
+ goto err_port_probe;
}
platform_set_drvdata(pdev, priv);
return 0;
+err_port_probe:
+ i = 0;
+ for_each_available_child_of_node(dn, port_node) {
+ if (priv->port_list[i])
+ mvpp2_port_remove(priv->port_list[i]);
+ i++;
+ }
err_mg_clk:
clk_disable_unprepare(priv->axi_clk);
if (priv->hw_version == MVPP22)
mlxsw_sp_ipip_entry_ol_down_event(mlxsw_sp, ipip_entry);
}
-static void mlxsw_sp_nexthop_rif_update(struct mlxsw_sp *mlxsw_sp,
- struct mlxsw_sp_rif *rif);
+static void mlxsw_sp_nexthop_rif_migrate(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_rif *old_rif,
+ struct mlxsw_sp_rif *new_rif);
static int
mlxsw_sp_ipip_entry_ol_lb_update(struct mlxsw_sp *mlxsw_sp,
struct mlxsw_sp_ipip_entry *ipip_entry,
return PTR_ERR(new_lb_rif);
ipip_entry->ol_lb = new_lb_rif;
- if (keep_encap) {
- list_splice_init(&old_lb_rif->common.nexthop_list,
- &new_lb_rif->common.nexthop_list);
- mlxsw_sp_nexthop_rif_update(mlxsw_sp, &new_lb_rif->common);
- }
+ if (keep_encap)
+ mlxsw_sp_nexthop_rif_migrate(mlxsw_sp, &old_lb_rif->common,
+ &new_lb_rif->common);
mlxsw_sp_rif_destroy(&old_lb_rif->common);
return 0;
}
+static void mlxsw_sp_nexthop_rif_update(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_rif *rif);
+
/**
* Update the offload related to an IPIP entry. This always updates decap, and
* in addition to that it also:
{
struct mlxsw_sp_ipip_entry *ipip_entry =
mlxsw_sp_ipip_entry_find_by_ol_dev(mlxsw_sp, ol_dev);
+ enum mlxsw_sp_l3proto ul_proto;
+ union mlxsw_sp_l3addr saddr;
+ u32 ul_tb_id;
if (!ipip_entry)
return 0;
+
+ /* For flat configuration cases, moving overlay to a different VRF might
+ * cause local address conflict, and the conflicting tunnels need to be
+ * demoted.
+ */
+ ul_tb_id = mlxsw_sp_ipip_dev_ul_tb_id(ol_dev);
+ ul_proto = mlxsw_sp->router->ipip_ops_arr[ipip_entry->ipipt]->ul_proto;
+ saddr = mlxsw_sp_ipip_netdev_saddr(ul_proto, ol_dev);
+ if (mlxsw_sp_ipip_demote_tunnel_by_saddr(mlxsw_sp, ul_proto,
+ saddr, ul_tb_id,
+ ipip_entry)) {
+ mlxsw_sp_ipip_entry_demote_tunnel(mlxsw_sp, ipip_entry);
+ return 0;
+ }
+
return __mlxsw_sp_ipip_entry_update_tunnel(mlxsw_sp, ipip_entry,
true, false, false, extack);
}
return ul_dev ? (ul_dev->flags & IFF_UP) : true;
}
-static int mlxsw_sp_nexthop_ipip_init(struct mlxsw_sp *mlxsw_sp,
- struct mlxsw_sp_nexthop *nh,
- struct net_device *ol_dev)
+static void mlxsw_sp_nexthop_ipip_init(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_nexthop *nh,
+ struct mlxsw_sp_ipip_entry *ipip_entry)
{
bool removing;
if (!nh->nh_grp->gateway || nh->ipip_entry)
- return 0;
-
- nh->ipip_entry = mlxsw_sp_ipip_entry_find_by_ol_dev(mlxsw_sp, ol_dev);
- if (!nh->ipip_entry)
- return -ENOENT;
+ return;
- removing = !mlxsw_sp_ipip_netdev_ul_up(ol_dev);
+ nh->ipip_entry = ipip_entry;
+ removing = !mlxsw_sp_ipip_netdev_ul_up(ipip_entry->ol_dev);
__mlxsw_sp_nexthop_neigh_update(nh, removing);
- return 0;
+ mlxsw_sp_nexthop_rif_init(nh, &ipip_entry->ol_lb->common);
}
static void mlxsw_sp_nexthop_ipip_fini(struct mlxsw_sp *mlxsw_sp,
struct mlxsw_sp_nexthop *nh,
struct fib_nh *fib_nh)
{
- struct mlxsw_sp_router *router = mlxsw_sp->router;
+ const struct mlxsw_sp_ipip_ops *ipip_ops;
struct net_device *dev = fib_nh->nh_dev;
- enum mlxsw_sp_ipip_type ipipt;
+ struct mlxsw_sp_ipip_entry *ipip_entry;
struct mlxsw_sp_rif *rif;
int err;
- if (mlxsw_sp_nexthop4_ipip_type(mlxsw_sp, fib_nh, &ipipt) &&
- router->ipip_ops_arr[ipipt]->can_offload(mlxsw_sp, dev,
- MLXSW_SP_L3_PROTO_IPV4)) {
- nh->type = MLXSW_SP_NEXTHOP_TYPE_IPIP;
- err = mlxsw_sp_nexthop_ipip_init(mlxsw_sp, nh, dev);
- if (err)
- return err;
- mlxsw_sp_nexthop_rif_init(nh, &nh->ipip_entry->ol_lb->common);
- return 0;
+ ipip_entry = mlxsw_sp_ipip_entry_find_by_ol_dev(mlxsw_sp, dev);
+ if (ipip_entry) {
+ ipip_ops = mlxsw_sp->router->ipip_ops_arr[ipip_entry->ipipt];
+ if (ipip_ops->can_offload(mlxsw_sp, dev,
+ MLXSW_SP_L3_PROTO_IPV4)) {
+ nh->type = MLXSW_SP_NEXTHOP_TYPE_IPIP;
+ mlxsw_sp_nexthop_ipip_init(mlxsw_sp, nh, ipip_entry);
+ return 0;
+ }
}
nh->type = MLXSW_SP_NEXTHOP_TYPE_ETH;
}
}
+static void mlxsw_sp_nexthop_rif_migrate(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_rif *old_rif,
+ struct mlxsw_sp_rif *new_rif)
+{
+ struct mlxsw_sp_nexthop *nh;
+
+ list_splice_init(&old_rif->nexthop_list, &new_rif->nexthop_list);
+ list_for_each_entry(nh, &new_rif->nexthop_list, rif_list_node)
+ nh->rif = new_rif;
+ mlxsw_sp_nexthop_rif_update(mlxsw_sp, new_rif);
+}
+
static void mlxsw_sp_nexthop_rif_gone_sync(struct mlxsw_sp *mlxsw_sp,
struct mlxsw_sp_rif *rif)
{
case RTN_LOCAL:
ipip_entry = mlxsw_sp_ipip_entry_find_by_decap(mlxsw_sp, dev,
MLXSW_SP_L3_PROTO_IPV4, dip);
- if (ipip_entry) {
+ if (ipip_entry && ipip_entry->ol_dev->flags & IFF_UP) {
fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_IPIP_DECAP;
return mlxsw_sp_fib_entry_decap_init(mlxsw_sp,
fib_entry,
struct mlxsw_sp_nexthop *nh,
const struct rt6_info *rt)
{
- struct mlxsw_sp_router *router = mlxsw_sp->router;
+ const struct mlxsw_sp_ipip_ops *ipip_ops;
+ struct mlxsw_sp_ipip_entry *ipip_entry;
struct net_device *dev = rt->dst.dev;
- enum mlxsw_sp_ipip_type ipipt;
struct mlxsw_sp_rif *rif;
int err;
- if (mlxsw_sp_nexthop6_ipip_type(mlxsw_sp, rt, &ipipt) &&
- router->ipip_ops_arr[ipipt]->can_offload(mlxsw_sp, dev,
- MLXSW_SP_L3_PROTO_IPV6)) {
- nh->type = MLXSW_SP_NEXTHOP_TYPE_IPIP;
- err = mlxsw_sp_nexthop_ipip_init(mlxsw_sp, nh, dev);
- if (err)
- return err;
- mlxsw_sp_nexthop_rif_init(nh, &nh->ipip_entry->ol_lb->common);
- return 0;
+ ipip_entry = mlxsw_sp_ipip_entry_find_by_ol_dev(mlxsw_sp, dev);
+ if (ipip_entry) {
+ ipip_ops = mlxsw_sp->router->ipip_ops_arr[ipip_entry->ipipt];
+ if (ipip_ops->can_offload(mlxsw_sp, dev,
+ MLXSW_SP_L3_PROTO_IPV6)) {
+ nh->type = MLXSW_SP_NEXTHOP_TYPE_IPIP;
+ mlxsw_sp_nexthop_ipip_init(mlxsw_sp, nh, ipip_entry);
+ return 0;
+ }
}
nh->type = MLXSW_SP_NEXTHOP_TYPE_ETH;
tx_skb->dma_len,
DMA_TO_DEVICE);
else
- pci_unmap_page(np->pci_dev, tx_skb->dma,
+ dma_unmap_page(&np->pci_dev->dev, tx_skb->dma,
tx_skb->dma_len,
- PCI_DMA_TODEVICE);
+ DMA_TO_DEVICE);
tx_skb->dma = 0;
}
}
/*
* dwmac-stm32.c - DWMAC Specific Glue layer for STM32 MCU
*
- * Copyright (C) Alexandre Torgue 2015
- * Author: Alexandre Torgue <alexandre.torgue@gmail.com>
+ * Copyright (C) STMicroelectronics SA 2017
+ * Author: Alexandre Torgue <alexandre.torgue@st.com> for STMicroelectronics.
* License terms: GNU General Public License (GPL), version 2
*
*/
else
name = "Rhine III";
- netdev_info(dev, "VIA %s at 0x%lx, %pM, IRQ %d\n",
- name, (long)ioaddr, dev->dev_addr, rp->irq);
+ netdev_info(dev, "VIA %s at %p, %pM, IRQ %d\n",
+ name, ioaddr, dev->dev_addr, rp->irq);
dev_set_drvdata(hwdev, dev);
config XILINX_LL_TEMAC
tristate "Xilinx LL TEMAC (LocalLink Tri-mode Ethernet MAC) driver"
depends on (PPC || MICROBLAZE)
+ depends on !64BIT || BROKEN
select PHYLIB
---help---
This driver supports the Xilinx 10/100/1000 LocalLink TEMAC
* link takes priority and the other port is completely locked out.
*/
#include <linux/phy.h>
+#include <linux/marvell_phy.h>
enum {
MV_PCS_BASE_T = 0x0000,
static struct phy_driver mv3310_drivers[] = {
{
.phy_id = 0x002b09aa,
- .phy_id_mask = 0xffffffff,
+ .phy_id_mask = MARVELL_PHY_ID_MASK,
.name = "mv88x3310",
.features = SUPPORTED_10baseT_Full |
SUPPORTED_100baseT_Full |
module_phy_driver(mv3310_drivers);
static struct mdio_device_id __maybe_unused mv3310_tbl[] = {
- { 0x002b09aa, 0xffffffff },
+ { 0x002b09aa, MARVELL_PHY_ID_MASK },
{ },
};
MODULE_DEVICE_TABLE(mdio, mv3310_tbl);
if (ring->ring->is_tx) {
dir = DMA_TO_DEVICE;
order = 0;
- size = tbnet_frame_size(tf);
+ size = TBNET_FRAME_SIZE;
} else {
dir = DMA_FROM_DEVICE;
order = TBNET_RX_PAGE_ORDER;
static struct tbnet_frame *tbnet_get_tx_buffer(struct tbnet *net)
{
struct tbnet_ring *ring = &net->tx_ring;
+ struct device *dma_dev = tb_ring_dma_device(ring->ring);
struct tbnet_frame *tf;
unsigned int index;
tf = &ring->frames[index];
tf->frame.size = 0;
- tf->frame.buffer_phy = 0;
+
+ dma_sync_single_for_cpu(dma_dev, tf->frame.buffer_phy,
+ tbnet_frame_size(tf), DMA_TO_DEVICE);
return tf;
}
bool canceled)
{
struct tbnet_frame *tf = container_of(frame, typeof(*tf), frame);
- struct device *dma_dev = tb_ring_dma_device(ring);
struct tbnet *net = netdev_priv(tf->dev);
- dma_unmap_page(dma_dev, tf->frame.buffer_phy, tbnet_frame_size(tf),
- DMA_TO_DEVICE);
- tf->frame.buffer_phy = 0;
-
/* Return buffer to the ring */
net->tx_ring.prod++;
static int tbnet_alloc_tx_buffers(struct tbnet *net)
{
struct tbnet_ring *ring = &net->tx_ring;
+ struct device *dma_dev = tb_ring_dma_device(ring->ring);
unsigned int i;
for (i = 0; i < TBNET_RING_SIZE; i++) {
struct tbnet_frame *tf = &ring->frames[i];
+ dma_addr_t dma_addr;
tf->page = alloc_page(GFP_KERNEL);
if (!tf->page) {
return -ENOMEM;
}
+ dma_addr = dma_map_page(dma_dev, tf->page, 0, TBNET_FRAME_SIZE,
+ DMA_TO_DEVICE);
+ if (dma_mapping_error(dma_dev, dma_addr)) {
+ __free_page(tf->page);
+ tf->page = NULL;
+ tbnet_free_buffers(ring);
+ return -ENOMEM;
+ }
+
tf->dev = net->dev;
+ tf->frame.buffer_phy = dma_addr;
tf->frame.callback = tbnet_tx_callback;
tf->frame.sof = TBIP_PDF_FRAME_START;
tf->frame.eof = TBIP_PDF_FRAME_END;
return 0;
}
-static bool tbnet_xmit_map(struct device *dma_dev, struct tbnet_frame *tf)
-{
- dma_addr_t dma_addr;
-
- dma_addr = dma_map_page(dma_dev, tf->page, 0, tbnet_frame_size(tf),
- DMA_TO_DEVICE);
- if (dma_mapping_error(dma_dev, dma_addr))
- return false;
-
- tf->frame.buffer_phy = dma_addr;
- return true;
-}
-
static bool tbnet_xmit_csum_and_map(struct tbnet *net, struct sk_buff *skb,
struct tbnet_frame **frames, u32 frame_count)
{
if (skb->ip_summed != CHECKSUM_PARTIAL) {
/* No need to calculate checksum so we just update the
- * total frame count and map the frames for DMA.
+ * total frame count and sync the frames for DMA.
*/
for (i = 0; i < frame_count; i++) {
hdr = page_address(frames[i]->page);
hdr->frame_count = cpu_to_le32(frame_count);
- if (!tbnet_xmit_map(dma_dev, frames[i]))
- goto err_unmap;
+ dma_sync_single_for_device(dma_dev,
+ frames[i]->frame.buffer_phy,
+ tbnet_frame_size(frames[i]), DMA_TO_DEVICE);
}
return true;
*tucso = csum_fold(wsum);
/* Checksum is finally calculated and we don't touch the memory
- * anymore, so DMA map the frames now.
+ * anymore, so DMA sync the frames now.
*/
for (i = 0; i < frame_count; i++) {
- if (!tbnet_xmit_map(dma_dev, frames[i]))
- goto err_unmap;
+ dma_sync_single_for_device(dma_dev, frames[i]->frame.buffer_phy,
+ tbnet_frame_size(frames[i]), DMA_TO_DEVICE);
}
return true;
-
-err_unmap:
- while (i--)
- dma_unmap_page(dma_dev, frames[i]->frame.buffer_phy,
- tbnet_frame_size(frames[i]), DMA_TO_DEVICE);
-
- return false;
}
static void *tbnet_kmap_frag(struct sk_buff *skb, unsigned int frag_num,
static int __vxlan_fdb_delete(struct vxlan_dev *vxlan,
const unsigned char *addr, union vxlan_addr ip,
- __be16 port, __be32 src_vni, u32 vni, u32 ifindex,
- u16 vid)
+ __be16 port, __be32 src_vni, __be32 vni,
+ u32 ifindex, u16 vid)
{
struct vxlan_fdb *f;
struct vxlan_rdst *rd = NULL;
break;
}
- data = kmalloc(xc.len, GFP_KERNEL);
- if (!data) {
- ret = -ENOMEM;
+ data = memdup_user(xc.data, xc.len);
+ if (IS_ERR(data)) {
+ ret = PTR_ERR(data);
break;
}
-
- if(copy_from_user(data, xc.data, xc.len))
- {
- kfree(data);
- ret = -ENOMEM;
- break;
- }
printk("%s: Starting load of data Len: %d at 0x%p == 0x%p\n", dev->name, xc.len, xc.data, data);
if (!avp->assoc)
return false;
- skb = ieee80211_nullfunc_get(sc->hw, vif);
+ skb = ieee80211_nullfunc_get(sc->hw, vif, false);
if (!skb)
return false;
priv->bss_loss_state++;
- skb = ieee80211_nullfunc_get(priv->hw, priv->vif);
+ skb = ieee80211_nullfunc_get(priv->hw, priv->vif, false);
WARN_ON(!skb);
if (skb)
cw1200_tx(priv->hw, NULL, skb);
.rate = 0xFF,
};
- frame.skb = ieee80211_nullfunc_get(priv->hw, priv->vif);
+ frame.skb = ieee80211_nullfunc_get(priv->hw, priv->vif, false);
if (!frame.skb)
return -ENOMEM;
size = sizeof(struct wl12xx_null_data_template);
ptr = NULL;
} else {
- skb = ieee80211_nullfunc_get(wl->hw, wl->vif);
+ skb = ieee80211_nullfunc_get(wl->hw, wl->vif, false);
if (!skb)
goto out;
size = skb->len;
ptr = NULL;
} else {
skb = ieee80211_nullfunc_get(wl->hw,
- wl12xx_wlvif_to_vif(wlvif));
+ wl12xx_wlvif_to_vif(wlvif),
+ false);
if (!skb)
goto out;
size = skb->len;
struct sk_buff *skb = NULL;
int ret = -ENOMEM;
- skb = ieee80211_nullfunc_get(wl->hw, vif);
+ skb = ieee80211_nullfunc_get(wl->hw, vif, false);
if (!skb)
goto out;
/* IRQ name is queue name with "-tx" or "-rx" appended */
#define IRQ_NAME_SIZE (QUEUE_NAME_SIZE + 3)
+static DECLARE_WAIT_QUEUE_HEAD(module_unload_q);
+
struct netfront_stats {
u64 packets;
u64 bytes;
break;
case XenbusStateClosed:
+ wake_up_all(&module_unload_q);
if (dev->state == XenbusStateClosed)
break;
/* Missed the backend's CLOSING state -- fallthrough */
case XenbusStateClosing:
+ wake_up_all(&module_unload_q);
xenbus_frontend_closed(dev);
break;
}
dev_dbg(&dev->dev, "%s\n", dev->nodename);
+ if (xenbus_read_driver_state(dev->otherend) != XenbusStateClosed) {
+ xenbus_switch_state(dev, XenbusStateClosing);
+ wait_event(module_unload_q,
+ xenbus_read_driver_state(dev->otherend) ==
+ XenbusStateClosing);
+
+ xenbus_switch_state(dev, XenbusStateClosed);
+ wait_event(module_unload_q,
+ xenbus_read_driver_state(dev->otherend) ==
+ XenbusStateClosed ||
+ xenbus_read_driver_state(dev->otherend) ==
+ XenbusStateUnknown);
+ }
+
xennet_disconnect_backend(info);
unregister_netdev(info->netdev);
int srcu_idx, ret;
u8 data[16] = { 0, };
+ ns = nvme_get_ns_from_disk(bdev->bd_disk, &head, &srcu_idx);
+ if (unlikely(!ns))
+ return -EWOULDBLOCK;
+
put_unaligned_le64(key, &data[0]);
put_unaligned_le64(sa_key, &data[8]);
memset(&c, 0, sizeof(c));
c.common.opcode = op;
- c.common.nsid = cpu_to_le32(head->ns_id);
+ c.common.nsid = cpu_to_le32(ns->head->ns_id);
c.common.cdw10[0] = cpu_to_le32(cdw10);
- ns = nvme_get_ns_from_disk(bdev->bd_disk, &head, &srcu_idx);
- if (unlikely(!ns))
- ret = -EWOULDBLOCK;
- else
- ret = nvme_submit_sync_cmd(ns->queue, &c, data, 16);
+ ret = nvme_submit_sync_cmd(ns->queue, &c, data, 16);
nvme_put_ns_from_disk(head, srcu_idx);
return ret;
}
static void nvme_ns_remove(struct nvme_ns *ns)
{
- struct nvme_ns_head *head = ns->head;
-
if (test_and_set_bit(NVME_NS_REMOVING, &ns->flags))
return;
mutex_lock(&ns->ctrl->subsys->lock);
nvme_mpath_clear_current_path(ns);
- if (head)
- list_del_rcu(&ns->siblings);
+ list_del_rcu(&ns->siblings);
mutex_unlock(&ns->ctrl->subsys->lock);
mutex_lock(&ns->ctrl->namespaces_mutex);
list_del_init(&ns->list);
mutex_unlock(&ns->ctrl->namespaces_mutex);
- synchronize_srcu(&head->srcu);
+ synchronize_srcu(&ns->head->srcu);
nvme_put_ns(ns);
}
int nvmf_get_address(struct nvme_ctrl *ctrl, char *buf, int size);
bool nvmf_should_reconnect(struct nvme_ctrl *ctrl);
+static inline blk_status_t nvmf_check_init_req(struct nvme_ctrl *ctrl,
+ struct request *rq)
+{
+ struct nvme_command *cmd = nvme_req(rq)->cmd;
+
+ /*
+ * We cannot accept any other command until the connect command has
+ * completed, so only allow connect to pass.
+ */
+ if (!blk_rq_is_passthrough(rq) ||
+ cmd->common.opcode != nvme_fabrics_command ||
+ cmd->fabrics.fctype != nvme_fabrics_type_connect) {
+ /*
+ * Reconnecting state means transport disruption, which can take
+ * a long time and even might fail permanently, fail fast to
+ * give upper layers a chance to failover.
+ * Deleting state means that the ctrl will never accept commands
+ * again, fail it permanently.
+ */
+ if (ctrl->state == NVME_CTRL_RECONNECTING ||
+ ctrl->state == NVME_CTRL_DELETING) {
+ nvme_req(rq)->status = NVME_SC_ABORT_REQ;
+ return BLK_STS_IOERR;
+ }
+ return BLK_STS_RESOURCE; /* try again later */
+ }
+
+ return BLK_STS_OK;
+}
+
#endif /* _NVME_FABRICS_H */
enum nvme_fc_queue_flags {
- NVME_FC_Q_CONNECTED = (1 << 0),
+ NVME_FC_Q_CONNECTED = 0,
+ NVME_FC_Q_LIVE,
};
#define NVMEFC_QUEUE_DELAY 3 /* ms units */
if (!test_and_clear_bit(NVME_FC_Q_CONNECTED, &queue->flags))
return;
+ clear_bit(NVME_FC_Q_LIVE, &queue->flags);
/*
* Current implementation never disconnects a single queue.
* It always terminates a whole association. So there is never
*/
queue->connection_id = 0;
- clear_bit(NVME_FC_Q_CONNECTED, &queue->flags);
}
static void
ret = nvmf_connect_io_queue(&ctrl->ctrl, i);
if (ret)
break;
+
+ set_bit(NVME_FC_Q_LIVE, &ctrl->queues[i].flags);
}
return ret;
return BLK_STS_RESOURCE;
}
+static inline blk_status_t nvme_fc_is_ready(struct nvme_fc_queue *queue,
+ struct request *rq)
+{
+ if (unlikely(!test_bit(NVME_FC_Q_LIVE, &queue->flags)))
+ return nvmf_check_init_req(&queue->ctrl->ctrl, rq);
+ return BLK_STS_OK;
+}
+
static blk_status_t
nvme_fc_queue_rq(struct blk_mq_hw_ctx *hctx,
const struct blk_mq_queue_data *bd)
u32 data_len;
blk_status_t ret;
+ ret = nvme_fc_is_ready(queue, rq);
+ if (unlikely(ret))
+ return ret;
+
ret = nvme_setup_cmd(ns, rq, sqe);
if (ret)
return ret;
if (ret)
goto out_disconnect_admin_queue;
+ set_bit(NVME_FC_Q_LIVE, &ctrl->queues[0].flags);
+
/*
* Check controller capabilities
*
bio->bi_opf |= REQ_NVME_MPATH;
ret = direct_make_request(bio);
} else if (!list_empty_careful(&head->list)) {
- dev_warn_ratelimited(dev, "no path available - requeing I/O\n");
+ dev_warn_ratelimited(dev, "no path available - requeuing I/O\n");
spin_lock_irq(&head->requeue_lock);
bio_list_add(&head->requeue_list, bio);
* NVME_QUIRK_DELAY_BEFORE_CHK_RDY quirk enabled. The value (in ms) was
* found empirically.
*/
-#define NVME_QUIRK_DELAY_AMOUNT 2000
+#define NVME_QUIRK_DELAY_AMOUNT 2300
enum nvme_ctrl_state {
NVME_CTRL_NEW,
dev->nr_host_mem_descs * sizeof(*dev->host_mem_descs),
dev->host_mem_descs, dev->host_mem_descs_dma);
dev->host_mem_descs = NULL;
+ dev->nr_host_mem_descs = 0;
}
static int __nvme_alloc_host_mem(struct nvme_dev *dev, u64 preferred,
if (!bufs)
goto out_free_descs;
- for (size = 0; size < preferred; size += len) {
+ for (size = 0; size < preferred && i < max_entries; size += len) {
dma_addr_t dma_addr;
len = min_t(u64, chunk_size, preferred - size);
return -ENODEV;
}
-static unsigned long check_dell_samsung_bug(struct pci_dev *pdev)
+static unsigned long check_vendor_combination_bug(struct pci_dev *pdev)
{
if (pdev->vendor == 0x144d && pdev->device == 0xa802) {
/*
(dmi_match(DMI_PRODUCT_NAME, "XPS 15 9550") ||
dmi_match(DMI_PRODUCT_NAME, "Precision 5510")))
return NVME_QUIRK_NO_DEEPEST_PS;
+ } else if (pdev->vendor == 0x144d && pdev->device == 0xa804) {
+ /*
+ * Samsung SSD 960 EVO drops off the PCIe bus after system
+ * suspend on a Ryzen board, ASUS PRIME B350M-A.
+ */
+ if (dmi_match(DMI_BOARD_VENDOR, "ASUSTeK COMPUTER INC.") &&
+ dmi_match(DMI_BOARD_NAME, "PRIME B350M-A"))
+ return NVME_QUIRK_NO_APST;
}
return 0;
if (result)
goto unmap;
- quirks |= check_dell_samsung_bug(pdev);
+ quirks |= check_vendor_combination_bug(pdev);
result = nvme_init_ctrl(&dev->ctrl, &pdev->dev, &nvme_pci_ctrl_ops,
quirks);
.driver_data = NVME_QUIRK_IDENTIFY_CNS, },
{ PCI_DEVICE(0x1c58, 0x0003), /* HGST adapter */
.driver_data = NVME_QUIRK_DELAY_BEFORE_CHK_RDY, },
+ { PCI_DEVICE(0x1c58, 0x0023), /* WDC SN200 adapter */
+ .driver_data = NVME_QUIRK_DELAY_BEFORE_CHK_RDY, },
{ PCI_DEVICE(0x1c5f, 0x0540), /* Memblaze Pblaze4 adapter */
.driver_data = NVME_QUIRK_DELAY_BEFORE_CHK_RDY, },
{ PCI_DEVICE(0x144d, 0xa821), /* Samsung PM1725 */
#include <linux/module.h>
#include <linux/init.h>
#include <linux/slab.h>
+#include <rdma/mr_pool.h>
#include <linux/err.h>
#include <linux/string.h>
#include <linux/atomic.h>
struct nvme_request req;
struct ib_mr *mr;
struct nvme_rdma_qe sqe;
+ union nvme_result result;
+ __le16 status;
+ refcount_t ref;
struct ib_sge sge[1 + NVME_RDMA_MAX_INLINE_SEGMENTS];
u32 num_sge;
int nents;
enum nvme_rdma_queue_flags {
NVME_RDMA_Q_ALLOCATED = 0,
NVME_RDMA_Q_LIVE = 1,
+ NVME_RDMA_Q_TR_READY = 2,
};
struct nvme_rdma_queue {
struct nvme_rdma_qe *rsp_ring;
- atomic_t sig_count;
int queue_size;
size_t cmnd_capsule_len;
struct nvme_rdma_ctrl *ctrl;
return ret;
}
-static int nvme_rdma_reinit_request(void *data, struct request *rq)
-{
- struct nvme_rdma_ctrl *ctrl = data;
- struct nvme_rdma_device *dev = ctrl->device;
- struct nvme_rdma_request *req = blk_mq_rq_to_pdu(rq);
- int ret = 0;
-
- if (WARN_ON_ONCE(!req->mr))
- return 0;
-
- ib_dereg_mr(req->mr);
-
- req->mr = ib_alloc_mr(dev->pd, IB_MR_TYPE_MEM_REG,
- ctrl->max_fr_pages);
- if (IS_ERR(req->mr)) {
- ret = PTR_ERR(req->mr);
- req->mr = NULL;
- goto out;
- }
-
- req->mr->need_inval = false;
-
-out:
- return ret;
-}
-
static void nvme_rdma_exit_request(struct blk_mq_tag_set *set,
struct request *rq, unsigned int hctx_idx)
{
struct nvme_rdma_queue *queue = &ctrl->queues[queue_idx];
struct nvme_rdma_device *dev = queue->device;
- if (req->mr)
- ib_dereg_mr(req->mr);
-
nvme_rdma_free_qe(dev->dev, &req->sqe, sizeof(struct nvme_command),
DMA_TO_DEVICE);
}
if (ret)
return ret;
- req->mr = ib_alloc_mr(dev->pd, IB_MR_TYPE_MEM_REG,
- ctrl->max_fr_pages);
- if (IS_ERR(req->mr)) {
- ret = PTR_ERR(req->mr);
- goto out_free_qe;
- }
-
req->queue = queue;
return 0;
-
-out_free_qe:
- nvme_rdma_free_qe(dev->dev, &req->sqe, sizeof(struct nvme_command),
- DMA_TO_DEVICE);
- return -ENOMEM;
}
static int nvme_rdma_init_hctx(struct blk_mq_hw_ctx *hctx, void *data,
static void nvme_rdma_destroy_queue_ib(struct nvme_rdma_queue *queue)
{
- struct nvme_rdma_device *dev = queue->device;
- struct ib_device *ibdev = dev->dev;
+ struct nvme_rdma_device *dev;
+ struct ib_device *ibdev;
- rdma_destroy_qp(queue->cm_id);
+ if (!test_and_clear_bit(NVME_RDMA_Q_TR_READY, &queue->flags))
+ return;
+
+ dev = queue->device;
+ ibdev = dev->dev;
+
+ ib_mr_pool_destroy(queue->qp, &queue->qp->rdma_mrs);
+
+ /*
+ * The cm_id object might have been destroyed during RDMA connection
+ * establishment error flow to avoid getting other cma events, thus
+ * the destruction of the QP shouldn't use rdma_cm API.
+ */
+ ib_destroy_qp(queue->qp);
ib_free_cq(queue->ib_cq);
nvme_rdma_free_ring(ibdev, queue->rsp_ring, queue->queue_size,
nvme_rdma_dev_put(dev);
}
+static int nvme_rdma_get_max_fr_pages(struct ib_device *ibdev)
+{
+ return min_t(u32, NVME_RDMA_MAX_SEGMENTS,
+ ibdev->attrs.max_fast_reg_page_list_len);
+}
+
static int nvme_rdma_create_queue_ib(struct nvme_rdma_queue *queue)
{
struct ib_device *ibdev;
goto out_destroy_qp;
}
+ ret = ib_mr_pool_init(queue->qp, &queue->qp->rdma_mrs,
+ queue->queue_size,
+ IB_MR_TYPE_MEM_REG,
+ nvme_rdma_get_max_fr_pages(ibdev));
+ if (ret) {
+ dev_err(queue->ctrl->ctrl.device,
+ "failed to initialize MR pool sized %d for QID %d\n",
+ queue->queue_size, idx);
+ goto out_destroy_ring;
+ }
+
+ set_bit(NVME_RDMA_Q_TR_READY, &queue->flags);
+
return 0;
+out_destroy_ring:
+ nvme_rdma_free_ring(ibdev, queue->rsp_ring, queue->queue_size,
+ sizeof(struct nvme_completion), DMA_FROM_DEVICE);
out_destroy_qp:
rdma_destroy_qp(queue->cm_id);
out_destroy_ib_cq:
queue->cmnd_capsule_len = sizeof(struct nvme_command);
queue->queue_size = queue_size;
- atomic_set(&queue->sig_count, 0);
queue->cm_id = rdma_create_id(&init_net, nvme_rdma_cm_handler, queue,
RDMA_PS_TCP, IB_QPT_RC);
out_destroy_cm_id:
rdma_destroy_id(queue->cm_id);
+ nvme_rdma_destroy_queue_ib(queue);
return ret;
}
ctrl->device = ctrl->queues[0].device;
- ctrl->max_fr_pages = min_t(u32, NVME_RDMA_MAX_SEGMENTS,
- ctrl->device->dev->attrs.max_fast_reg_page_list_len);
+ ctrl->max_fr_pages = nvme_rdma_get_max_fr_pages(ctrl->device->dev);
if (new) {
ctrl->ctrl.admin_tagset = nvme_rdma_alloc_tagset(&ctrl->ctrl, true);
error = PTR_ERR(ctrl->ctrl.admin_q);
goto out_free_tagset;
}
- } else {
- error = nvme_reinit_tagset(&ctrl->ctrl, ctrl->ctrl.admin_tagset);
- if (error)
- goto out_free_queue;
}
error = nvme_rdma_start_queue(ctrl, 0);
goto out_free_tag_set;
}
} else {
- ret = nvme_reinit_tagset(&ctrl->ctrl, ctrl->ctrl.tagset);
- if (ret)
- goto out_free_io_queues;
-
blk_mq_update_nr_hw_queues(&ctrl->tag_set,
ctrl->ctrl.queue_count - 1);
}
static void nvme_rdma_inv_rkey_done(struct ib_cq *cq, struct ib_wc *wc)
{
- if (unlikely(wc->status != IB_WC_SUCCESS))
+ struct nvme_rdma_request *req =
+ container_of(wc->wr_cqe, struct nvme_rdma_request, reg_cqe);
+ struct request *rq = blk_mq_rq_from_pdu(req);
+
+ if (unlikely(wc->status != IB_WC_SUCCESS)) {
nvme_rdma_wr_error(cq, wc, "LOCAL_INV");
+ return;
+ }
+
+ if (refcount_dec_and_test(&req->ref))
+ nvme_end_request(rq, req->status, req->result);
+
}
static int nvme_rdma_inv_rkey(struct nvme_rdma_queue *queue,
.opcode = IB_WR_LOCAL_INV,
.next = NULL,
.num_sge = 0,
- .send_flags = 0,
+ .send_flags = IB_SEND_SIGNALED,
.ex.invalidate_rkey = req->mr->rkey,
};
struct request *rq)
{
struct nvme_rdma_request *req = blk_mq_rq_to_pdu(rq);
- struct nvme_rdma_ctrl *ctrl = queue->ctrl;
struct nvme_rdma_device *dev = queue->device;
struct ib_device *ibdev = dev->dev;
- int res;
if (!blk_rq_bytes(rq))
return;
- if (req->mr->need_inval && test_bit(NVME_RDMA_Q_LIVE, &req->queue->flags)) {
- res = nvme_rdma_inv_rkey(queue, req);
- if (unlikely(res < 0)) {
- dev_err(ctrl->ctrl.device,
- "Queueing INV WR for rkey %#x failed (%d)\n",
- req->mr->rkey, res);
- nvme_rdma_error_recovery(queue->ctrl);
- }
+ if (req->mr) {
+ ib_mr_pool_put(queue->qp, &queue->qp->rdma_mrs, req->mr);
+ req->mr = NULL;
}
ib_dma_unmap_sg(ibdev, req->sg_table.sgl,
struct nvme_keyed_sgl_desc *sg = &c->common.dptr.ksgl;
int nr;
+ req->mr = ib_mr_pool_get(queue->qp, &queue->qp->rdma_mrs);
+ if (WARN_ON_ONCE(!req->mr))
+ return -EAGAIN;
+
/*
* Align the MR to a 4K page size to match the ctrl page size and
* the block virtual boundary.
*/
nr = ib_map_mr_sg(req->mr, req->sg_table.sgl, count, NULL, SZ_4K);
if (unlikely(nr < count)) {
+ ib_mr_pool_put(queue->qp, &queue->qp->rdma_mrs, req->mr);
+ req->mr = NULL;
if (nr < 0)
return nr;
return -EINVAL;
IB_ACCESS_REMOTE_READ |
IB_ACCESS_REMOTE_WRITE;
- req->mr->need_inval = true;
-
sg->addr = cpu_to_le64(req->mr->iova);
put_unaligned_le24(req->mr->length, sg->length);
put_unaligned_le32(req->mr->rkey, sg->key);
req->num_sge = 1;
req->inline_data = false;
- req->mr->need_inval = false;
+ refcount_set(&req->ref, 2); /* send and recv completions */
c->common.flags |= NVME_CMD_SGL_METABUF;
static void nvme_rdma_send_done(struct ib_cq *cq, struct ib_wc *wc)
{
- if (unlikely(wc->status != IB_WC_SUCCESS))
- nvme_rdma_wr_error(cq, wc, "SEND");
-}
+ struct nvme_rdma_qe *qe =
+ container_of(wc->wr_cqe, struct nvme_rdma_qe, cqe);
+ struct nvme_rdma_request *req =
+ container_of(qe, struct nvme_rdma_request, sqe);
+ struct request *rq = blk_mq_rq_from_pdu(req);
-/*
- * We want to signal completion at least every queue depth/2. This returns the
- * largest power of two that is not above half of (queue size + 1) to optimize
- * (avoid divisions).
- */
-static inline bool nvme_rdma_queue_sig_limit(struct nvme_rdma_queue *queue)
-{
- int limit = 1 << ilog2((queue->queue_size + 1) / 2);
+ if (unlikely(wc->status != IB_WC_SUCCESS)) {
+ nvme_rdma_wr_error(cq, wc, "SEND");
+ return;
+ }
- return (atomic_inc_return(&queue->sig_count) & (limit - 1)) == 0;
+ if (refcount_dec_and_test(&req->ref))
+ nvme_end_request(rq, req->status, req->result);
}
static int nvme_rdma_post_send(struct nvme_rdma_queue *queue,
struct nvme_rdma_qe *qe, struct ib_sge *sge, u32 num_sge,
- struct ib_send_wr *first, bool flush)
+ struct ib_send_wr *first)
{
struct ib_send_wr wr, *bad_wr;
int ret;
sge->length = sizeof(struct nvme_command),
sge->lkey = queue->device->pd->local_dma_lkey;
- qe->cqe.done = nvme_rdma_send_done;
-
wr.next = NULL;
wr.wr_cqe = &qe->cqe;
wr.sg_list = sge;
wr.num_sge = num_sge;
wr.opcode = IB_WR_SEND;
- wr.send_flags = 0;
-
- /*
- * Unsignalled send completions are another giant desaster in the
- * IB Verbs spec: If we don't regularly post signalled sends
- * the send queue will fill up and only a QP reset will rescue us.
- * Would have been way to obvious to handle this in hardware or
- * at least the RDMA stack..
- *
- * Always signal the flushes. The magic request used for the flush
- * sequencer is not allocated in our driver's tagset and it's
- * triggered to be freed by blk_cleanup_queue(). So we need to
- * always mark it as signaled to ensure that the "wr_cqe", which is
- * embedded in request's payload, is not freed when __ib_process_cq()
- * calls wr_cqe->done().
- */
- if (nvme_rdma_queue_sig_limit(queue) || flush)
- wr.send_flags |= IB_SEND_SIGNALED;
+ wr.send_flags = IB_SEND_SIGNALED;
if (first)
first->next = ≀
return queue->ctrl->tag_set.tags[queue_idx - 1];
}
+static void nvme_rdma_async_done(struct ib_cq *cq, struct ib_wc *wc)
+{
+ if (unlikely(wc->status != IB_WC_SUCCESS))
+ nvme_rdma_wr_error(cq, wc, "ASYNC");
+}
+
static void nvme_rdma_submit_async_event(struct nvme_ctrl *arg)
{
struct nvme_rdma_ctrl *ctrl = to_rdma_ctrl(arg);
cmd->common.flags |= NVME_CMD_SGL_METABUF;
nvme_rdma_set_sg_null(cmd);
+ sqe->cqe.done = nvme_rdma_async_done;
+
ib_dma_sync_single_for_device(dev, sqe->dma, sizeof(*cmd),
DMA_TO_DEVICE);
- ret = nvme_rdma_post_send(queue, sqe, &sge, 1, NULL, false);
+ ret = nvme_rdma_post_send(queue, sqe, &sge, 1, NULL);
WARN_ON_ONCE(ret);
}
}
req = blk_mq_rq_to_pdu(rq);
- if (rq->tag == tag)
- ret = 1;
+ req->status = cqe->status;
+ req->result = cqe->result;
- if ((wc->wc_flags & IB_WC_WITH_INVALIDATE) &&
- wc->ex.invalidate_rkey == req->mr->rkey)
- req->mr->need_inval = false;
+ if (wc->wc_flags & IB_WC_WITH_INVALIDATE) {
+ if (unlikely(wc->ex.invalidate_rkey != req->mr->rkey)) {
+ dev_err(queue->ctrl->ctrl.device,
+ "Bogus remote invalidation for rkey %#x\n",
+ req->mr->rkey);
+ nvme_rdma_error_recovery(queue->ctrl);
+ }
+ } else if (req->mr) {
+ ret = nvme_rdma_inv_rkey(queue, req);
+ if (unlikely(ret < 0)) {
+ dev_err(queue->ctrl->ctrl.device,
+ "Queueing INV WR for rkey %#x failed (%d)\n",
+ req->mr->rkey, ret);
+ nvme_rdma_error_recovery(queue->ctrl);
+ }
+ /* the local invalidation completion will end the request */
+ return 0;
+ }
+
+ if (refcount_dec_and_test(&req->ref)) {
+ if (rq->tag == tag)
+ ret = 1;
+ nvme_end_request(rq, req->status, req->result);
+ }
- nvme_end_request(rq, cqe->status, cqe->result);
return ret;
}
* We cannot accept any other command until the Connect command has completed.
*/
static inline blk_status_t
-nvme_rdma_queue_is_ready(struct nvme_rdma_queue *queue, struct request *rq)
-{
- if (unlikely(!test_bit(NVME_RDMA_Q_LIVE, &queue->flags))) {
- struct nvme_command *cmd = nvme_req(rq)->cmd;
-
- if (!blk_rq_is_passthrough(rq) ||
- cmd->common.opcode != nvme_fabrics_command ||
- cmd->fabrics.fctype != nvme_fabrics_type_connect) {
- /*
- * reconnecting state means transport disruption, which
- * can take a long time and even might fail permanently,
- * fail fast to give upper layers a chance to failover.
- * deleting state means that the ctrl will never accept
- * commands again, fail it permanently.
- */
- if (queue->ctrl->ctrl.state == NVME_CTRL_RECONNECTING ||
- queue->ctrl->ctrl.state == NVME_CTRL_DELETING) {
- nvme_req(rq)->status = NVME_SC_ABORT_REQ;
- return BLK_STS_IOERR;
- }
- return BLK_STS_RESOURCE; /* try again later */
- }
- }
-
- return 0;
+nvme_rdma_is_ready(struct nvme_rdma_queue *queue, struct request *rq)
+{
+ if (unlikely(!test_bit(NVME_RDMA_Q_LIVE, &queue->flags)))
+ return nvmf_check_init_req(&queue->ctrl->ctrl, rq);
+ return BLK_STS_OK;
}
static blk_status_t nvme_rdma_queue_rq(struct blk_mq_hw_ctx *hctx,
struct nvme_rdma_request *req = blk_mq_rq_to_pdu(rq);
struct nvme_rdma_qe *sqe = &req->sqe;
struct nvme_command *c = sqe->data;
- bool flush = false;
struct ib_device *dev;
blk_status_t ret;
int err;
WARN_ON_ONCE(rq->tag < 0);
- ret = nvme_rdma_queue_is_ready(queue, rq);
+ ret = nvme_rdma_is_ready(queue, rq);
if (unlikely(ret))
return ret;
goto err;
}
+ sqe->cqe.done = nvme_rdma_send_done;
+
ib_dma_sync_single_for_device(dev, sqe->dma,
sizeof(struct nvme_command), DMA_TO_DEVICE);
- if (req_op(rq) == REQ_OP_FLUSH)
- flush = true;
err = nvme_rdma_post_send(queue, sqe, req->sge, req->num_sge,
- req->mr->need_inval ? &req->reg_wr.wr : NULL, flush);
+ req->mr ? &req->reg_wr.wr : NULL);
if (unlikely(err)) {
nvme_rdma_unmap_data(queue, rq);
goto err;
.submit_async_event = nvme_rdma_submit_async_event,
.delete_ctrl = nvme_rdma_delete_ctrl,
.get_address = nvmf_get_address,
- .reinit_request = nvme_rdma_reinit_request,
};
static inline bool
tgtport->ops->fcp_req_release(&tgtport->fc_target_port, fcpreq);
+ /* release the queue lookup reference on the completed IO */
+ nvmet_fc_tgt_q_put(queue);
+
spin_lock_irqsave(&queue->qlock, flags);
deferfcp = list_first_entry_or_null(&queue->pending_cmd_list,
struct nvmet_fc_defer_fcp_req, req_list);
if (!deferfcp) {
list_add_tail(&fod->fcp_list, &fod->queue->fod_list);
spin_unlock_irqrestore(&queue->qlock, flags);
-
- /* Release reference taken at queue lookup and fod allocation */
- nvmet_fc_tgt_q_put(queue);
return;
}
tgtport->ops->fcp_req_release(&tgtport->fc_target_port,
deferfcp->fcp_req);
+ /* release the queue lookup reference */
+ nvmet_fc_tgt_q_put(queue);
+
kfree(deferfcp);
spin_lock_irqsave(&queue->qlock, flags);
return container_of(ctrl, struct nvme_loop_ctrl, ctrl);
}
+enum nvme_loop_queue_flags {
+ NVME_LOOP_Q_LIVE = 0,
+};
+
struct nvme_loop_queue {
struct nvmet_cq nvme_cq;
struct nvmet_sq nvme_sq;
struct nvme_loop_ctrl *ctrl;
+ unsigned long flags;
};
static struct nvmet_port *nvmet_loop_port;
return BLK_EH_HANDLED;
}
+static inline blk_status_t nvme_loop_is_ready(struct nvme_loop_queue *queue,
+ struct request *rq)
+{
+ if (unlikely(!test_bit(NVME_LOOP_Q_LIVE, &queue->flags)))
+ return nvmf_check_init_req(&queue->ctrl->ctrl, rq);
+ return BLK_STS_OK;
+}
+
static blk_status_t nvme_loop_queue_rq(struct blk_mq_hw_ctx *hctx,
const struct blk_mq_queue_data *bd)
{
struct nvme_loop_iod *iod = blk_mq_rq_to_pdu(req);
blk_status_t ret;
+ ret = nvme_loop_is_ready(queue, req);
+ if (unlikely(ret))
+ return ret;
+
ret = nvme_setup_cmd(ns, req, &iod->cmd);
if (ret)
return ret;
static void nvme_loop_destroy_admin_queue(struct nvme_loop_ctrl *ctrl)
{
+ clear_bit(NVME_LOOP_Q_LIVE, &ctrl->queues[0].flags);
nvmet_sq_destroy(&ctrl->queues[0].nvme_sq);
blk_cleanup_queue(ctrl->ctrl.admin_q);
blk_mq_free_tag_set(&ctrl->admin_tag_set);
{
int i;
- for (i = 1; i < ctrl->ctrl.queue_count; i++)
+ for (i = 1; i < ctrl->ctrl.queue_count; i++) {
+ clear_bit(NVME_LOOP_Q_LIVE, &ctrl->queues[i].flags);
nvmet_sq_destroy(&ctrl->queues[i].nvme_sq);
+ }
}
static int nvme_loop_init_io_queues(struct nvme_loop_ctrl *ctrl)
ret = nvmf_connect_io_queue(&ctrl->ctrl, i);
if (ret)
return ret;
+ set_bit(NVME_LOOP_Q_LIVE, &ctrl->queues[i].flags);
}
return 0;
if (error)
goto out_cleanup_queue;
+ set_bit(NVME_LOOP_Q_LIVE, &ctrl->queues[0].flags);
+
error = nvmf_reg_read64(&ctrl->ctrl, NVME_REG_CAP, &ctrl->ctrl.cap);
if (error) {
dev_err(ctrl->ctrl.device,
+// SPDX-License-Identifier: GPL-2.0
/*
* Author(s)......: Holger Smolinski <Holger.Smolinski@de.ibm.com>
* Horst Hummel <Horst.Hummel@de.ibm.com>
+// SPDX-License-Identifier: GPL-2.0
/*
* Author(s)......: Holger Smolinski <Holger.Smolinski@de.ibm.com>
* Horst Hummel <Horst.Hummel@de.ibm.com>
+// SPDX-License-Identifier: GPL-2.0
/*
* Author(s)......: Holger Smolinski <Holger.Smolinski@de.ibm.com>
* Based on.......: linux/drivers/s390/block/mdisk.c
+// SPDX-License-Identifier: GPL-2.0
/*
* Author(s)......: Holger Smolinski <Holger.Smolinski@de.ibm.com>
* Horst Hummel <Horst.Hummel@de.ibm.com>
+// SPDX-License-Identifier: GPL-2.0
/*
* Author(s)......: Holger Smolinski <Holger.Smolinski@de.ibm.com>
* Bugreports.to..: <Linux390@de.ibm.com>
+// SPDX-License-Identifier: GPL-2.0
/*
* dcssblk.c -- the S/390 block driver for dcss memory
*
+// SPDX-License-Identifier: GPL-2.0
/*
* Block driver for s390 storage class memory.
*
+// SPDX-License-Identifier: GPL-2.0
/*
* Xpram.c -- the S/390 expanded memory RAM-disk
*
+// SPDX-License-Identifier: GPL-2.0
/*
* IBM/3270 Driver - fullscreen driver.
*
+// SPDX-License-Identifier: GPL-2.0
/*
* HMC Drive DVD Module
*
+// SPDX-License-Identifier: GPL-2.0
/*
* Character device driver for reading z/VM *MONITOR service records.
*
+// SPDX-License-Identifier: GPL-2.0
/*
* Character device driver for writing z/VM *MONITOR service records.
*
+// SPDX-License-Identifier: GPL-2.0
/*
* IBM/3270 Driver - core functions.
*
+// SPDX-License-Identifier: GPL-2.0
/*
* Enable Asynchronous Notification via SCLP.
*
+// SPDX-License-Identifier: GPL-2.0
/*
* tape device discipline for 3480/3490 tapes.
*
+// SPDX-License-Identifier: GPL-2.0
/*
* tape device discipline for 3590 tapes.
*
+// SPDX-License-Identifier: GPL-2.0
/*
* Copyright IBM Corp. 2004
*
+// SPDX-License-Identifier: GPL-2.0
/*
* basic function of the tape device driver
*
+// SPDX-License-Identifier: GPL-2.0
/*
* IBM/3270 Driver - tty functions.
*
+// SPDX-License-Identifier: GPL-2.0
/*
* character device driver for reading z/VM system service records
*
+// SPDX-License-Identifier: GPL-2.0
/*
* Linux driver for System z and s390 unit record devices
* (z/VM virtual punch, reader, printer)
+// SPDX-License-Identifier: GPL-1.0+
/*
* zcore module to export memory content and register sets for creating system
* dumps on SCSI disks (zfcpdump). The "zcore/mem" debugfs file shows the same
*
* Copyright IBM Corp. 2003, 2008
* Author(s): Michael Holzheu
- * License: GPL
*/
#define KMSG_COMPONENT "zdump"
+// SPDX-License-Identifier: GPL-2.0
/*
* bus driver for ccwgroup
*
+// SPDX-License-Identifier: GPL-2.0
/*
* Copyright IBM Corp. 1999, 2010
* Author(s): Cornelia Huck (cornelia.huck@de.ibm.com)
+// SPDX-License-Identifier: GPL-2.0
/*
* S/390 common I/O routines -- channel subsystem call
*
+// SPDX-License-Identifier: GPL-2.0
/*
* Driver for s390 chsc subchannels
*
+// SPDX-License-Identifier: GPL-2.0
/*
* S/390 common I/O routines -- low level i/o calls
*
+// SPDX-License-Identifier: GPL-2.0+
/*
* Linux on zSeries Channel Measurement Facility support
*
* Cornelia Huck <cornelia.huck@de.ibm.com>
*
* original idea from Natarajan Krishnaswami <nkrishna@us.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
*/
#define KMSG_COMPONENT "cio"
+// SPDX-License-Identifier: GPL-2.0
/*
* driver for channel subsystem
*
*
* Author(s): Arnd Bergmann (arndb@de.ibm.com)
* Cornelia Huck (cornelia.huck@de.ibm.com)
- *
- * License: GPL
*/
#define KMSG_COMPONENT "cio"
+// SPDX-License-Identifier: GPL-1.0+
/*
* bus driver for ccw devices
*
* Author(s): Arnd Bergmann (arndb@de.ibm.com)
* Cornelia Huck (cornelia.huck@de.ibm.com)
* Martin Schwidefsky (schwidefsky@de.ibm.com)
- *
- * License: GPL
*/
#define KMSG_COMPONENT "cio"
+// SPDX-License-Identifier: GPL-2.0
/*
* finite state machine for device handling
*
+// SPDX-License-Identifier: GPL-1.0+
/*
* Copyright IBM Corp. 2002, 2009
*
* Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com)
* Cornelia Huck (cornelia.huck@de.ibm.com)
- *
- * License: GPL
*/
#include <linux/export.h>
#include <linux/init.h>
+// SPDX-License-Identifier: GPL-2.0
/*
* Driver for s390 eadm subchannels
*
+// SPDX-License-Identifier: GPL-2.0
/*
* Functions for registration of I/O interruption subclasses on s390.
*
+// SPDX-License-Identifier: GPL-2.0
/*
* Linux for s390 qdio support, buffer handling, qdio API and module support.
*
+// SPDX-License-Identifier: GPL-2.0
/*
* qdio queue initialization
*
+// SPDX-License-Identifier: GPL-2.0
/*
* Recognize and maintain s390 storage class memory.
*
+// SPDX-License-Identifier: GPL-2.0
/*
* VFIO based Physical Subchannel device driver
*
+// SPDX-License-Identifier: GPL-2.0+
/*
* Copyright IBM Corp. 2006, 2012
* Author(s): Cornelia Huck <cornelia.huck@de.ibm.com>
* Holger Dengler <hd@linux.vnet.ibm.com>
*
* Adjunct processor bus.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
*/
#define KMSG_COMPONENT "ap"
+// SPDX-License-Identifier: GPL-2.0+
/*
* Copyright IBM Corp. 2006, 2012
* Author(s): Cornelia Huck <cornelia.huck@de.ibm.com>
* Holger Dengler <hd@linux.vnet.ibm.com>
*
* Adjunct processor bus header file.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
*/
#ifndef _AP_BUS_H_
+// SPDX-License-Identifier: GPL-2.0
/*
* pkey device driver
*
* Copyright IBM Corp. 2017
* Author(s): Harald Freudenberger
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
- *
*/
#define KMSG_COMPONENT "pkey"
+// SPDX-License-Identifier: GPL-2.0+
/*
* zcrypt 2.1.0
*
* Major cleanup & driver split: Martin Schwidefsky <schwidefsky@de.ibm.com>
* Ralph Wuerthner <rwuerthn@de.ibm.com>
* MSGTYPE restruct: Holger Dengler <hd@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
*/
#include <linux/module.h>
weight += atomic_read(&zq->load);
pref_weight += atomic_read(&pref_zq->load);
if (weight == pref_weight)
- return &zq->queue->total_request_count >
- &pref_zq->queue->total_request_count;
+ return zq->queue->total_request_count >
+ pref_zq->queue->total_request_count;
return weight > pref_weight;
}
+// SPDX-License-Identifier: GPL-2.0+
/*
* zcrypt 2.1.0
*
* Major cleanup & driver split: Martin Schwidefsky <schwidefsky@de.ibm.com>
* Ralph Wuerthner <rwuerthn@de.ibm.com>
* MSGTYPE restruct: Holger Dengler <hd@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
*/
#ifndef _ZCRYPT_API_H_
+// SPDX-License-Identifier: GPL-2.0+
/*
* zcrypt 2.1.0
*
* Major cleanup & driver split: Martin Schwidefsky <schwidefsky@de.ibm.com>
* Ralph Wuerthner <rwuerthn@de.ibm.com>
* MSGTYPE restruct: Holger Dengler <hd@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
*/
#include <linux/module.h>
+// SPDX-License-Identifier: GPL-2.0+
/*
* zcrypt 2.1.0
*
*
* Hotplug & misc device support: Jochen Roehrig (roehrig@de.ibm.com)
* Major cleanup & driver split: Martin Schwidefsky <schwidefsky@de.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
*/
#ifndef _ZCRYPT_CCA_KEY_H_
+// SPDX-License-Identifier: GPL-2.0+
/*
* zcrypt 2.1.0
*
* Major cleanup & driver split: Martin Schwidefsky <schwidefsky@de.ibm.com>
* Ralph Wuerthner <rwuerthn@de.ibm.com>
* MSGTYPE restruct: Holger Dengler <hd@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
*/
#include <linux/module.h>
+// SPDX-License-Identifier: GPL-2.0+
/*
* zcrypt 2.1.0
*
*
* Hotplug & misc device support: Jochen Roehrig (roehrig@de.ibm.com)
* Major cleanup & driver split: Martin Schwidefsky <schwidefsky@de.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
*/
#ifndef _ZCRYPT_CEX2A_H_
+// SPDX-License-Identifier: GPL-2.0
/*
* Copyright IBM Corp. 2012
* Author(s): Holger Dengler <hd@linux.vnet.ibm.com>
+// SPDX-License-Identifier: GPL-2.0+
/*
* zcrypt 2.1.0
*
*
* Hotplug & misc device support: Jochen Roehrig (roehrig@de.ibm.com)
* Major cleanup & driver split: Martin Schwidefsky <schwidefsky@de.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
*/
#ifndef _ZCRYPT_ERROR_H_
+// SPDX-License-Identifier: GPL-2.0+
/*
* zcrypt 2.1.0
*
* Major cleanup & driver split: Martin Schwidefsky <schwidefsky@de.ibm.com>
* Ralph Wuerthner <rwuerthn@de.ibm.com>
* MSGTYPE restruct: Holger Dengler <hd@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
*/
#define KMSG_COMPONENT "zcrypt"
+// SPDX-License-Identifier: GPL-2.0+
/*
* zcrypt 2.1.0
*
* Hotplug & misc device support: Jochen Roehrig (roehrig@de.ibm.com)
* Major cleanup & driver split: Martin Schwidefsky <schwidefsky@de.ibm.com>
* MSGTYPE restruct: Holger Dengler <hd@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
*/
#ifndef _ZCRYPT_MSGTYPE50_H_
+// SPDX-License-Identifier: GPL-2.0+
/*
* zcrypt 2.1.0
*
* Major cleanup & driver split: Martin Schwidefsky <schwidefsky@de.ibm.com>
* Ralph Wuerthner <rwuerthn@de.ibm.com>
* MSGTYPE restruct: Holger Dengler <hd@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
*/
#define KMSG_COMPONENT "zcrypt"
+// SPDX-License-Identifier: GPL-2.0+
/*
* zcrypt 2.1.0
*
* Hotplug & misc device support: Jochen Roehrig (roehrig@de.ibm.com)
* Major cleanup & driver split: Martin Schwidefsky <schwidefsky@de.ibm.com>
* MSGTYPE restruct: Holger Dengler <hd@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
*/
#ifndef _ZCRYPT_MSGTYPE6_H_
+// SPDX-License-Identifier: GPL-2.0+
/*
* zcrypt 2.1.0
*
* Major cleanup & driver split: Martin Schwidefsky <schwidefsky@de.ibm.com>
* Ralph Wuerthner <rwuerthn@de.ibm.com>
* MSGTYPE restruct: Holger Dengler <hd@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
*/
#include <linux/module.h>
+// SPDX-License-Identifier: GPL-2.0+
/*
* zcrypt 2.1.0
*
* Hotplug & misc device support: Jochen Roehrig (roehrig@de.ibm.com)
* Major cleanup & driver split: Martin Schwidefsky <schwidefsky@de.ibm.com>
* MSGTYPE restruct: Holger Dengler <hd@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
*/
#ifndef _ZCRYPT_PCIXCC_H_
+// SPDX-License-Identifier: GPL-2.0+
/*
* zcrypt 2.1.0
*
* Major cleanup & driver split: Martin Schwidefsky <schwidefsky@de.ibm.com>
* Ralph Wuerthner <rwuerthn@de.ibm.com>
* MSGTYPE restruct: Holger Dengler <hd@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
*/
#include <linux/module.h>
+// SPDX-License-Identifier: GPL-2.0
/*
* Copyright IBM Corp. 2001, 2009
* Author(s):
+// SPDX-License-Identifier: GPL-2.0
/**
* A generic FSM based on fsm used in isdn4linux
*
+// SPDX-License-Identifier: GPL-2.0+
/*
* Linux for S/390 Lan Channel Station Network Driver
*
* Rewritten by
* Frank Pavlic <fpavlic@de.ibm.com> and
* Martin Schwidefsky <schwidefsky@de.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
*/
#define KMSG_COMPONENT "lcs"
+// SPDX-License-Identifier: GPL-2.0+
/*
* IUCV network driver
*
* Denis Joseph Barrow (djbarrow@de.ibm.com,barrow_dj@yahoo.com)
* Martin Schwidefsky (schwidefsky@de.ibm.com)
* Alan Altmark (Alan_Altmark@us.ibm.com) Sept. 2000
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- *
*/
#define KMSG_COMPONENT "netiucv"
+// SPDX-License-Identifier: GPL-2.0
/*
* Copyright IBM Corp. 2007, 2009
* Author(s): Utz Bacher <utz.bacher@de.ibm.com>,
+// SPDX-License-Identifier: GPL-2.0
/*
* Copyright IBM Corp. 2007
* Author(s): Utz Bacher <utz.bacher@de.ibm.com>,
+// SPDX-License-Identifier: GPL-2.0
/*
* Copyright IBM Corp. 2007, 2009
* Author(s): Utz Bacher <utz.bacher@de.ibm.com>,
+// SPDX-License-Identifier: GPL-2.0
/*
* Copyright IBM Corp. 2007, 2009
* Author(s): Utz Bacher <utz.bacher@de.ibm.com>,
+// SPDX-License-Identifier: GPL-2.0+
/*
* IUCV special message driver
*
* Copyright IBM Corp. 2003, 2009
*
* Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com)
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
*/
#include <linux/module.h>
+// SPDX-License-Identifier: GPL-2.0
/*
* Deliver z/VM CP special messages (SMSG) as uevents.
*
+// SPDX-License-Identifier: GPL-2.0
/*
* zfcp device driver
*
+# SPDX-License-Identifier: GPL-2.0
# Makefile for kvm guest drivers on s390
#
# Copyright IBM Corp. 2008
-#
-# This program is free software; you can redistribute it and/or modify
-# it under the terms of the GNU General Public License (version 2 only)
-# as published by the Free Software Foundation.
obj-$(CONFIG_S390_GUEST) += virtio_ccw.o
+// SPDX-License-Identifier: GPL-2.0
/*
* ccw based virtio transport
*
* Copyright IBM Corp. 2012, 2014
*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
- *
* Author(s): Cornelia Huck <cornelia.huck@de.ibm.com>
*/
if ((mnt->mnt_flags & MNT_NODIRATIME) && S_ISDIR(inode->i_mode))
return true;
- if ((inode->i_sb->s_flags & MS_NODIRATIME) && S_ISDIR(inode->i_mode))
+ if ((inode->i_sb->s_flags & SB_NODIRATIME) && S_ISDIR(inode->i_mode))
return true;
return false;
}
if (data->ocd_connect_flags & OBD_CONNECT_ACL) {
- sb->s_flags |= MS_POSIXACL;
+ sb->s_flags |= SB_POSIXACL;
sbi->ll_flags |= LL_SBI_ACL;
} else {
LCONSOLE_INFO("client wants to enable acl, but mdt not!\n");
- sb->s_flags &= ~MS_POSIXACL;
+ sb->s_flags &= ~SB_POSIXACL;
sbi->ll_flags &= ~LL_SBI_ACL;
}
struct ll_sb_info *sbi;
/* not init sb ?*/
- if (!(sb->s_flags & MS_ACTIVE))
+ if (!(sb->s_flags & SB_ACTIVE))
return;
sbi = ll_s2sbi(sb);
int err;
__u32 read_only;
- if ((bool)(*flags & MS_RDONLY) != sb_rdonly(sb)) {
- read_only = *flags & MS_RDONLY;
+ if ((bool)(*flags & SB_RDONLY) != sb_rdonly(sb)) {
+ read_only = *flags & SB_RDONLY;
err = obd_set_info_async(NULL, sbi->ll_md_exp,
sizeof(KEY_READ_ONLY),
KEY_READ_ONLY, sizeof(read_only),
}
if (read_only)
- sb->s_flags |= MS_RDONLY;
+ sb->s_flags |= SB_RDONLY;
else
- sb->s_flags &= ~MS_RDONLY;
+ sb->s_flags &= ~SB_RDONLY;
if (sbi->ll_flags & LL_SBI_VERBOSE)
LCONSOLE_WARN("Remounted %s %s\n", profilenm,
if (v9ses->cache)
sb->s_bdi->ra_pages = (VM_MAX_READAHEAD * 1024)/PAGE_SIZE;
- sb->s_flags |= MS_ACTIVE | MS_DIRSYNC | MS_NOATIME;
+ sb->s_flags |= SB_ACTIVE | SB_DIRSYNC | SB_NOATIME;
if (!v9ses->cache)
- sb->s_flags |= MS_SYNCHRONOUS;
+ sb->s_flags |= SB_SYNCHRONOUS;
#ifdef CONFIG_9P_FS_POSIX_ACL
if ((v9ses->flags & V9FS_ACL_MASK) == V9FS_POSIX_ACL)
- sb->s_flags |= MS_POSIXACL;
+ sb->s_flags |= SB_POSIXACL;
#endif
return 0;
static int adfs_remount(struct super_block *sb, int *flags, char *data)
{
sync_filesystem(sb);
- *flags |= MS_NODIRATIME;
+ *flags |= SB_NODIRATIME;
return parse_options(sb, data);
}
struct inode *root;
int ret = -EINVAL;
- sb->s_flags |= MS_NODIRATIME;
+ sb->s_flags |= SB_NODIRATIME;
asb = kzalloc(sizeof(*asb), GFP_KERNEL);
if (!asb)
pr_crit("error (device %s): %s(): %pV\n", sb->s_id, function, &vaf);
if (!sb_rdonly(sb))
pr_warn("Remounting filesystem read-only\n");
- sb->s_flags |= MS_RDONLY;
+ sb->s_flags |= SB_RDONLY;
va_end(args);
}
int i, res = 0;
struct affs_sb_info *sbi = AFFS_SB(sb);
- if (*flags & MS_RDONLY)
+ if (*flags & SB_RDONLY)
return 0;
if (!AFFS_ROOT_TAIL(sb, sbi->s_root_bh)->bm_flag) {
pr_notice("Bitmap invalid - mounting %s read only\n", sb->s_id);
- *flags |= MS_RDONLY;
+ *flags |= SB_RDONLY;
return 0;
}
if (affs_checksum_block(sb, bh)) {
pr_warn("Bitmap %u invalid - mounting %s read only.\n",
bm->bm_key, sb->s_id);
- *flags |= MS_RDONLY;
+ *flags |= SB_RDONLY;
goto out;
}
pr_debug("read bitmap block %d: %d\n", blk, bm->bm_key);
sb->s_magic = AFFS_SUPER_MAGIC;
sb->s_op = &affs_sops;
- sb->s_flags |= MS_NODIRATIME;
+ sb->s_flags |= SB_NODIRATIME;
sbi = kzalloc(sizeof(struct affs_sb_info), GFP_KERNEL);
if (!sbi)
if ((chksum == FS_DCFFS || chksum == MUFS_DCFFS || chksum == FS_DCOFS
|| chksum == MUFS_DCOFS) && !sb_rdonly(sb)) {
pr_notice("Dircache FS - mounting %s read only\n", sb->s_id);
- sb->s_flags |= MS_RDONLY;
+ sb->s_flags |= SB_RDONLY;
}
switch (chksum) {
case MUFS_FS:
/* fall thru */
case FS_OFS:
affs_set_opt(sbi->s_flags, SF_OFS);
- sb->s_flags |= MS_NOEXEC;
+ sb->s_flags |= SB_NOEXEC;
break;
case MUFS_DCOFS:
case MUFS_INTLOFS:
case FS_INTLOFS:
affs_set_opt(sbi->s_flags, SF_INTL);
affs_set_opt(sbi->s_flags, SF_OFS);
- sb->s_flags |= MS_NOEXEC;
+ sb->s_flags |= SB_NOEXEC;
break;
default:
pr_err("Unknown filesystem on device %s: %08X\n",
sig, sig[3] + '0', blocksize);
}
- sb->s_flags |= MS_NODEV | MS_NOSUID;
+ sb->s_flags |= SB_NODEV | SB_NOSUID;
sbi->s_data_blksize = sb->s_blocksize;
if (affs_test_opt(sbi->s_flags, SF_OFS))
pr_debug("%s(flags=0x%x,opts=\"%s\")\n", __func__, *flags, data);
sync_filesystem(sb);
- *flags |= MS_NODIRATIME;
+ *flags |= SB_NODIRATIME;
memcpy(volume, sbi->s_volume, 32);
if (!parse_options(data, &uid, &gid, &mode, &reserved, &root_block,
memcpy(sbi->s_volume, volume, 32);
spin_unlock(&sbi->symlink_lock);
- if ((bool)(*flags & MS_RDONLY) == sb_rdonly(sb))
+ if ((bool)(*flags & SB_RDONLY) == sb_rdonly(sb))
return 0;
- if (*flags & MS_RDONLY)
+ if (*flags & SB_RDONLY)
affs_free_bitmap(sb);
else
res = affs_init_bitmap(sb, flags);
};
/*
- * AFS inode private data
+ * AFS inode private data.
+ *
+ * Note that afs_alloc_inode() *must* reset anything that could incorrectly
+ * leak from one inode to another.
*/
struct afs_vnode {
struct inode vfs_inode; /* the VFS's inode record */
void afs_cache_permit(struct afs_vnode *vnode, struct key *key,
unsigned int cb_break)
{
- struct afs_permits *permits, *xpermits, *replacement, *new = NULL;
+ struct afs_permits *permits, *xpermits, *replacement, *zap, *new = NULL;
afs_access_t caller_access = READ_ONCE(vnode->status.caller_access);
size_t size = 0;
bool changed = false;
new = kzalloc(sizeof(struct afs_permits) +
sizeof(struct afs_permit) * size, GFP_NOFS);
if (!new)
- return;
+ goto out_put;
refcount_set(&new->usage, 1);
new->nr_permits = size;
afs_hash_permits(new);
- afs_put_permits(permits);
-
/* Now see if the permit list we want is actually already available */
spin_lock(&afs_permits_lock);
kfree(new);
spin_lock(&vnode->lock);
- if (cb_break != (vnode->cb_break + vnode->cb_interest->server->cb_s_break) ||
- permits != rcu_access_pointer(vnode->permit_cache))
- goto someone_else_changed_it_unlock;
- rcu_assign_pointer(vnode->permit_cache, replacement);
+ zap = rcu_access_pointer(vnode->permit_cache);
+ if (cb_break == (vnode->cb_break + vnode->cb_interest->server->cb_s_break) &&
+ zap == permits)
+ rcu_assign_pointer(vnode->permit_cache, replacement);
+ else
+ zap = replacement;
spin_unlock(&vnode->lock);
+ afs_put_permits(zap);
+out_put:
afs_put_permits(permits);
return;
if (ret < 0)
goto error_sb;
as = NULL;
- sb->s_flags |= MS_ACTIVE;
+ sb->s_flags |= SB_ACTIVE;
} else {
_debug("reuse");
- ASSERTCMP(sb->s_flags, &, MS_ACTIVE);
+ ASSERTCMP(sb->s_flags, &, SB_ACTIVE);
afs_destroy_sbi(as);
as = NULL;
}
}
/*
- * initialise an inode cache slab element prior to any use
+ * Initialise an inode cache slab element prior to any use. Note that
+ * afs_alloc_inode() *must* reset anything that could incorrectly leak from one
+ * inode to another.
*/
static void afs_i_init_once(void *_vnode)
{
atomic_inc(&afs_count_active_inodes);
+ /* Reset anything that shouldn't leak from one inode to the next. */
memset(&vnode->fid, 0, sizeof(vnode->fid));
memset(&vnode->status, 0, sizeof(vnode->status));
vnode->volume = NULL;
+ vnode->lock_key = NULL;
+ vnode->permit_cache = NULL;
+ vnode->cb_interest = NULL;
+#ifdef CONFIG_AFS_FSCACHE
+ vnode->cache = NULL;
+#endif
+
vnode->flags = 1 << AFS_VNODE_UNSET;
+ vnode->cb_type = 0;
+ vnode->lock_state = AFS_VNODE_LOCK_NONE;
_leave(" = %p", &vnode->vfs_inode);
return &vnode->vfs_inode;
pr_debug("waiting for mount name=%pd\n", path->dentry);
status = autofs4_wait(sbi, path, NFY_MOUNT);
pr_debug("mount wait done status=%d\n", status);
- ino->last_used = jiffies;
}
+ ino->last_used = jiffies;
return status;
}
*/
if (autofs_type_indirect(sbi->type) && d_unhashed(dentry)) {
struct dentry *parent = dentry->d_parent;
+ struct autofs_info *ino;
struct dentry *new;
new = d_lookup(parent, &dentry->d_name);
if (!new)
return NULL;
- if (new == dentry)
- dput(new);
- else {
- struct autofs_info *ino;
-
- ino = autofs4_dentry_ino(new);
- ino->last_used = jiffies;
- dput(path->dentry);
- path->dentry = new;
- }
+ ino = autofs4_dentry_ino(new);
+ ino->last_used = jiffies;
+ dput(path->dentry);
+ path->dentry = new;
}
return path->dentry;
}
(fs/befs/super.c)
* Tell the kernel to only mount befs read-only.
- By setting the MS_RDONLY flag in befs_read_super().
+ By setting the SB_RDONLY flag in befs_read_super().
Not that it was possible to write before. But now the kernel won't even try.
(fs/befs/super.c)
if (!sb_rdonly(sb)) {
befs_warning(sb,
"No write support. Marking filesystem read-only");
- sb->s_flags |= MS_RDONLY;
+ sb->s_flags |= SB_RDONLY;
}
/*
befs_remount(struct super_block *sb, int *flags, char *data)
{
sync_filesystem(sb);
- if (!(*flags & MS_RDONLY))
+ if (!(*flags & SB_RDONLY))
return -EINVAL;
return 0;
}
unsigned long len, u64 disk_start,
unsigned long compressed_len,
struct page **compressed_pages,
- unsigned long nr_pages)
+ unsigned long nr_pages,
+ unsigned int write_flags)
{
struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
struct bio *bio = NULL;
bdev = fs_info->fs_devices->latest_bdev;
bio = btrfs_bio_alloc(bdev, first_byte);
- bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
+ bio->bi_opf = REQ_OP_WRITE | write_flags;
bio->bi_private = cb;
bio->bi_end_io = end_compressed_bio_write;
refcount_set(&cb->pending_bios, 1);
bio_put(bio);
bio = btrfs_bio_alloc(bdev, first_byte);
- bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
+ bio->bi_opf = REQ_OP_WRITE | write_flags;
bio->bi_private = cb;
bio->bi_end_io = end_compressed_bio_write;
bio_add_page(bio, page, PAGE_SIZE, 0);
if (str[4] == ':' && '1' <= str[5] && str[5] <= '9' && str[6] == 0)
return str[5] - '0';
- return 0;
+ return BTRFS_ZLIB_DEFAULT_LEVEL;
}
/* Maximum size of data before compression */
#define BTRFS_MAX_UNCOMPRESSED (SZ_128K)
+#define BTRFS_ZLIB_DEFAULT_LEVEL 3
+
struct compressed_bio {
/* number of bios pending for this compressed extent */
refcount_t pending_bios;
unsigned long len, u64 disk_start,
unsigned long compressed_len,
struct page **compressed_pages,
- unsigned long nr_pages);
+ unsigned long nr_pages,
+ unsigned int write_flags);
blk_status_t btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
int mirror_num, unsigned long bio_flags);
*/
static inline int btrfs_need_cleaner_sleep(struct btrfs_fs_info *fs_info)
{
- return fs_info->sb->s_flags & MS_RDONLY || btrfs_fs_closing(fs_info);
+ return fs_info->sb->s_flags & SB_RDONLY || btrfs_fs_closing(fs_info);
}
static inline void free_fs_info(struct btrfs_fs_info *fs_info)
int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, int delay_iput,
int nr);
int btrfs_set_extent_delalloc(struct inode *inode, u64 start, u64 end,
+ unsigned int extra_bits,
struct extent_state **cached_state, int dedupe);
int btrfs_create_subvol_root(struct btrfs_trans_handle *trans,
struct btrfs_root *new_root,
* that we don't try and read the other copies of this block, just
* return -EIO.
*/
- if (found_level == 0 && btrfs_check_leaf(root, eb)) {
+ if (found_level == 0 && btrfs_check_leaf_full(root, eb)) {
set_bit(EXTENT_BUFFER_CORRUPT, &eb->bflags);
ret = -EIO;
}
buf->len,
fs_info->dirty_metadata_batch);
#ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY
- if (btrfs_header_level(buf) == 0 && btrfs_check_leaf(root, buf)) {
+ /*
+ * Since btrfs_mark_buffer_dirty() can be called with item pointer set
+ * but item data not updated.
+ * So here we should only check item pointers, not item data.
+ */
+ if (btrfs_header_level(buf) == 0 &&
+ btrfs_check_leaf_relaxed(root, buf)) {
btrfs_print_leaf(buf);
ASSERT(0);
}
goto again;
}
- /* We've already setup this transaction, go ahead and exit */
- if (block_group->cache_generation == trans->transid &&
- i_size_read(inode)) {
- dcs = BTRFS_DC_SETUP;
- goto out_put;
- }
-
/*
* We want to set the generation to 0, that way if anything goes wrong
* from here on out we know not to trust this cache when we load up next
}
WARN_ON(ret);
+ /* We've already setup this transaction, go ahead and exit */
+ if (block_group->cache_generation == trans->transid &&
+ i_size_read(inode)) {
+ dcs = BTRFS_DC_SETUP;
+ goto out_put;
+ }
+
if (i_size_read(inode) > 0) {
ret = btrfs_check_trunc_cache_free_space(fs_info,
&fs_info->global_block_rsv);
struct btrfs_bio *bbio = NULL;
int ret;
- ASSERT(!(fs_info->sb->s_flags & MS_RDONLY));
+ ASSERT(!(fs_info->sb->s_flags & SB_RDONLY));
BUG_ON(!mirror_num);
bio = btrfs_io_bio_alloc(1);
delalloc_start,
delalloc_end,
&page_started,
- nr_written);
+ nr_written, wbc);
/* File system has been set read-only */
if (ret) {
SetPageError(page);
*/
int (*fill_delalloc)(void *private_data, struct page *locked_page,
u64 start, u64 end, int *page_started,
- unsigned long *nr_written);
+ unsigned long *nr_written,
+ struct writeback_control *wbc);
int (*writepage_start_hook)(struct page *page, u64 start, u64 end);
void (*writepage_end_io_hook)(struct page *page, u64 start, u64 end,
struct extent_state **cached_state);
static inline int set_extent_delalloc(struct extent_io_tree *tree, u64 start,
- u64 end, struct extent_state **cached_state)
+ u64 end, unsigned int extra_bits,
+ struct extent_state **cached_state)
{
return set_extent_bit(tree, start, end,
- EXTENT_DELALLOC | EXTENT_UPTODATE,
+ EXTENT_DELALLOC | EXTENT_UPTODATE | extra_bits,
NULL, cached_state, GFP_NOFS);
}
}
}
+static int btrfs_find_new_delalloc_bytes(struct btrfs_inode *inode,
+ const u64 start,
+ const u64 len,
+ struct extent_state **cached_state)
+{
+ u64 search_start = start;
+ const u64 end = start + len - 1;
+
+ while (search_start < end) {
+ const u64 search_len = end - search_start + 1;
+ struct extent_map *em;
+ u64 em_len;
+ int ret = 0;
+
+ em = btrfs_get_extent(inode, NULL, 0, search_start,
+ search_len, 0);
+ if (IS_ERR(em))
+ return PTR_ERR(em);
+
+ if (em->block_start != EXTENT_MAP_HOLE)
+ goto next;
+
+ em_len = em->len;
+ if (em->start < search_start)
+ em_len -= search_start - em->start;
+ if (em_len > search_len)
+ em_len = search_len;
+
+ ret = set_extent_bit(&inode->io_tree, search_start,
+ search_start + em_len - 1,
+ EXTENT_DELALLOC_NEW,
+ NULL, cached_state, GFP_NOFS);
+next:
+ search_start = extent_map_end(em);
+ free_extent_map(em);
+ if (ret)
+ return ret;
+ }
+ return 0;
+}
+
/*
* after copy_from_user, pages need to be dirtied and we need to make
* sure holes are created between the current EOF and the start of
u64 end_of_last_block;
u64 end_pos = pos + write_bytes;
loff_t isize = i_size_read(inode);
+ unsigned int extra_bits = 0;
start_pos = pos & ~((u64) fs_info->sectorsize - 1);
num_bytes = round_up(write_bytes + pos - start_pos,
fs_info->sectorsize);
end_of_last_block = start_pos + num_bytes - 1;
+
+ if (!btrfs_is_free_space_inode(BTRFS_I(inode))) {
+ if (start_pos >= isize &&
+ !(BTRFS_I(inode)->flags & BTRFS_INODE_PREALLOC)) {
+ /*
+ * There can't be any extents following eof in this case
+ * so just set the delalloc new bit for the range
+ * directly.
+ */
+ extra_bits |= EXTENT_DELALLOC_NEW;
+ } else {
+ err = btrfs_find_new_delalloc_bytes(BTRFS_I(inode),
+ start_pos,
+ num_bytes, cached);
+ if (err)
+ return err;
+ }
+ }
+
err = btrfs_set_extent_delalloc(inode, start_pos, end_of_last_block,
- cached, 0);
+ extra_bits, cached, 0);
if (err)
return err;
}
-static int btrfs_find_new_delalloc_bytes(struct btrfs_inode *inode,
- const u64 start,
- const u64 len,
- struct extent_state **cached_state)
-{
- u64 search_start = start;
- const u64 end = start + len - 1;
-
- while (search_start < end) {
- const u64 search_len = end - search_start + 1;
- struct extent_map *em;
- u64 em_len;
- int ret = 0;
-
- em = btrfs_get_extent(inode, NULL, 0, search_start,
- search_len, 0);
- if (IS_ERR(em))
- return PTR_ERR(em);
-
- if (em->block_start != EXTENT_MAP_HOLE)
- goto next;
-
- em_len = em->len;
- if (em->start < search_start)
- em_len -= search_start - em->start;
- if (em_len > search_len)
- em_len = search_len;
-
- ret = set_extent_bit(&inode->io_tree, search_start,
- search_start + em_len - 1,
- EXTENT_DELALLOC_NEW,
- NULL, cached_state, GFP_NOFS);
-next:
- search_start = extent_map_end(em);
- free_extent_map(em);
- if (ret)
- return ret;
- }
- return 0;
-}
-
/*
* This function locks the extent and properly waits for data=ordered extents
* to finish before allowing the pages to be modified if need.
+ round_up(pos + write_bytes - start_pos,
fs_info->sectorsize) - 1;
- if (start_pos < inode->vfs_inode.i_size ||
- (inode->flags & BTRFS_INODE_PREALLOC)) {
+ if (start_pos < inode->vfs_inode.i_size) {
struct btrfs_ordered_extent *ordered;
- unsigned int clear_bits;
lock_extent_bits(&inode->io_tree, start_pos, last_pos,
cached_state);
}
if (ordered)
btrfs_put_ordered_extent(ordered);
- ret = btrfs_find_new_delalloc_bytes(inode, start_pos,
- last_pos - start_pos + 1,
- cached_state);
- clear_bits = EXTENT_DIRTY | EXTENT_DELALLOC |
- EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG;
- if (ret)
- clear_bits |= EXTENT_DELALLOC_NEW | EXTENT_LOCKED;
- clear_extent_bit(&inode->io_tree, start_pos,
- last_pos, clear_bits,
- (clear_bits & EXTENT_LOCKED) ? 1 : 0,
- 0, cached_state, GFP_NOFS);
- if (ret)
- return ret;
+ clear_extent_bit(&inode->io_tree, start_pos, last_pos,
+ EXTENT_DIRTY | EXTENT_DELALLOC |
+ EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG,
+ 0, 0, cached_state, GFP_NOFS);
*lockstart = start_pos;
*lockend = last_pos;
ret = 1;
len = (u64)end - (u64)start + 1;
trace_btrfs_sync_file(file, datasync);
+ btrfs_init_log_ctx(&ctx, inode);
+
/*
* We write the dirty pages in the range and wait until they complete
* out of the ->i_mutex. If so, we can flush the dirty pages by
}
trans->sync = true;
- btrfs_init_log_ctx(&ctx, inode);
-
ret = btrfs_log_dentry_safe(trans, root, dentry, start, end, &ctx);
if (ret < 0) {
/* Fallthrough and commit/free transaction. */
ret = btrfs_end_transaction(trans);
}
out:
+ ASSERT(list_empty(&ctx.list));
err = file_check_and_advance_wb_err(file);
if (!ret)
ret = err;
/* Lock all pages first so we can lock the extent safely. */
ret = io_ctl_prepare_pages(io_ctl, inode, 0);
if (ret)
- goto out;
+ goto out_unlock;
lock_extent_bits(&BTRFS_I(inode)->io_tree, 0, i_size_read(inode) - 1,
&cached_state);
out_nospc:
cleanup_write_cache_enospc(inode, io_ctl, &cached_state);
+out_unlock:
if (block_group && (block_group->flags & BTRFS_BLOCK_GROUP_DATA))
up_write(&block_group->data_rwsem);
struct page *locked_page;
u64 start;
u64 end;
+ unsigned int write_flags;
struct list_head extents;
struct btrfs_work work;
};
async_extent->ram_size,
ins.objectid,
ins.offset, async_extent->pages,
- async_extent->nr_pages)) {
+ async_extent->nr_pages,
+ async_cow->write_flags)) {
struct extent_io_tree *tree = &BTRFS_I(inode)->io_tree;
struct page *p = async_extent->pages[0];
const u64 start = async_extent->start;
static int cow_file_range_async(struct inode *inode, struct page *locked_page,
u64 start, u64 end, int *page_started,
- unsigned long *nr_written)
+ unsigned long *nr_written,
+ unsigned int write_flags)
{
struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
struct async_cow *async_cow;
async_cow->root = root;
async_cow->locked_page = locked_page;
async_cow->start = start;
+ async_cow->write_flags = write_flags;
if (BTRFS_I(inode)->flags & BTRFS_INODE_NOCOMPRESS &&
!btrfs_test_opt(fs_info, FORCE_COMPRESS))
*/
static int run_delalloc_range(void *private_data, struct page *locked_page,
u64 start, u64 end, int *page_started,
- unsigned long *nr_written)
+ unsigned long *nr_written,
+ struct writeback_control *wbc)
{
struct inode *inode = private_data;
int ret;
int force_cow = need_force_cow(inode, start, end);
+ unsigned int write_flags = wbc_to_write_flags(wbc);
if (BTRFS_I(inode)->flags & BTRFS_INODE_NODATACOW && !force_cow) {
ret = run_delalloc_nocow(inode, locked_page, start, end,
set_bit(BTRFS_INODE_HAS_ASYNC_EXTENT,
&BTRFS_I(inode)->runtime_flags);
ret = cow_file_range_async(inode, locked_page, start, end,
- page_started, nr_written);
+ page_started, nr_written,
+ write_flags);
}
if (ret)
btrfs_cleanup_ordered_extents(inode, start, end - start + 1);
}
int btrfs_set_extent_delalloc(struct inode *inode, u64 start, u64 end,
+ unsigned int extra_bits,
struct extent_state **cached_state, int dedupe)
{
WARN_ON((end & (PAGE_SIZE - 1)) == 0);
return set_extent_delalloc(&BTRFS_I(inode)->io_tree, start, end,
- cached_state);
+ extra_bits, cached_state);
}
/* see btrfs_writepage_start_hook for details on why this is required */
goto out;
}
- btrfs_set_extent_delalloc(inode, page_start, page_end, &cached_state,
+ btrfs_set_extent_delalloc(inode, page_start, page_end, 0, &cached_state,
0);
ClearPageChecked(page);
set_page_dirty(page);
EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG,
0, 0, &cached_state, GFP_NOFS);
- ret = btrfs_set_extent_delalloc(inode, block_start, block_end,
+ ret = btrfs_set_extent_delalloc(inode, block_start, block_end, 0,
&cached_state, 0);
if (ret) {
unlock_extent_cached(io_tree, block_start, block_end,
goto out_err;
btrfs_dir_item_key_to_cpu(path->nodes[0], di, location);
+ if (location->type != BTRFS_INODE_ITEM_KEY &&
+ location->type != BTRFS_ROOT_ITEM_KEY) {
+ btrfs_warn(root->fs_info,
+"%s gets something invalid in DIR_ITEM (name %s, directory ino %llu, location(%llu %u %llu))",
+ __func__, name, btrfs_ino(BTRFS_I(dir)),
+ location->objectid, location->type, location->offset);
+ goto out_err;
+ }
out:
btrfs_free_path(path);
return ret;
return inode;
}
- BUG_ON(location.type != BTRFS_ROOT_ITEM_KEY);
-
index = srcu_read_lock(&fs_info->subvol_srcu);
ret = fixup_tree_root_location(fs_info, dir, dentry,
&location, &sub_root);
EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG,
0, 0, &cached_state, GFP_NOFS);
- ret = btrfs_set_extent_delalloc(inode, page_start, end,
+ ret = btrfs_set_extent_delalloc(inode, page_start, end, 0,
&cached_state, 0);
if (ret) {
unlock_extent_cached(io_tree, page_start, page_end,
if (!i_done || ret)
goto out;
- if (!(inode->i_sb->s_flags & MS_ACTIVE))
+ if (!(inode->i_sb->s_flags & SB_ACTIVE))
goto out;
/*
* make sure we stop running if someone unmounts
* the FS
*/
- if (!(inode->i_sb->s_flags & MS_ACTIVE))
+ if (!(inode->i_sb->s_flags & SB_ACTIVE))
break;
if (btrfs_defrag_cancelled(fs_info)) {
nr++;
}
- btrfs_set_extent_delalloc(inode, page_start, page_end, NULL, 0);
+ btrfs_set_extent_delalloc(inode, page_start, page_end, 0, NULL,
+ 0);
set_page_dirty(page);
unlock_extent(&BTRFS_I(inode)->io_tree,
}
/*
- * Check if ino ino1 is an ancestor of inode ino2 in the given root.
+ * Check if inode ino2, or any of its ancestors, is inode ino1.
+ * Return 1 if true, 0 if false and < 0 on error.
+ */
+static int check_ino_in_path(struct btrfs_root *root,
+ const u64 ino1,
+ const u64 ino1_gen,
+ const u64 ino2,
+ const u64 ino2_gen,
+ struct fs_path *fs_path)
+{
+ u64 ino = ino2;
+
+ if (ino1 == ino2)
+ return ino1_gen == ino2_gen;
+
+ while (ino > BTRFS_FIRST_FREE_OBJECTID) {
+ u64 parent;
+ u64 parent_gen;
+ int ret;
+
+ fs_path_reset(fs_path);
+ ret = get_first_ref(root, ino, &parent, &parent_gen, fs_path);
+ if (ret < 0)
+ return ret;
+ if (parent == ino1)
+ return parent_gen == ino1_gen;
+ ino = parent;
+ }
+ return 0;
+}
+
+/*
+ * Check if ino ino1 is an ancestor of inode ino2 in the given root for any
+ * possible path (in case ino2 is not a directory and has multiple hard links).
* Return 1 if true, 0 if false and < 0 on error.
*/
static int is_ancestor(struct btrfs_root *root,
const u64 ino2,
struct fs_path *fs_path)
{
- u64 ino = ino2;
- bool free_path = false;
+ bool free_fs_path = false;
int ret = 0;
+ struct btrfs_path *path = NULL;
+ struct btrfs_key key;
if (!fs_path) {
fs_path = fs_path_alloc();
if (!fs_path)
return -ENOMEM;
- free_path = true;
+ free_fs_path = true;
}
- while (ino > BTRFS_FIRST_FREE_OBJECTID) {
- u64 parent;
- u64 parent_gen;
+ path = alloc_path_for_send();
+ if (!path) {
+ ret = -ENOMEM;
+ goto out;
+ }
- fs_path_reset(fs_path);
- ret = get_first_ref(root, ino, &parent, &parent_gen, fs_path);
- if (ret < 0) {
- if (ret == -ENOENT && ino == ino2)
- ret = 0;
- goto out;
+ key.objectid = ino2;
+ key.type = BTRFS_INODE_REF_KEY;
+ key.offset = 0;
+
+ ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
+ if (ret < 0)
+ goto out;
+
+ while (true) {
+ struct extent_buffer *leaf = path->nodes[0];
+ int slot = path->slots[0];
+ u32 cur_offset = 0;
+ u32 item_size;
+
+ if (slot >= btrfs_header_nritems(leaf)) {
+ ret = btrfs_next_leaf(root, path);
+ if (ret < 0)
+ goto out;
+ if (ret > 0)
+ break;
+ continue;
}
- if (parent == ino1) {
- ret = parent_gen == ino1_gen ? 1 : 0;
- goto out;
+
+ btrfs_item_key_to_cpu(leaf, &key, slot);
+ if (key.objectid != ino2)
+ break;
+ if (key.type != BTRFS_INODE_REF_KEY &&
+ key.type != BTRFS_INODE_EXTREF_KEY)
+ break;
+
+ item_size = btrfs_item_size_nr(leaf, slot);
+ while (cur_offset < item_size) {
+ u64 parent;
+ u64 parent_gen;
+
+ if (key.type == BTRFS_INODE_EXTREF_KEY) {
+ unsigned long ptr;
+ struct btrfs_inode_extref *extref;
+
+ ptr = btrfs_item_ptr_offset(leaf, slot);
+ extref = (struct btrfs_inode_extref *)
+ (ptr + cur_offset);
+ parent = btrfs_inode_extref_parent(leaf,
+ extref);
+ cur_offset += sizeof(*extref);
+ cur_offset += btrfs_inode_extref_name_len(leaf,
+ extref);
+ } else {
+ parent = key.offset;
+ cur_offset = item_size;
+ }
+
+ ret = get_inode_info(root, parent, NULL, &parent_gen,
+ NULL, NULL, NULL, NULL);
+ if (ret < 0)
+ goto out;
+ ret = check_ino_in_path(root, ino1, ino1_gen,
+ parent, parent_gen, fs_path);
+ if (ret)
+ goto out;
}
- ino = parent;
+ path->slots[0]++;
}
+ ret = 0;
out:
- if (free_path)
+ btrfs_free_path(path);
+ if (free_fs_path)
fs_path_free(fs_path);
return ret;
}
return;
if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state)) {
- sb->s_flags |= MS_RDONLY;
+ sb->s_flags |= SB_RDONLY;
btrfs_info(fs_info, "forced readonly");
/*
* Note that a running device replace operation is not
/*
* Special case: if the error is EROFS, and we're already
- * under MS_RDONLY, then it is safe here.
+ * under SB_RDONLY, then it is safe here.
*/
if (errno == -EROFS && sb_rdonly(sb))
return;
set_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state);
/* Don't go through full error handling during mount */
- if (sb->s_flags & MS_BORN)
+ if (sb->s_flags & SB_BORN)
btrfs_handle_error(fs_info);
}
token == Opt_compress_force ||
strncmp(args[0].from, "zlib", 4) == 0) {
compress_type = "zlib";
+
info->compress_type = BTRFS_COMPRESS_ZLIB;
- info->compress_level =
- btrfs_compress_str2level(args[0].from);
+ info->compress_level = BTRFS_ZLIB_DEFAULT_LEVEL;
+ /*
+ * args[0] contains uninitialized data since
+ * for these tokens we don't expect any
+ * parameter.
+ */
+ if (token != Opt_compress &&
+ token != Opt_compress_force)
+ info->compress_level =
+ btrfs_compress_str2level(args[0].from);
btrfs_set_opt(info->mount_opt, COMPRESS);
btrfs_clear_opt(info->mount_opt, NODATACOW);
btrfs_clear_opt(info->mount_opt, NODATASUM);
break;
case Opt_acl:
#ifdef CONFIG_BTRFS_FS_POSIX_ACL
- info->sb->s_flags |= MS_POSIXACL;
+ info->sb->s_flags |= SB_POSIXACL;
break;
#else
btrfs_err(info, "support for ACL not compiled in!");
goto out;
#endif
case Opt_noacl:
- info->sb->s_flags &= ~MS_POSIXACL;
+ info->sb->s_flags &= ~SB_POSIXACL;
break;
case Opt_notreelog:
btrfs_set_and_info(info, NOTREELOG,
/*
* Extra check for current option against current flag
*/
- if (btrfs_test_opt(info, NOLOGREPLAY) && !(new_flags & MS_RDONLY)) {
+ if (btrfs_test_opt(info, NOLOGREPLAY) && !(new_flags & SB_RDONLY)) {
btrfs_err(info,
"nologreplay must be used with ro mount option");
ret = -EINVAL;
sb->s_xattr = btrfs_xattr_handlers;
sb->s_time_gran = 1;
#ifdef CONFIG_BTRFS_FS_POSIX_ACL
- sb->s_flags |= MS_POSIXACL;
+ sb->s_flags |= SB_POSIXACL;
#endif
sb->s_flags |= SB_I_VERSION;
sb->s_iflags |= SB_I_CGROUPWB;
}
cleancache_init_fs(sb);
- sb->s_flags |= MS_ACTIVE;
+ sb->s_flags |= SB_ACTIVE;
return 0;
fail_close:
seq_puts(seq, ",flushoncommit");
if (btrfs_test_opt(info, DISCARD))
seq_puts(seq, ",discard");
- if (!(info->sb->s_flags & MS_POSIXACL))
+ if (!(info->sb->s_flags & SB_POSIXACL))
seq_puts(seq, ",noacl");
if (btrfs_test_opt(info, SPACE_CACHE))
seq_puts(seq, ",space_cache");
mnt = vfs_kern_mount(&btrfs_fs_type, flags, device_name, newargs);
if (PTR_ERR_OR_ZERO(mnt) == -EBUSY) {
- if (flags & MS_RDONLY) {
- mnt = vfs_kern_mount(&btrfs_fs_type, flags & ~MS_RDONLY,
+ if (flags & SB_RDONLY) {
+ mnt = vfs_kern_mount(&btrfs_fs_type, flags & ~SB_RDONLY,
device_name, newargs);
} else {
- mnt = vfs_kern_mount(&btrfs_fs_type, flags | MS_RDONLY,
+ mnt = vfs_kern_mount(&btrfs_fs_type, flags | SB_RDONLY,
device_name, newargs);
if (IS_ERR(mnt)) {
root = ERR_CAST(mnt);
u64 subvol_objectid = 0;
int error = 0;
- if (!(flags & MS_RDONLY))
+ if (!(flags & SB_RDONLY))
mode |= FMODE_WRITE;
error = btrfs_parse_early_options(data, mode, fs_type,
if (error)
goto error_fs_info;
- if (!(flags & MS_RDONLY) && fs_devices->rw_devices == 0) {
+ if (!(flags & SB_RDONLY) && fs_devices->rw_devices == 0) {
error = -EACCES;
goto error_close_devices;
}
bdev = fs_devices->latest_bdev;
- s = sget(fs_type, btrfs_test_super, btrfs_set_super, flags | MS_NOSEC,
+ s = sget(fs_type, btrfs_test_super, btrfs_set_super, flags | SB_NOSEC,
fs_info);
if (IS_ERR(s)) {
error = PTR_ERR(s);
if (s->s_root) {
btrfs_close_devices(fs_devices);
free_fs_info(fs_info);
- if ((flags ^ s->s_flags) & MS_RDONLY)
+ if ((flags ^ s->s_flags) & SB_RDONLY)
error = -EBUSY;
} else {
snprintf(s->s_id, sizeof(s->s_id), "%pg", bdev);
{
if (btrfs_raw_test_opt(old_opts, AUTO_DEFRAG) &&
(!btrfs_raw_test_opt(fs_info->mount_opt, AUTO_DEFRAG) ||
- (flags & MS_RDONLY))) {
+ (flags & SB_RDONLY))) {
/* wait for any defraggers to finish */
wait_event(fs_info->transaction_wait,
(atomic_read(&fs_info->defrag_running) == 0));
- if (flags & MS_RDONLY)
+ if (flags & SB_RDONLY)
sync_filesystem(fs_info->sb);
}
}
btrfs_resize_thread_pool(fs_info,
fs_info->thread_pool_size, old_thread_pool_size);
- if ((bool)(*flags & MS_RDONLY) == sb_rdonly(sb))
+ if ((bool)(*flags & SB_RDONLY) == sb_rdonly(sb))
goto out;
- if (*flags & MS_RDONLY) {
+ if (*flags & SB_RDONLY) {
/*
* this also happens on 'umount -rf' or on shutdown, when
* the filesystem is busy.
/* avoid complains from lockdep et al. */
up(&fs_info->uuid_tree_rescan_sem);
- sb->s_flags |= MS_RDONLY;
+ sb->s_flags |= SB_RDONLY;
/*
- * Setting MS_RDONLY will put the cleaner thread to
+ * Setting SB_RDONLY will put the cleaner thread to
* sleep at the next loop if it's already active.
* If it's already asleep, we'll leave unused block
* groups on disk until we're mounted read-write again
goto restore;
}
}
- sb->s_flags &= ~MS_RDONLY;
+ sb->s_flags &= ~SB_RDONLY;
set_bit(BTRFS_FS_OPEN, &fs_info->flags);
}
return 0;
restore:
- /* We've hit an error - don't reset MS_RDONLY */
+ /* We've hit an error - don't reset SB_RDONLY */
if (sb_rdonly(sb))
- old_flags |= MS_RDONLY;
+ old_flags |= SB_RDONLY;
sb->s_flags = old_flags;
fs_info->mount_opt = old_opts;
fs_info->compress_type = old_compress_type;
* |--- delalloc ---|
* |--- search ---|
*/
- set_extent_delalloc(&tmp, 0, sectorsize - 1, NULL);
+ set_extent_delalloc(&tmp, 0, sectorsize - 1, 0, NULL);
start = 0;
end = 0;
found = find_lock_delalloc_range(inode, &tmp, locked_page, &start,
test_msg("Couldn't find the locked page\n");
goto out_bits;
}
- set_extent_delalloc(&tmp, sectorsize, max_bytes - 1, NULL);
+ set_extent_delalloc(&tmp, sectorsize, max_bytes - 1, 0, NULL);
start = test_start;
end = 0;
found = find_lock_delalloc_range(inode, &tmp, locked_page, &start,
*
* We are re-using our test_start from above since it works out well.
*/
- set_extent_delalloc(&tmp, max_bytes, total_dirty - 1, NULL);
+ set_extent_delalloc(&tmp, max_bytes, total_dirty - 1, 0, NULL);
start = test_start;
end = 0;
found = find_lock_delalloc_range(inode, &tmp, locked_page, &start,
btrfs_test_inode_set_ops(inode);
/* [BTRFS_MAX_EXTENT_SIZE] */
- ret = btrfs_set_extent_delalloc(inode, 0, BTRFS_MAX_EXTENT_SIZE - 1,
+ ret = btrfs_set_extent_delalloc(inode, 0, BTRFS_MAX_EXTENT_SIZE - 1, 0,
NULL, 0);
if (ret) {
test_msg("btrfs_set_extent_delalloc returned %d\n", ret);
/* [BTRFS_MAX_EXTENT_SIZE][sectorsize] */
ret = btrfs_set_extent_delalloc(inode, BTRFS_MAX_EXTENT_SIZE,
BTRFS_MAX_EXTENT_SIZE + sectorsize - 1,
- NULL, 0);
+ 0, NULL, 0);
if (ret) {
test_msg("btrfs_set_extent_delalloc returned %d\n", ret);
goto out;
ret = btrfs_set_extent_delalloc(inode, BTRFS_MAX_EXTENT_SIZE >> 1,
(BTRFS_MAX_EXTENT_SIZE >> 1)
+ sectorsize - 1,
- NULL, 0);
+ 0, NULL, 0);
if (ret) {
test_msg("btrfs_set_extent_delalloc returned %d\n", ret);
goto out;
ret = btrfs_set_extent_delalloc(inode,
BTRFS_MAX_EXTENT_SIZE + 2 * sectorsize,
(BTRFS_MAX_EXTENT_SIZE << 1) + 3 * sectorsize - 1,
- NULL, 0);
+ 0, NULL, 0);
if (ret) {
test_msg("btrfs_set_extent_delalloc returned %d\n", ret);
goto out;
*/
ret = btrfs_set_extent_delalloc(inode,
BTRFS_MAX_EXTENT_SIZE + sectorsize,
- BTRFS_MAX_EXTENT_SIZE + 2 * sectorsize - 1, NULL, 0);
+ BTRFS_MAX_EXTENT_SIZE + 2 * sectorsize - 1, 0, NULL, 0);
if (ret) {
test_msg("btrfs_set_extent_delalloc returned %d\n", ret);
goto out;
*/
ret = btrfs_set_extent_delalloc(inode,
BTRFS_MAX_EXTENT_SIZE + sectorsize,
- BTRFS_MAX_EXTENT_SIZE + 2 * sectorsize - 1, NULL, 0);
+ BTRFS_MAX_EXTENT_SIZE + 2 * sectorsize - 1, 0, NULL, 0);
if (ret) {
test_msg("btrfs_set_extent_delalloc returned %d\n", ret);
goto out;
return ret;
}
-int btrfs_check_leaf(struct btrfs_root *root, struct extent_buffer *leaf)
+static int check_leaf(struct btrfs_root *root, struct extent_buffer *leaf,
+ bool check_item_data)
{
struct btrfs_fs_info *fs_info = root->fs_info;
/* No valid key type is 0, so all key should be larger than this key */
return -EUCLEAN;
}
- /* Check if the item size and content meet other criteria */
- ret = check_leaf_item(root, leaf, &key, slot);
- if (ret < 0)
- return ret;
+ if (check_item_data) {
+ /*
+ * Check if the item size and content meet other
+ * criteria
+ */
+ ret = check_leaf_item(root, leaf, &key, slot);
+ if (ret < 0)
+ return ret;
+ }
prev_key.objectid = key.objectid;
prev_key.type = key.type;
return 0;
}
+int btrfs_check_leaf_full(struct btrfs_root *root, struct extent_buffer *leaf)
+{
+ return check_leaf(root, leaf, true);
+}
+
+int btrfs_check_leaf_relaxed(struct btrfs_root *root,
+ struct extent_buffer *leaf)
+{
+ return check_leaf(root, leaf, false);
+}
+
int btrfs_check_node(struct btrfs_root *root, struct extent_buffer *node)
{
unsigned long nr = btrfs_header_nritems(node);
#include "ctree.h"
#include "extent_io.h"
-int btrfs_check_leaf(struct btrfs_root *root, struct extent_buffer *leaf);
+/*
+ * Comprehensive leaf checker.
+ * Will check not only the item pointers, but also every possible member
+ * in item data.
+ */
+int btrfs_check_leaf_full(struct btrfs_root *root, struct extent_buffer *leaf);
+
+/*
+ * Less strict leaf checker.
+ * Will only check item pointers, not reading item data.
+ */
+int btrfs_check_leaf_relaxed(struct btrfs_root *root,
+ struct extent_buffer *leaf);
int btrfs_check_node(struct btrfs_root *root, struct extent_buffer *node);
#endif
if (ordered_io_err) {
ctx->io_err = -EIO;
- return 0;
+ return ctx->io_err;
}
btrfs_init_map_token(&token);
struct btrfs_device, dev_list);
list_del(&device->dev_list);
rcu_string_free(device->name);
+ bio_put(device->flush_bio);
kfree(device);
}
kfree(fs_devices);
fs_devs->num_devices--;
list_del(&dev->dev_list);
rcu_string_free(dev->name);
+ bio_put(dev->flush_bio);
kfree(dev);
}
break;
name = rcu_string_strdup(path, GFP_NOFS);
if (!name) {
+ bio_put(device->flush_bio);
kfree(device);
return -ENOMEM;
}
name = rcu_string_strdup(orig_dev->name->str,
GFP_KERNEL);
if (!name) {
+ bio_put(device->flush_bio);
kfree(device);
goto error;
}
list_del_init(&device->dev_list);
fs_devices->num_devices--;
rcu_string_free(device->name);
+ bio_put(device->flush_bio);
kfree(device);
}
key.offset = device->devid;
ret = btrfs_search_slot(trans, root, &key, path, -1, 1);
- if (ret < 0)
- goto out;
-
- if (ret > 0) {
- ret = -ENOENT;
+ if (ret) {
+ if (ret > 0)
+ ret = -ENOENT;
+ btrfs_abort_transaction(trans, ret);
+ btrfs_end_transaction(trans);
goto out;
}
ret = btrfs_del_item(trans, root, path);
- if (ret)
- goto out;
+ if (ret) {
+ btrfs_abort_transaction(trans, ret);
+ btrfs_end_transaction(trans);
+ }
+
out:
btrfs_free_path(path);
- btrfs_commit_transaction(trans);
+ if (!ret)
+ ret = btrfs_commit_transaction(trans);
return ret;
}
fs_devices = srcdev->fs_devices;
list_del_rcu(&srcdev->dev_list);
- list_del_rcu(&srcdev->dev_alloc_list);
+ list_del(&srcdev->dev_alloc_list);
fs_devices->num_devices--;
if (srcdev->missing)
fs_devices->missing_devices--;
name = rcu_string_strdup(device_path, GFP_KERNEL);
if (!name) {
+ bio_put(device->flush_bio);
kfree(device);
ret = -ENOMEM;
goto error;
trans = btrfs_start_transaction(root, 0);
if (IS_ERR(trans)) {
rcu_string_free(device->name);
+ bio_put(device->flush_bio);
kfree(device);
ret = PTR_ERR(trans);
goto error;
set_blocksize(device->bdev, BTRFS_BDEV_BLOCKSIZE);
if (seeding_dev) {
- sb->s_flags &= ~MS_RDONLY;
+ sb->s_flags &= ~SB_RDONLY;
ret = btrfs_prepare_sprout(fs_info);
if (ret) {
btrfs_abort_transaction(trans, ret);
btrfs_sysfs_rm_device_link(fs_info->fs_devices, device);
error_trans:
if (seeding_dev)
- sb->s_flags |= MS_RDONLY;
+ sb->s_flags |= SB_RDONLY;
if (trans)
btrfs_end_transaction(trans);
rcu_string_free(device->name);
+ bio_put(device->flush_bio);
kfree(device);
error:
blkdev_put(bdev, FMODE_EXCL);
name = rcu_string_strdup(device_path, GFP_KERNEL);
if (!name) {
+ bio_put(device->flush_bio);
kfree(device);
ret = -ENOMEM;
goto error;
ret = find_next_devid(fs_info, &tmp);
if (ret) {
+ bio_put(dev->flush_bio);
kfree(dev);
return ERR_PTR(ret);
}
break;
#ifdef CONFIG_CEPH_FS_POSIX_ACL
case Opt_acl:
- fsopt->sb_flags |= MS_POSIXACL;
+ fsopt->sb_flags |= SB_POSIXACL;
break;
#endif
case Opt_noacl:
- fsopt->sb_flags &= ~MS_POSIXACL;
+ fsopt->sb_flags &= ~SB_POSIXACL;
break;
default:
BUG_ON(token);
seq_puts(m, ",nopoolperm");
#ifdef CONFIG_CEPH_FS_POSIX_ACL
- if (fsopt->sb_flags & MS_POSIXACL)
+ if (fsopt->sb_flags & SB_POSIXACL)
seq_puts(m, ",acl");
else
seq_puts(m, ",noacl");
dout("ceph_mount\n");
#ifdef CONFIG_CEPH_FS_POSIX_ACL
- flags |= MS_POSIXACL;
+ flags |= SB_POSIXACL;
#endif
err = parse_mount_options(&fsopt, &opt, flags, data, dev_name);
if (err < 0) {
#define CIFS_MOUNT_MULTIUSER 0x20000 /* multiuser mount */
#define CIFS_MOUNT_STRICT_IO 0x40000 /* strict cache mode */
#define CIFS_MOUNT_RWPIDFORWARD 0x80000 /* use pid forwarding for rw */
-#define CIFS_MOUNT_POSIXACL 0x100000 /* mirror of MS_POSIXACL in mnt_cifs_flags */
+#define CIFS_MOUNT_POSIXACL 0x100000 /* mirror of SB_POSIXACL in mnt_cifs_flags */
#define CIFS_MOUNT_CIFS_BACKUPUID 0x200000 /* backup intent bit for a user */
#define CIFS_MOUNT_CIFS_BACKUPGID 0x400000 /* backup intent bit for a group */
#define CIFS_MOUNT_MAP_SFM_CHR 0x800000 /* SFM/MAC mapping for illegal chars */
tcon = cifs_sb_master_tcon(cifs_sb);
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIXACL)
- sb->s_flags |= MS_POSIXACL;
+ sb->s_flags |= SB_POSIXACL;
if (tcon->ses->capabilities & tcon->ses->server->vals->cap_large_files)
sb->s_maxbytes = MAX_LFS_FILESIZE;
seq_puts(s, ",cifsacl");
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_DYNPERM)
seq_puts(s, ",dynperm");
- if (root->d_sb->s_flags & MS_POSIXACL)
+ if (root->d_sb->s_flags & SB_POSIXACL)
seq_puts(s, ",acl");
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MF_SYMLINKS)
seq_puts(s, ",mfsymlinks");
static int cifs_remount(struct super_block *sb, int *flags, char *data)
{
sync_filesystem(sb);
- *flags |= MS_NODIRATIME;
+ *flags |= SB_NODIRATIME;
return 0;
}
rc = cifs_mount(cifs_sb, volume_info);
if (rc) {
- if (!(flags & MS_SILENT))
+ if (!(flags & SB_SILENT))
cifs_dbg(VFS, "cifs_mount failed w/return code = %d\n",
rc);
root = ERR_PTR(rc);
mnt_data.flags = flags;
/* BB should we make this contingent on mount parm? */
- flags |= MS_NODIRATIME | MS_NOATIME;
+ flags |= SB_NODIRATIME | SB_NOATIME;
sb = sget(fs_type, cifs_match_super, cifs_set_super, flags, &mnt_data);
if (IS_ERR(sb)) {
goto out_super;
}
- sb->s_flags |= MS_ACTIVE;
+ sb->s_flags |= SB_ACTIVE;
}
root = cifs_get_root(volume_info, sb);
CIFS_MOUNT_MULTIUSER | CIFS_MOUNT_STRICT_IO | \
CIFS_MOUNT_CIFS_BACKUPUID | CIFS_MOUNT_CIFS_BACKUPGID)
-#define CIFS_MS_MASK (MS_RDONLY | MS_MANDLOCK | MS_NOEXEC | MS_NOSUID | \
- MS_NODEV | MS_SYNCHRONOUS)
+#define CIFS_MS_MASK (SB_RDONLY | SB_MANDLOCK | SB_NOEXEC | SB_NOSUID | \
+ SB_NODEV | SB_SYNCHRONOUS)
struct cifs_mnt_data {
struct cifs_sb_info *cifs_sb;
}
cifs_fattr_to_inode(inode, fattr);
- if (sb->s_flags & MS_NOATIME)
+ if (sb->s_flags & SB_NOATIME)
inode->i_flags |= S_NOATIME | S_NOCMTIME;
if (inode->i_state & I_NEW) {
inode->i_ino = hash;
#ifdef CONFIG_CIFS_POSIX
if (!value)
goto out;
- if (sb->s_flags & MS_POSIXACL)
+ if (sb->s_flags & SB_POSIXACL)
rc = CIFSSMBSetPosixACL(xid, pTcon, full_path,
value, (const int)size,
ACL_TYPE_ACCESS, cifs_sb->local_nls,
#ifdef CONFIG_CIFS_POSIX
if (!value)
goto out;
- if (sb->s_flags & MS_POSIXACL)
+ if (sb->s_flags & SB_POSIXACL)
rc = CIFSSMBSetPosixACL(xid, pTcon, full_path,
value, (const int)size,
ACL_TYPE_DEFAULT, cifs_sb->local_nls,
case XATTR_ACL_ACCESS:
#ifdef CONFIG_CIFS_POSIX
- if (sb->s_flags & MS_POSIXACL)
+ if (sb->s_flags & SB_POSIXACL)
rc = CIFSSMBGetPosixACL(xid, pTcon, full_path,
value, size, ACL_TYPE_ACCESS,
cifs_sb->local_nls,
case XATTR_ACL_DEFAULT:
#ifdef CONFIG_CIFS_POSIX
- if (sb->s_flags & MS_POSIXACL)
+ if (sb->s_flags & SB_POSIXACL)
rc = CIFSSMBGetPosixACL(xid, pTcon, full_path,
value, size, ACL_TYPE_DEFAULT,
cifs_sb->local_nls,
static int coda_remount(struct super_block *sb, int *flags, char *data)
{
sync_filesystem(sb);
- *flags |= MS_NOATIME;
+ *flags |= SB_NOATIME;
return 0;
}
mutex_unlock(&vc->vc_mutex);
sb->s_fs_info = vc;
- sb->s_flags |= MS_NOATIME;
+ sb->s_flags |= SB_NOATIME;
sb->s_blocksize = 4096; /* XXXXX what do we put here?? */
sb->s_blocksize_bits = 12;
sb->s_magic = CODA_SUPER_MAGIC;
static int cramfs_remount(struct super_block *sb, int *flags, char *data)
{
sync_filesystem(sb);
- *flags |= MS_RDONLY;
+ *flags |= SB_RDONLY;
return 0;
}
struct inode *root;
/* Set it all up.. */
- sb->s_flags |= MS_RDONLY;
+ sb->s_flags |= SB_RDONLY;
sb->s_op = &cramfs_ops;
root = get_cramfs_inode(sb, cramfs_root, 0);
if (IS_ERR(root))
if (pfn != pmd_pfn(*pmdp))
goto unlock_pmd;
- if (!pmd_dirty(*pmdp) && !pmd_write(*pmdp))
+ if (!pmd_dirty(*pmdp)
+ && !pmd_access_permitted(*pmdp, WRITE))
goto unlock_pmd;
flush_cache_page(vma, address, pfn);
* Set the POSIX ACL flag based on whether they're enabled in the lower
* mount.
*/
- s->s_flags = flags & ~MS_POSIXACL;
- s->s_flags |= path.dentry->d_sb->s_flags & MS_POSIXACL;
+ s->s_flags = flags & ~SB_POSIXACL;
+ s->s_flags |= path.dentry->d_sb->s_flags & SB_POSIXACL;
/**
* Force a read-only eCryptfs mount when:
* 2) The ecryptfs_encrypted_view mount option is specified
*/
if (sb_rdonly(path.dentry->d_sb) || mount_crypt_stat->flags & ECRYPTFS_ENCRYPTED_VIEW_ENABLED)
- s->s_flags |= MS_RDONLY;
+ s->s_flags |= SB_RDONLY;
s->s_maxbytes = path.dentry->d_sb->s_maxbytes;
s->s_blocksize = path.dentry->d_sb->s_blocksize;
ecryptfs_set_dentry_private(s->s_root, root_info);
root_info->lower_path = path;
- s->s_flags |= MS_ACTIVE;
+ s->s_flags |= SB_ACTIVE;
return dget(s->s_root);
out_free:
static int efs_remount(struct super_block *sb, int *flags, char *data)
{
sync_filesystem(sb);
- *flags |= MS_RDONLY;
+ *flags |= SB_RDONLY;
return 0;
}
#ifdef DEBUG
pr_info("forcing read-only mode\n");
#endif
- s->s_flags |= MS_RDONLY;
+ s->s_flags |= SB_RDONLY;
}
s->s_op = &efs_superblock_operations;
s->s_export_op = &efs_export_ops;
* avoid bad behavior from the prior rlimits. This has to
* happen before arch_pick_mmap_layout(), which examines
* RLIMIT_STACK, but after the point of no return to avoid
- * needing to clean up the change on failure.
+ * races from other threads changing the limits. This also
+ * must be protected from races with prlimit() calls.
*/
+ task_lock(current->group_leader);
if (current->signal->rlim[RLIMIT_STACK].rlim_cur > _STK_LIM)
current->signal->rlim[RLIMIT_STACK].rlim_cur = _STK_LIM;
+ if (current->signal->rlim[RLIMIT_STACK].rlim_max > _STK_LIM)
+ current->signal->rlim[RLIMIT_STACK].rlim_max = _STK_LIM;
+ task_unlock(current->group_leader);
}
arch_pick_mmap_layout(current->mm);
}
mark_buffer_dirty(bitmap_bh);
- if (sb->s_flags & MS_SYNCHRONOUS)
+ if (sb->s_flags & SB_SYNCHRONOUS)
sync_dirty_buffer(bitmap_bh);
group_adjust_blocks(sb, block_group, desc, bh2, group_freed);
percpu_counter_sub(&sbi->s_freeblocks_counter, num);
mark_buffer_dirty(bitmap_bh);
- if (sb->s_flags & MS_SYNCHRONOUS)
+ if (sb->s_flags & SB_SYNCHRONOUS)
sync_dirty_buffer(bitmap_bh);
*errp = 0;
else
ext2_release_inode(sb, block_group, is_directory);
mark_buffer_dirty(bitmap_bh);
- if (sb->s_flags & MS_SYNCHRONOUS)
+ if (sb->s_flags & SB_SYNCHRONOUS)
sync_dirty_buffer(bitmap_bh);
brelse(bitmap_bh);
goto fail;
got:
mark_buffer_dirty(bitmap_bh);
- if (sb->s_flags & MS_SYNCHRONOUS)
+ if (sb->s_flags & SB_SYNCHRONOUS)
sync_dirty_buffer(bitmap_bh);
brelse(bitmap_bh);
if (test_opt(sb, ERRORS_RO)) {
ext2_msg(sb, KERN_CRIT,
"error: remounting filesystem read-only");
- sb->s_flags |= MS_RDONLY;
+ sb->s_flags |= SB_RDONLY;
}
}
ext2_msg(sb, KERN_ERR,
"error: revision level too high, "
"forcing read-only mode");
- res = MS_RDONLY;
+ res = SB_RDONLY;
}
if (read_only)
return res;
sbi->s_resuid = opts.s_resuid;
sbi->s_resgid = opts.s_resgid;
- sb->s_flags = (sb->s_flags & ~MS_POSIXACL) |
+ sb->s_flags = (sb->s_flags & ~SB_POSIXACL) |
((EXT2_SB(sb)->s_mount_opt & EXT2_MOUNT_POSIX_ACL) ?
- MS_POSIXACL : 0);
+ SB_POSIXACL : 0);
sb->s_iflags |= SB_I_CGROUPWB;
if (le32_to_cpu(es->s_rev_level) == EXT2_GOOD_OLD_REV &&
ext2_msg(sb, KERN_WARNING,
"warning: mounting ext3 filesystem as ext2");
if (ext2_setup_super (sb, es, sb_rdonly(sb)))
- sb->s_flags |= MS_RDONLY;
+ sb->s_flags |= SB_RDONLY;
ext2_write_super(sb);
return 0;
"dax flag with busy inodes while remounting");
new_opts.s_mount_opt ^= EXT2_MOUNT_DAX;
}
- if ((bool)(*flags & MS_RDONLY) == sb_rdonly(sb))
+ if ((bool)(*flags & SB_RDONLY) == sb_rdonly(sb))
goto out_set;
- if (*flags & MS_RDONLY) {
+ if (*flags & SB_RDONLY) {
if (le16_to_cpu(es->s_state) & EXT2_VALID_FS ||
!(sbi->s_mount_state & EXT2_VALID_FS))
goto out_set;
*/
sbi->s_mount_state = le16_to_cpu(es->s_state);
if (!ext2_setup_super (sb, es, 0))
- sb->s_flags &= ~MS_RDONLY;
+ sb->s_flags &= ~SB_RDONLY;
spin_unlock(&sbi->s_lock);
ext2_write_super(sb);
sbi->s_mount_opt = new_opts.s_mount_opt;
sbi->s_resuid = new_opts.s_resuid;
sbi->s_resgid = new_opts.s_resgid;
- sb->s_flags = (sb->s_flags & ~MS_POSIXACL) |
- ((sbi->s_mount_opt & EXT2_MOUNT_POSIX_ACL) ? MS_POSIXACL : 0);
+ sb->s_flags = (sb->s_flags & ~SB_POSIXACL) |
+ ((sbi->s_mount_opt & EXT2_MOUNT_POSIX_ACL) ? SB_POSIXACL : 0);
spin_unlock(&sbi->s_lock);
return 0;
* If the filesystem has aborted, it is read-only, so return
* right away instead of dumping stack traces later on that
* will obscure the real source of the problem. We test
- * EXT4_MF_FS_ABORTED instead of sb->s_flag's MS_RDONLY because
+ * EXT4_MF_FS_ABORTED instead of sb->s_flag's SB_RDONLY because
* the latter could be true if the filesystem is mounted
* read-only, and in that case, ext4_writepages should
* *never* be called, so if that ever happens, we would want
ext4_inode_csum_set(inode, raw_inode, ei);
spin_unlock(&ei->i_raw_lock);
- if (inode->i_sb->s_flags & MS_LAZYTIME)
+ if (inode->i_sb->s_flags & SB_LAZYTIME)
ext4_update_other_inodes_time(inode->i_sb, inode->i_ino,
bh->b_data);
* before ->s_flags update
*/
smp_wmb();
- sb->s_flags |= MS_RDONLY;
+ sb->s_flags |= SB_RDONLY;
}
if (test_opt(sb, ERRORS_PANIC)) {
if (EXT4_SB(sb)->s_journal &&
* before ->s_flags update
*/
smp_wmb();
- sb->s_flags |= MS_RDONLY;
+ sb->s_flags |= SB_RDONLY;
if (EXT4_SB(sb)->s_journal)
jbd2_journal_abort(EXT4_SB(sb)->s_journal, -EIO);
save_error_info(sb, function, line);
sb->s_flags |= SB_I_VERSION;
return 1;
case Opt_lazytime:
- sb->s_flags |= MS_LAZYTIME;
+ sb->s_flags |= SB_LAZYTIME;
return 1;
case Opt_nolazytime:
- sb->s_flags &= ~MS_LAZYTIME;
+ sb->s_flags &= ~SB_LAZYTIME;
return 1;
}
if (le32_to_cpu(es->s_rev_level) > EXT4_MAX_SUPP_REV) {
ext4_msg(sb, KERN_ERR, "revision level too high, "
"forcing read-only mode");
- res = MS_RDONLY;
+ res = SB_RDONLY;
}
if (read_only)
goto done;
if (EXT4_SB(sb)->s_mount_state & EXT4_ERROR_FS) {
/* don't clear list on RO mount w/ errors */
- if (es->s_last_orphan && !(s_flags & MS_RDONLY)) {
+ if (es->s_last_orphan && !(s_flags & SB_RDONLY)) {
ext4_msg(sb, KERN_INFO, "Errors on filesystem, "
"clearing orphan list.\n");
es->s_last_orphan = 0;
return;
}
- if (s_flags & MS_RDONLY) {
+ if (s_flags & SB_RDONLY) {
ext4_msg(sb, KERN_INFO, "orphan cleanup on readonly fs");
- sb->s_flags &= ~MS_RDONLY;
+ sb->s_flags &= ~SB_RDONLY;
}
#ifdef CONFIG_QUOTA
/* Needed for iput() to work correctly and not trash data */
- sb->s_flags |= MS_ACTIVE;
+ sb->s_flags |= SB_ACTIVE;
/*
* Turn on quotas which were not enabled for read-only mounts if
* filesystem has quota feature, so that they are updated correctly.
*/
- if (ext4_has_feature_quota(sb) && (s_flags & MS_RDONLY)) {
+ if (ext4_has_feature_quota(sb) && (s_flags & SB_RDONLY)) {
int ret = ext4_enable_quotas(sb);
if (!ret)
}
}
#endif
- sb->s_flags = s_flags; /* Restore MS_RDONLY status */
+ sb->s_flags = s_flags; /* Restore SB_RDONLY status */
}
/*
if (ext4_has_feature_readonly(sb)) {
ext4_msg(sb, KERN_INFO, "filesystem is read-only");
- sb->s_flags |= MS_RDONLY;
+ sb->s_flags |= SB_RDONLY;
return 1;
}
sb->s_iflags |= SB_I_CGROUPWB;
}
- sb->s_flags = (sb->s_flags & ~MS_POSIXACL) |
- (test_opt(sb, POSIX_ACL) ? MS_POSIXACL : 0);
+ sb->s_flags = (sb->s_flags & ~SB_POSIXACL) |
+ (test_opt(sb, POSIX_ACL) ? SB_POSIXACL : 0);
if (le32_to_cpu(es->s_rev_level) == EXT4_GOOD_OLD_REV &&
(ext4_has_compat_features(sb) ||
}
if (ext4_setup_super(sb, es, sb_rdonly(sb)))
- sb->s_flags |= MS_RDONLY;
+ sb->s_flags |= SB_RDONLY;
/* determine the minimum size of new large inodes, if present */
if (sbi->s_inode_size > EXT4_GOOD_OLD_INODE_SIZE &&
* the clock is set in the future, and this will cause e2fsck
* to complain and force a full file system check.
*/
- if (!(sb->s_flags & MS_RDONLY))
+ if (!(sb->s_flags & SB_RDONLY))
es->s_wtime = cpu_to_le32(get_seconds());
if (sb->s_bdev->bd_part)
es->s_kbytes_written =
if (sbi->s_mount_flags & EXT4_MF_FS_ABORTED)
ext4_abort(sb, "Abort forced by user");
- sb->s_flags = (sb->s_flags & ~MS_POSIXACL) |
- (test_opt(sb, POSIX_ACL) ? MS_POSIXACL : 0);
+ sb->s_flags = (sb->s_flags & ~SB_POSIXACL) |
+ (test_opt(sb, POSIX_ACL) ? SB_POSIXACL : 0);
es = sbi->s_es;
set_task_ioprio(sbi->s_journal->j_task, journal_ioprio);
}
- if (*flags & MS_LAZYTIME)
- sb->s_flags |= MS_LAZYTIME;
+ if (*flags & SB_LAZYTIME)
+ sb->s_flags |= SB_LAZYTIME;
- if ((bool)(*flags & MS_RDONLY) != sb_rdonly(sb)) {
+ if ((bool)(*flags & SB_RDONLY) != sb_rdonly(sb)) {
if (sbi->s_mount_flags & EXT4_MF_FS_ABORTED) {
err = -EROFS;
goto restore_opts;
}
- if (*flags & MS_RDONLY) {
+ if (*flags & SB_RDONLY) {
err = sync_filesystem(sb);
if (err < 0)
goto restore_opts;
* First of all, the unconditional stuff we have to do
* to disable replay of the journal when we next remount
*/
- sb->s_flags |= MS_RDONLY;
+ sb->s_flags |= SB_RDONLY;
/*
* OK, test if we are remounting a valid rw partition
ext4_clear_journal_err(sb, es);
sbi->s_mount_state = le16_to_cpu(es->s_state);
if (!ext4_setup_super(sb, es, 0))
- sb->s_flags &= ~MS_RDONLY;
+ sb->s_flags &= ~SB_RDONLY;
if (ext4_has_feature_mmp(sb))
if (ext4_multi_mount_protect(sb,
le64_to_cpu(es->s_mmp_block))) {
}
ext4_setup_system_zone(sb);
- if (sbi->s_journal == NULL && !(old_sb_flags & MS_RDONLY))
+ if (sbi->s_journal == NULL && !(old_sb_flags & SB_RDONLY))
ext4_commit_super(sb, 1);
#ifdef CONFIG_QUOTA
}
#endif
- *flags = (*flags & ~MS_LAZYTIME) | (sb->s_flags & MS_LAZYTIME);
+ *flags = (*flags & ~SB_LAZYTIME) | (sb->s_flags & SB_LAZYTIME);
ext4_msg(sb, KERN_INFO, "re-mounted. Opts: %s", orig_data);
kfree(orig_data);
return 0;
if (!is_set_ckpt_flags(sbi, CP_ORPHAN_PRESENT_FLAG))
return 0;
- if (s_flags & MS_RDONLY) {
+ if (s_flags & SB_RDONLY) {
f2fs_msg(sbi->sb, KERN_INFO, "orphan cleanup on readonly fs");
- sbi->sb->s_flags &= ~MS_RDONLY;
+ sbi->sb->s_flags &= ~SB_RDONLY;
}
#ifdef CONFIG_QUOTA
/* Needed for iput() to work correctly and not trash data */
- sbi->sb->s_flags |= MS_ACTIVE;
+ sbi->sb->s_flags |= SB_ACTIVE;
/* Turn on quotas so that they are updated correctly */
- quota_enabled = f2fs_enable_quota_files(sbi, s_flags & MS_RDONLY);
+ quota_enabled = f2fs_enable_quota_files(sbi, s_flags & SB_RDONLY);
#endif
start_blk = __start_cp_addr(sbi) + 1 + __cp_payload(sbi);
if (quota_enabled)
f2fs_quota_off_umount(sbi->sb);
#endif
- sbi->sb->s_flags = s_flags; /* Restore MS_RDONLY status */
+ sbi->sb->s_flags = s_flags; /* Restore SB_RDONLY status */
return err;
}
static inline int f2fs_readonly(struct super_block *sb)
{
- return sb->s_flags & MS_RDONLY;
+ return sb->s_flags & SB_RDONLY;
}
static inline bool f2fs_cp_error(struct f2fs_sb_info *sbi)
cpc.reason = __get_cp_reason(sbi);
gc_more:
- if (unlikely(!(sbi->sb->s_flags & MS_ACTIVE))) {
+ if (unlikely(!(sbi->sb->s_flags & SB_ACTIVE))) {
ret = -EINVAL;
goto stop;
}
int quota_enabled;
#endif
- if (s_flags & MS_RDONLY) {
+ if (s_flags & SB_RDONLY) {
f2fs_msg(sbi->sb, KERN_INFO, "orphan cleanup on readonly fs");
- sbi->sb->s_flags &= ~MS_RDONLY;
+ sbi->sb->s_flags &= ~SB_RDONLY;
}
#ifdef CONFIG_QUOTA
/* Needed for iput() to work correctly and not trash data */
- sbi->sb->s_flags |= MS_ACTIVE;
+ sbi->sb->s_flags |= SB_ACTIVE;
/* Turn on quotas so that they are updated correctly */
- quota_enabled = f2fs_enable_quota_files(sbi, s_flags & MS_RDONLY);
+ quota_enabled = f2fs_enable_quota_files(sbi, s_flags & SB_RDONLY);
#endif
fsync_entry_slab = f2fs_kmem_cache_create("f2fs_fsync_inode_entry",
if (quota_enabled)
f2fs_quota_off_umount(sbi->sb);
#endif
- sbi->sb->s_flags = s_flags; /* Restore MS_RDONLY status */
+ sbi->sb->s_flags = s_flags; /* Restore SB_RDONLY status */
return ret ? ret: err;
}
#endif
break;
case Opt_lazytime:
- sb->s_flags |= MS_LAZYTIME;
+ sb->s_flags |= SB_LAZYTIME;
break;
case Opt_nolazytime:
- sb->s_flags &= ~MS_LAZYTIME;
+ sb->s_flags &= ~SB_LAZYTIME;
break;
#ifdef CONFIG_QUOTA
case Opt_quota:
set_opt(sbi, INLINE_DENTRY);
set_opt(sbi, EXTENT_CACHE);
set_opt(sbi, NOHEAP);
- sbi->sb->s_flags |= MS_LAZYTIME;
+ sbi->sb->s_flags |= SB_LAZYTIME;
set_opt(sbi, FLUSH_MERGE);
if (f2fs_sb_mounted_blkzoned(sbi->sb)) {
set_opt_mode(sbi, F2FS_MOUNT_LFS);
#endif
/* recover superblocks we couldn't write due to previous RO mount */
- if (!(*flags & MS_RDONLY) && is_sbi_flag_set(sbi, SBI_NEED_SB_WRITE)) {
+ if (!(*flags & SB_RDONLY) && is_sbi_flag_set(sbi, SBI_NEED_SB_WRITE)) {
err = f2fs_commit_super(sbi, false);
f2fs_msg(sb, KERN_INFO,
"Try to recover all the superblocks, ret: %d", err);
* Previous and new state of filesystem is RO,
* so skip checking GC and FLUSH_MERGE conditions.
*/
- if (f2fs_readonly(sb) && (*flags & MS_RDONLY))
+ if (f2fs_readonly(sb) && (*flags & SB_RDONLY))
goto skip;
#ifdef CONFIG_QUOTA
- if (!f2fs_readonly(sb) && (*flags & MS_RDONLY)) {
+ if (!f2fs_readonly(sb) && (*flags & SB_RDONLY)) {
err = dquot_suspend(sb, -1);
if (err < 0)
goto restore_opts;
} else {
/* dquot_resume needs RW */
- sb->s_flags &= ~MS_RDONLY;
+ sb->s_flags &= ~SB_RDONLY;
if (sb_any_quota_suspended(sb)) {
dquot_resume(sb, -1);
} else if (f2fs_sb_has_quota_ino(sb)) {
* or if background_gc = off is passed in mount
* option. Also sync the filesystem.
*/
- if ((*flags & MS_RDONLY) || !test_opt(sbi, BG_GC)) {
+ if ((*flags & SB_RDONLY) || !test_opt(sbi, BG_GC)) {
if (sbi->gc_thread) {
stop_gc_thread(sbi);
need_restart_gc = true;
need_stop_gc = true;
}
- if (*flags & MS_RDONLY) {
+ if (*flags & SB_RDONLY) {
writeback_inodes_sb(sb, WB_REASON_SYNC);
sync_inodes_sb(sb);
* We stop issue flush thread if FS is mounted as RO
* or if flush_merge is not passed in mount option.
*/
- if ((*flags & MS_RDONLY) || !test_opt(sbi, FLUSH_MERGE)) {
+ if ((*flags & SB_RDONLY) || !test_opt(sbi, FLUSH_MERGE)) {
clear_opt(sbi, FLUSH_MERGE);
destroy_flush_cmd_control(sbi, false);
} else {
kfree(s_qf_names[i]);
#endif
/* Update the POSIXACL Flag */
- sb->s_flags = (sb->s_flags & ~MS_POSIXACL) |
- (test_opt(sbi, POSIX_ACL) ? MS_POSIXACL : 0);
+ sb->s_flags = (sb->s_flags & ~SB_POSIXACL) |
+ (test_opt(sbi, POSIX_ACL) ? SB_POSIXACL : 0);
return 0;
restore_gc:
sb->s_export_op = &f2fs_export_ops;
sb->s_magic = F2FS_SUPER_MAGIC;
sb->s_time_gran = 1;
- sb->s_flags = (sb->s_flags & ~MS_POSIXACL) |
- (test_opt(sbi, POSIX_ACL) ? MS_POSIXACL : 0);
+ sb->s_flags = (sb->s_flags & ~SB_POSIXACL) |
+ (test_opt(sbi, POSIX_ACL) ? SB_POSIXACL : 0);
memcpy(&sb->s_uuid, raw_super->uuid, sizeof(raw_super->uuid));
/* init f2fs-specific super block info */
memcpy(c_bh->b_data, bhs[n]->b_data, sb->s_blocksize);
set_buffer_uptodate(c_bh);
mark_buffer_dirty_inode(c_bh, sbi->fat_inode);
- if (sb->s_flags & MS_SYNCHRONOUS)
+ if (sb->s_flags & SB_SYNCHRONOUS)
err = sync_dirty_buffer(c_bh);
brelse(c_bh);
if (err)
}
if (nr_bhs + fatent.nr_bhs > MAX_BUF_PER_PAGE) {
- if (sb->s_flags & MS_SYNCHRONOUS) {
+ if (sb->s_flags & SB_SYNCHRONOUS) {
err = fat_sync_bhs(bhs, nr_bhs);
if (err)
goto error;
fat_collect_bhs(bhs, &nr_bhs, &fatent);
} while (cluster != FAT_ENT_EOF);
- if (sb->s_flags & MS_SYNCHRONOUS) {
+ if (sb->s_flags & SB_SYNCHRONOUS) {
err = fat_sync_bhs(bhs, nr_bhs);
if (err)
goto error;
static int fat_remount(struct super_block *sb, int *flags, char *data)
{
- int new_rdonly;
+ bool new_rdonly;
struct msdos_sb_info *sbi = MSDOS_SB(sb);
- *flags |= MS_NODIRATIME | (sbi->options.isvfat ? 0 : MS_NOATIME);
+ *flags |= SB_NODIRATIME | (sbi->options.isvfat ? 0 : SB_NOATIME);
sync_filesystem(sb);
/* make sure we update state on remount. */
- new_rdonly = *flags & MS_RDONLY;
+ new_rdonly = *flags & SB_RDONLY;
if (new_rdonly != sb_rdonly(sb)) {
if (new_rdonly)
fat_set_state(sb, 0, 0);
if (opts->unicode_xlate)
opts->utf8 = 0;
if (opts->nfs == FAT_NFS_NOSTALE_RO) {
- sb->s_flags |= MS_RDONLY;
+ sb->s_flags |= SB_RDONLY;
sb->s_export_op = &fat_export_ops_nostale;
}
return -ENOMEM;
sb->s_fs_info = sbi;
- sb->s_flags |= MS_NODIRATIME;
+ sb->s_flags |= SB_NODIRATIME;
sb->s_magic = MSDOS_SUPER_MAGIC;
sb->s_op = &fat_sops;
sb->s_export_op = &fat_export_ops;
if (opts->errors == FAT_ERRORS_PANIC)
panic("FAT-fs (%s): fs panic from previous error\n", sb->s_id);
else if (opts->errors == FAT_ERRORS_RO && !sb_rdonly(sb)) {
- sb->s_flags |= MS_RDONLY;
+ sb->s_flags |= SB_RDONLY;
fat_msg(sb, KERN_ERR, "Filesystem has been set read-only");
}
}
{
MSDOS_SB(sb)->dir_ops = &msdos_dir_inode_operations;
sb->s_d_op = &msdos_dentry_operations;
- sb->s_flags |= MS_NOATIME;
+ sb->s_flags |= SB_NOATIME;
}
static int msdos_fill_super(struct super_block *sb, void *data, int silent)
static int vxfs_remount(struct super_block *sb, int *flags, char *data)
{
sync_filesystem(sb);
- *flags |= MS_RDONLY;
+ *flags |= SB_RDONLY;
return 0;
}
int ret = -EINVAL;
u32 j;
- sbp->s_flags |= MS_RDONLY;
+ sbp->s_flags |= SB_RDONLY;
infp = kzalloc(sizeof(*infp), GFP_KERNEL);
if (!infp) {
/* while holding I_WB_SWITCH, no one else can update the association */
spin_lock(&inode->i_lock);
- if (!(inode->i_sb->s_flags & MS_ACTIVE) ||
+ if (!(inode->i_sb->s_flags & SB_ACTIVE) ||
inode->i_state & (I_WB_SWITCH | I_FREEING) ||
inode_to_wb(inode) == isw->new_wb) {
spin_unlock(&inode->i_lock);
{
truncate_inode_pages_final(&inode->i_data);
clear_inode(inode);
- if (inode->i_sb->s_flags & MS_ACTIVE) {
+ if (inode->i_sb->s_flags & SB_ACTIVE) {
struct fuse_conn *fc = get_fuse_conn(inode);
struct fuse_inode *fi = get_fuse_inode(inode);
fuse_queue_forget(fc, fi->forget, fi->nodeid, fi->nlookup);
static int fuse_remount_fs(struct super_block *sb, int *flags, char *data)
{
sync_filesystem(sb);
- if (*flags & MS_MANDLOCK)
+ if (*flags & SB_MANDLOCK)
return -EINVAL;
return 0;
int is_bdev = sb->s_bdev != NULL;
err = -EINVAL;
- if (sb->s_flags & MS_MANDLOCK)
+ if (sb->s_flags & SB_MANDLOCK)
goto err;
- sb->s_flags &= ~(MS_NOSEC | SB_I_VERSION);
+ sb->s_flags &= ~(SB_NOSEC | SB_I_VERSION);
if (!parse_fuse_opt(data, &d, is_bdev))
goto err;
goto err_dev_free;
/* Handle umasking inside the fuse code */
- if (sb->s_flags & MS_POSIXACL)
+ if (sb->s_flags & SB_POSIXACL)
fc->dont_mask = 1;
- sb->s_flags |= MS_POSIXACL;
+ sb->s_flags |= SB_POSIXACL;
fc->default_permissions = d.default_permissions;
fc->allow_other = d.allow_other;
sdp->sd_args = *args;
if (sdp->sd_args.ar_spectator) {
- sb->s_flags |= MS_RDONLY;
+ sb->s_flags |= SB_RDONLY;
set_bit(SDF_RORECOVERY, &sdp->sd_flags);
}
if (sdp->sd_args.ar_posix_acl)
- sb->s_flags |= MS_POSIXACL;
+ sb->s_flags |= SB_POSIXACL;
if (sdp->sd_args.ar_nobarrier)
set_bit(SDF_NOBARRIERS, &sdp->sd_flags);
- sb->s_flags |= MS_NOSEC;
+ sb->s_flags |= SB_NOSEC;
sb->s_magic = GFS2_MAGIC;
sb->s_op = &gfs2_super_ops;
sb->s_d_op = &gfs2_dops;
struct gfs2_args args;
struct gfs2_sbd *sdp;
- if (!(flags & MS_RDONLY))
+ if (!(flags & SB_RDONLY))
mode |= FMODE_WRITE;
bdev = blkdev_get_by_path(dev_name, mode, fs_type);
if (s->s_root) {
error = -EBUSY;
- if ((flags ^ s->s_flags) & MS_RDONLY)
+ if ((flags ^ s->s_flags) & SB_RDONLY)
goto error_super;
} else {
snprintf(s->s_id, sizeof(s->s_id), "%pg", bdev);
sb_set_blocksize(s, block_size(bdev));
- error = fill_super(s, &args, flags & MS_SILENT ? 1 : 0);
+ error = fill_super(s, &args, flags & SB_SILENT ? 1 : 0);
if (error)
goto error_super;
- s->s_flags |= MS_ACTIVE;
+ s->s_flags |= SB_ACTIVE;
bdev->bd_super = s;
}
pr_warn("gfs2 mount does not exist\n");
return ERR_CAST(s);
}
- if ((flags ^ s->s_flags) & MS_RDONLY) {
+ if ((flags ^ s->s_flags) & SB_RDONLY) {
deactivate_locked_super(s);
return ERR_PTR(-EBUSY);
}
return -EINVAL;
if (sdp->sd_args.ar_spectator)
- *flags |= MS_RDONLY;
+ *flags |= SB_RDONLY;
- if ((sb->s_flags ^ *flags) & MS_RDONLY) {
- if (*flags & MS_RDONLY)
+ if ((sb->s_flags ^ *flags) & SB_RDONLY) {
+ if (*flags & SB_RDONLY)
error = gfs2_make_fs_ro(sdp);
else
error = gfs2_make_fs_rw(sdp);
sdp->sd_args = args;
if (sdp->sd_args.ar_posix_acl)
- sb->s_flags |= MS_POSIXACL;
+ sb->s_flags |= SB_POSIXACL;
else
- sb->s_flags &= ~MS_POSIXACL;
+ sb->s_flags &= ~SB_POSIXACL;
if (sdp->sd_args.ar_nobarrier)
set_bit(SDF_NOBARRIERS, &sdp->sd_flags);
else
kfree(tr);
up_read(&sdp->sd_log_flush_lock);
- if (sdp->sd_vfs->s_flags & MS_SYNCHRONOUS)
+ if (sdp->sd_vfs->s_flags & SB_SYNCHRONOUS)
gfs2_log_flush(sdp, NULL, NORMAL_FLUSH);
if (alloced)
sb_end_intwrite(sdp->sd_vfs);
attrib = mdb->drAtrb;
if (!(attrib & cpu_to_be16(HFS_SB_ATTRIB_UNMNT))) {
pr_warn("filesystem was not cleanly unmounted, running fsck.hfs is recommended. mounting read-only.\n");
- sb->s_flags |= MS_RDONLY;
+ sb->s_flags |= SB_RDONLY;
}
if ((attrib & cpu_to_be16(HFS_SB_ATTRIB_SLOCK))) {
pr_warn("filesystem is marked locked, mounting read-only.\n");
- sb->s_flags |= MS_RDONLY;
+ sb->s_flags |= SB_RDONLY;
}
if (!sb_rdonly(sb)) {
/* Mark the volume uncleanly unmounted in case we crash */
static int hfs_remount(struct super_block *sb, int *flags, char *data)
{
sync_filesystem(sb);
- *flags |= MS_NODIRATIME;
- if ((bool)(*flags & MS_RDONLY) == sb_rdonly(sb))
+ *flags |= SB_NODIRATIME;
+ if ((bool)(*flags & SB_RDONLY) == sb_rdonly(sb))
return 0;
- if (!(*flags & MS_RDONLY)) {
+ if (!(*flags & SB_RDONLY)) {
if (!(HFS_SB(sb)->mdb->drAtrb & cpu_to_be16(HFS_SB_ATTRIB_UNMNT))) {
pr_warn("filesystem was not cleanly unmounted, running fsck.hfs is recommended. leaving read-only.\n");
- sb->s_flags |= MS_RDONLY;
- *flags |= MS_RDONLY;
+ sb->s_flags |= SB_RDONLY;
+ *flags |= SB_RDONLY;
} else if (HFS_SB(sb)->mdb->drAtrb & cpu_to_be16(HFS_SB_ATTRIB_SLOCK)) {
pr_warn("filesystem is marked locked, leaving read-only.\n");
- sb->s_flags |= MS_RDONLY;
- *flags |= MS_RDONLY;
+ sb->s_flags |= SB_RDONLY;
+ *flags |= SB_RDONLY;
}
}
return 0;
sb->s_op = &hfs_super_operations;
sb->s_xattr = hfs_xattr_handlers;
- sb->s_flags |= MS_NODIRATIME;
+ sb->s_flags |= SB_NODIRATIME;
mutex_init(&sbi->bitmap_lock);
res = hfs_mdb_get(sb);
static int hfsplus_remount(struct super_block *sb, int *flags, char *data)
{
sync_filesystem(sb);
- if ((bool)(*flags & MS_RDONLY) == sb_rdonly(sb))
+ if ((bool)(*flags & SB_RDONLY) == sb_rdonly(sb))
return 0;
- if (!(*flags & MS_RDONLY)) {
+ if (!(*flags & SB_RDONLY)) {
struct hfsplus_vh *vhdr = HFSPLUS_SB(sb)->s_vhdr;
int force = 0;
if (!(vhdr->attributes & cpu_to_be32(HFSPLUS_VOL_UNMNT))) {
pr_warn("filesystem was not cleanly unmounted, running fsck.hfsplus is recommended. leaving read-only.\n");
- sb->s_flags |= MS_RDONLY;
- *flags |= MS_RDONLY;
+ sb->s_flags |= SB_RDONLY;
+ *flags |= SB_RDONLY;
} else if (force) {
/* nothing */
} else if (vhdr->attributes &
cpu_to_be32(HFSPLUS_VOL_SOFTLOCK)) {
pr_warn("filesystem is marked locked, leaving read-only.\n");
- sb->s_flags |= MS_RDONLY;
- *flags |= MS_RDONLY;
+ sb->s_flags |= SB_RDONLY;
+ *flags |= SB_RDONLY;
} else if (vhdr->attributes &
cpu_to_be32(HFSPLUS_VOL_JOURNALED)) {
pr_warn("filesystem is marked journaled, leaving read-only.\n");
- sb->s_flags |= MS_RDONLY;
- *flags |= MS_RDONLY;
+ sb->s_flags |= SB_RDONLY;
+ *flags |= SB_RDONLY;
}
}
return 0;
if (!(vhdr->attributes & cpu_to_be32(HFSPLUS_VOL_UNMNT))) {
pr_warn("Filesystem was not cleanly unmounted, running fsck.hfsplus is recommended. mounting read-only.\n");
- sb->s_flags |= MS_RDONLY;
+ sb->s_flags |= SB_RDONLY;
} else if (test_and_clear_bit(HFSPLUS_SB_FORCE, &sbi->flags)) {
/* nothing */
} else if (vhdr->attributes & cpu_to_be32(HFSPLUS_VOL_SOFTLOCK)) {
pr_warn("Filesystem is marked locked, mounting read-only.\n");
- sb->s_flags |= MS_RDONLY;
+ sb->s_flags |= SB_RDONLY;
} else if ((vhdr->attributes & cpu_to_be32(HFSPLUS_VOL_JOURNALED)) &&
!sb_rdonly(sb)) {
pr_warn("write access to a journaled filesystem is not supported, use the force option at your own risk, mounting read-only.\n");
- sb->s_flags |= MS_RDONLY;
+ sb->s_flags |= SB_RDONLY;
}
err = -EINVAL;
goto bail;
}
if (((31 + de->namelen + de->down*4 + 3) & ~3) != le16_to_cpu(de->length)) {
- if (((31 + de->namelen + de->down*4 + 3) & ~3) < le16_to_cpu(de->length) && s->s_flags & MS_RDONLY) goto ok;
+ if (((31 + de->namelen + de->down*4 + 3) & ~3) < le16_to_cpu(de->length) && s->s_flags & SB_RDONLY) goto ok;
hpfs_error(s, "namelen does not match dirent size in dnode %08x, dirent %03x, last %03x", secno, p, pp);
goto bail;
}
else {
pr_cont("; remounting read-only\n");
mark_dirty(s, 0);
- s->s_flags |= MS_RDONLY;
+ s->s_flags |= SB_RDONLY;
}
} else if (sb_rdonly(s))
pr_cont("; going on - but anything won't be destroyed because it's read-only\n");
sync_filesystem(s);
- *flags |= MS_NOATIME;
+ *flags |= SB_NOATIME;
hpfs_lock(s);
uid = sbi->sb_uid; gid = sbi->sb_gid;
sbi->sb_eas = eas; sbi->sb_chk = chk; sbi->sb_chkdsk = chkdsk;
sbi->sb_err = errs; sbi->sb_timeshift = timeshift;
- if (!(*flags & MS_RDONLY)) mark_dirty(s, 1);
+ if (!(*flags & SB_RDONLY)) mark_dirty(s, 1);
hpfs_unlock(s);
return 0;
goto bail4;
}
- s->s_flags |= MS_NOATIME;
+ s->s_flags |= SB_NOATIME;
/* Fill superblock stuff */
s->s_magic = HPFS_SUPER_MAGIC;
mutex_unlock(&hugetlb_fault_mutex_table[hash]);
/*
- * page_put due to reference from alloc_huge_page()
* unlock_page because locked by add_to_page_cache()
+ * page_put due to reference from alloc_huge_page()
*/
- put_page(page);
unlock_page(page);
+ put_page(page);
}
if (!(mode & FALLOC_FL_KEEP_SIZE) && offset + len > inode->i_size)
{
if (!(inode->i_state & (I_DIRTY_ALL | I_SYNC |
I_FREEING | I_WILL_FREE)) &&
- !atomic_read(&inode->i_count) && inode->i_sb->s_flags & MS_ACTIVE)
+ !atomic_read(&inode->i_count) && inode->i_sb->s_flags & SB_ACTIVE)
inode_lru_list_add(inode);
}
* @sb: superblock to operate on
*
* Make sure that no inodes with zero refcount are retained. This is
- * called by superblock shutdown after having MS_ACTIVE flag removed,
+ * called by superblock shutdown after having SB_ACTIVE flag removed,
* so any inode reaching zero refcount during or after that call will
* be immediately evicted.
*/
else
drop = generic_drop_inode(inode);
- if (!drop && (sb->s_flags & MS_ACTIVE)) {
+ if (!drop && (sb->s_flags & SB_ACTIVE)) {
inode_add_lru(inode);
spin_unlock(&inode->i_lock);
return;
if (flags & S_MTIME)
inode->i_mtime = *time;
- if (!(inode->i_sb->s_flags & MS_LAZYTIME) || (flags & S_VERSION))
+ if (!(inode->i_sb->s_flags & SB_LAZYTIME) || (flags & S_VERSION))
iflags |= I_DIRTY_SYNC;
__mark_inode_dirty(inode, iflags);
return 0;
if (IS_NOATIME(inode))
return false;
- if ((inode->i_sb->s_flags & MS_NODIRATIME) && S_ISDIR(inode->i_mode))
+ if ((inode->i_sb->s_flags & SB_NODIRATIME) && S_ISDIR(inode->i_mode))
return false;
if (mnt->mnt_flags & MNT_NOATIME)
static int isofs_remount(struct super_block *sb, int *flags, char *data)
{
sync_filesystem(sb);
- if (!(*flags & MS_RDONLY))
+ if (!(*flags & SB_RDONLY))
return -EROFS;
return 0;
}
mutex_unlock(&c->alloc_sem);
}
- if (!(*flags & MS_RDONLY))
+ if (!(*flags & SB_RDONLY))
jffs2_start_garbage_collect_thread(c);
- *flags |= MS_NOATIME;
+ *flags |= SB_NOATIME;
return 0;
}
}
-#define jffs2_is_readonly(c) (OFNI_BS_2SFFJ(c)->s_flags & MS_RDONLY)
+#define jffs2_is_readonly(c) (OFNI_BS_2SFFJ(c)->s_flags & SB_RDONLY)
#define SECTOR_ADDR(x) ( (((unsigned long)(x) / c->sector_size) * c->sector_size) )
#ifndef CONFIG_JFFS2_FS_WRITEBUFFER
sb->s_op = &jffs2_super_operations;
sb->s_export_op = &jffs2_export_ops;
- sb->s_flags = sb->s_flags | MS_NOATIME;
+ sb->s_flags = sb->s_flags | SB_NOATIME;
sb->s_xattr = jffs2_xattr_handlers;
#ifdef CONFIG_JFFS2_FS_POSIX_ACL
- sb->s_flags |= MS_POSIXACL;
+ sb->s_flags |= SB_POSIXACL;
#endif
ret = jffs2_do_fill_super(sb, data, silent);
return ret;
else if (sbi->flag & JFS_ERR_REMOUNT_RO) {
jfs_err("ERROR: (device %s): remounting filesystem as read-only",
sb->s_id);
- sb->s_flags |= MS_RDONLY;
+ sb->s_flags |= SB_RDONLY;
}
/* nothing is done for continue beyond marking the superblock dirty */
return rc;
}
- if (sb_rdonly(sb) && !(*flags & MS_RDONLY)) {
+ if (sb_rdonly(sb) && !(*flags & SB_RDONLY)) {
/*
* Invalidate any previously read metadata. fsck may have
* changed the on-disk data since we mounted r/o
ret = jfs_mount_rw(sb, 1);
/* mark the fs r/w for quota activity */
- sb->s_flags &= ~MS_RDONLY;
+ sb->s_flags &= ~SB_RDONLY;
dquot_resume(sb, -1);
return ret;
}
- if (!sb_rdonly(sb) && (*flags & MS_RDONLY)) {
+ if (!sb_rdonly(sb) && (*flags & SB_RDONLY)) {
rc = dquot_suspend(sb, -1);
if (rc < 0)
return rc;
sbi->flag = flag;
#ifdef CONFIG_JFS_POSIX_ACL
- sb->s_flags |= MS_POSIXACL;
+ sb->s_flags |= SB_POSIXACL;
#endif
if (newLVSize) {
deactivate_locked_super(sb);
return ERR_PTR(error);
}
- sb->s_flags |= MS_ACTIVE;
+ sb->s_flags |= SB_ACTIVE;
mutex_lock(&kernfs_mutex);
list_add(&info->node, &root->supers);
struct inode *root;
struct qstr d_name = QSTR_INIT(name, strlen(name));
- s = sget_userns(fs_type, NULL, set_anon_super, MS_KERNMOUNT|MS_NOUSER,
+ s = sget_userns(fs_type, NULL, set_anon_super, SB_KERNMOUNT|SB_NOUSER,
&init_user_ns, NULL);
if (IS_ERR(s))
return ERR_CAST(s);
d_instantiate(dentry, root);
s->s_root = dentry;
s->s_d_op = dops;
- s->s_flags |= MS_ACTIVE;
+ s->s_flags |= SB_ACTIVE;
return dget(s->s_root);
Enomem:
spin_lock(&pin_fs_lock);
if (unlikely(!*mount)) {
spin_unlock(&pin_fs_lock);
- mnt = vfs_kern_mount(type, MS_KERNMOUNT, type->name, NULL);
+ mnt = vfs_kern_mount(type, SB_KERNMOUNT, type->name, NULL);
if (IS_ERR(mnt))
return PTR_ERR(mnt);
spin_lock(&pin_fs_lock);
if (ln->nrhosts == 0)
return;
- printk(KERN_WARNING "lockd: couldn't shutdown host module for net %p!\n", net);
- dprintk("lockd: %lu hosts left in net %p:\n", ln->nrhosts, net);
+ pr_warn("lockd: couldn't shutdown host module for net %x!\n",
+ net->ns.inum);
+ dprintk("lockd: %lu hosts left in net %x:\n", ln->nrhosts,
+ net->ns.inum);
} else {
if (nrhosts == 0)
return;
for_each_host(host, chain, nlm_server_hosts) {
if (net && host->net != net)
continue;
- dprintk(" %s (cnt %d use %d exp %ld net %p)\n",
+ dprintk(" %s (cnt %d use %d exp %ld net %x)\n",
host->h_name, atomic_read(&host->h_count),
- host->h_inuse, host->h_expires, host->net);
+ host->h_inuse, host->h_expires, host->net->ns.inum);
}
}
mutex_lock(&nlm_host_mutex);
/* First, make all hosts eligible for gc */
- dprintk("lockd: nuking all hosts in net %p...\n", net);
+ dprintk("lockd: nuking all hosts in net %x...\n",
+ net ? net->ns.inum : 0);
for_each_host(host, chain, nlm_server_hosts) {
if (net && host->net != net)
continue;
/* Then, perform a garbage collection pass */
nlm_gc_hosts(net);
- mutex_unlock(&nlm_host_mutex);
-
nlm_complain_hosts(net);
+ mutex_unlock(&nlm_host_mutex);
}
/*
struct hlist_node *next;
struct nlm_host *host;
- dprintk("lockd: host garbage collection for net %p\n", net);
+ dprintk("lockd: host garbage collection for net %x\n",
+ net ? net->ns.inum : 0);
for_each_host(host, chain, nlm_server_hosts) {
if (net && host->net != net)
continue;
if (atomic_read(&host->h_count) || host->h_inuse
|| time_before(jiffies, host->h_expires)) {
dprintk("nlm_gc_hosts skipping %s "
- "(cnt %d use %d exp %ld net %p)\n",
+ "(cnt %d use %d exp %ld net %x)\n",
host->h_name, atomic_read(&host->h_count),
- host->h_inuse, host->h_expires, host->net);
+ host->h_inuse, host->h_expires,
+ host->net->ns.inum);
continue;
}
nlm_destroy_host_locked(host);
clnt = nsm_create(host->net, host->nodename);
if (IS_ERR(clnt)) {
dprintk("lockd: failed to create NSM upcall transport, "
- "status=%ld, net=%p\n", PTR_ERR(clnt), host->net);
+ "status=%ld, net=%x\n", PTR_ERR(clnt),
+ host->net->ns.inum);
return PTR_ERR(clnt);
}
static struct svc_rqst *nlmsvc_rqst;
unsigned long nlmsvc_timeout;
+atomic_t nlm_ntf_refcnt = ATOMIC_INIT(0);
+DECLARE_WAIT_QUEUE_HEAD(nlm_ntf_wq);
+
unsigned int lockd_net_id;
/*
if (error < 0)
goto err_bind;
set_grace_period(net);
- dprintk("lockd_up_net: per-net data created; net=%p\n", net);
+ dprintk("%s: per-net data created; net=%x\n", __func__, net->ns.inum);
return 0;
err_bind:
if (ln->nlmsvc_users) {
if (--ln->nlmsvc_users == 0) {
nlm_shutdown_hosts_net(net);
+ cancel_delayed_work_sync(&ln->grace_period_end);
+ locks_end_grace(&ln->lockd_manager);
svc_shutdown_net(serv, net);
- dprintk("lockd_down_net: per-net data destroyed; net=%p\n", net);
+ dprintk("%s: per-net data destroyed; net=%x\n",
+ __func__, net->ns.inum);
}
} else {
- printk(KERN_ERR "lockd_down_net: no users! task=%p, net=%p\n",
- nlmsvc_task, net);
+ pr_err("%s: no users! task=%p, net=%x\n",
+ __func__, nlmsvc_task, net->ns.inum);
BUG();
}
}
struct in_ifaddr *ifa = (struct in_ifaddr *)ptr;
struct sockaddr_in sin;
- if (event != NETDEV_DOWN)
+ if ((event != NETDEV_DOWN) ||
+ !atomic_inc_not_zero(&nlm_ntf_refcnt))
goto out;
if (nlmsvc_rqst) {
svc_age_temp_xprts_now(nlmsvc_rqst->rq_server,
(struct sockaddr *)&sin);
}
+ atomic_dec(&nlm_ntf_refcnt);
+ wake_up(&nlm_ntf_wq);
out:
return NOTIFY_DONE;
struct inet6_ifaddr *ifa = (struct inet6_ifaddr *)ptr;
struct sockaddr_in6 sin6;
- if (event != NETDEV_DOWN)
+ if ((event != NETDEV_DOWN) ||
+ !atomic_inc_not_zero(&nlm_ntf_refcnt))
goto out;
if (nlmsvc_rqst) {
svc_age_temp_xprts_now(nlmsvc_rqst->rq_server,
(struct sockaddr *)&sin6);
}
+ atomic_dec(&nlm_ntf_refcnt);
+ wake_up(&nlm_ntf_wq);
out:
return NOTIFY_DONE;
#if IS_ENABLED(CONFIG_IPV6)
unregister_inet6addr_notifier(&lockd_inet6addr_notifier);
#endif
+ wait_event(nlm_ntf_wq, atomic_read(&nlm_ntf_refcnt) == 0);
}
static void lockd_svc_exit_thread(void)
{
+ atomic_dec(&nlm_ntf_refcnt);
lockd_unregister_notifiers();
svc_exit_thread(nlmsvc_rqst);
}
goto out_rqst;
}
+ atomic_inc(&nlm_ntf_refcnt);
svc_sock_update_bufs(serv);
serv->sv_maxconn = nlm_max_connections;
static void lockd_exit_net(struct net *net)
{
+ struct lockd_net *ln = net_generic(net, lockd_net_id);
+
+ WARN_ONCE(!list_empty(&ln->lockd_manager.list),
+ "net %x %s: lockd_manager.list is not empty\n",
+ net->ns.inum, __func__);
+ WARN_ONCE(!list_empty(&ln->nsm_handles),
+ "net %x %s: nsm_handles list is not empty\n",
+ net->ns.inum, __func__);
+ WARN_ONCE(delayed_work_pending(&ln->grace_period_end),
+ "net %x %s: grace_period_end was not cancelled\n",
+ net->ns.inum, __func__);
}
static struct pernet_operations lockd_net_ops = {
{
struct nlm_host hint;
- dprintk("lockd: nlmsvc_mark_resources for net %p\n", net);
+ dprintk("lockd: %s for net %x\n", __func__, net ? net->ns.inum : 0);
hint.net = net;
nlm_traverse_files(&hint, nlmsvc_mark_host, NULL);
}
static inline bool is_remote_lock(struct file *filp)
{
- return likely(!(filp->f_path.dentry->d_sb->s_flags & MS_NOREMOTELOCK));
+ return likely(!(filp->f_path.dentry->d_sb->s_flags & SB_NOREMOTELOCK));
}
static bool lease_breaking(struct file_lock *fl)
struct mb_cache *cache = container_of(shrink, struct mb_cache,
c_shrink);
+ /* Unlikely, but not impossible */
+ if (unlikely(cache->c_entry_count < 0))
+ return 0;
return cache->c_entry_count;
}
sync_filesystem(sb);
ms = sbi->s_ms;
- if ((bool)(*flags & MS_RDONLY) == sb_rdonly(sb))
+ if ((bool)(*flags & SB_RDONLY) == sb_rdonly(sb))
return 0;
- if (*flags & MS_RDONLY) {
+ if (*flags & SB_RDONLY) {
if (ms->s_state & MINIX_VALID_FS ||
!(sbi->s_mount_state & MINIX_VALID_FS))
return 0;
* of the daemon to instantiate them before they can be used.
*/
if (!(nd->flags & (LOOKUP_PARENT | LOOKUP_DIRECTORY |
- LOOKUP_OPEN | LOOKUP_CREATE |
- LOOKUP_AUTOMOUNT))) {
- /* Positive dentry that isn't meant to trigger an
- * automount, EISDIR will allow it to be used,
- * otherwise there's no mount here "now" so return
- * ENOENT.
- */
- if (path->dentry->d_inode)
- return -EISDIR;
- else
- return -ENOENT;
- }
+ LOOKUP_OPEN | LOOKUP_CREATE | LOOKUP_AUTOMOUNT)) &&
+ path->dentry->d_inode)
+ return -EISDIR;
if (path->dentry->d_sb->s_user_ns != &init_user_ns)
return -EACCES;
static int ncp_remount(struct super_block *sb, int *flags, char* data)
{
sync_filesystem(sb);
- *flags |= MS_NODIRATIME;
+ *flags |= SB_NODIRATIME;
return 0;
}
else
default_bufsize = 1024;
- sb->s_flags |= MS_NODIRATIME; /* probably even noatime */
+ sb->s_flags |= SB_NODIRATIME; /* probably even noatime */
sb->s_maxbytes = 0xFFFFFFFFU;
sb->s_blocksize = 1024; /* Eh... Is this correct? */
sb->s_blocksize_bits = 10;
/* Unhash it, so that ->d_iput() would be called */
return 1;
}
- if (!(dentry->d_sb->s_flags & MS_ACTIVE)) {
+ if (!(dentry->d_sb->s_flags & SB_ACTIVE)) {
/* Unhash it, so that ancestors of killed async unlink
* files will be cleaned up during umount */
return 1;
* Note that we only have to check the vfsmount flags here:
* - NFS always sets S_NOATIME by so checking it would give a
* bogus result
- * - NFS never sets MS_NOATIME or MS_NODIRATIME so there is
+ * - NFS never sets SB_NOATIME or SB_NODIRATIME so there is
* no point in checking those.
*/
if ((path->mnt->mnt_flags & MNT_NOATIME) ||
#include <linux/nfs_page.h>
#include <linux/wait_bit.h>
-#define NFS_MS_MASK (MS_RDONLY|MS_NOSUID|MS_NODEV|MS_NOEXEC|MS_SYNCHRONOUS)
+#define NFS_MS_MASK (SB_RDONLY|SB_NOSUID|SB_NODEV|SB_NOEXEC|SB_SYNCHRONOUS)
extern const struct export_operations nfs_export_ops;
*/
seq_printf(m, "\n\topts:\t");
seq_puts(m, sb_rdonly(root->d_sb) ? "ro" : "rw");
- seq_puts(m, root->d_sb->s_flags & MS_SYNCHRONOUS ? ",sync" : "");
- seq_puts(m, root->d_sb->s_flags & MS_NOATIME ? ",noatime" : "");
- seq_puts(m, root->d_sb->s_flags & MS_NODIRATIME ? ",nodiratime" : "");
+ seq_puts(m, root->d_sb->s_flags & SB_SYNCHRONOUS ? ",sync" : "");
+ seq_puts(m, root->d_sb->s_flags & SB_NOATIME ? ",noatime" : "");
+ seq_puts(m, root->d_sb->s_flags & SB_NODIRATIME ? ",nodiratime" : "");
nfs_show_mount_options(m, nfss, 1);
seq_printf(m, "\n\tage:\t%lu", (jiffies - nfss->mount_time) / HZ);
/*
* noac is a special case. It implies -o sync, but that's not
* necessarily reflected in the mtab options. do_remount_sb
- * will clear MS_SYNCHRONOUS if -o sync wasn't specified in the
+ * will clear SB_SYNCHRONOUS if -o sync wasn't specified in the
* remount options, so we have to explicitly reset it.
*/
if (data->flags & NFS_MOUNT_NOAC)
- *flags |= MS_SYNCHRONOUS;
+ *flags |= SB_SYNCHRONOUS;
/* compare new mount options with old ones */
error = nfs_compare_remount_data(nfss, data);
/* The VFS shouldn't apply the umask to mode bits. We will do
* so ourselves when necessary.
*/
- sb->s_flags |= MS_POSIXACL;
+ sb->s_flags |= SB_POSIXACL;
sb->s_time_gran = 1;
sb->s_export_op = &nfs_export_ops;
}
/* The VFS shouldn't apply the umask to mode bits. We will do
* so ourselves when necessary.
*/
- sb->s_flags |= MS_POSIXACL;
+ sb->s_flags |= SB_POSIXACL;
}
nfs_initialise_sb(sb);
/* -o noac implies -o sync */
if (server->flags & NFS_MOUNT_NOAC)
- sb_mntdata.mntflags |= MS_SYNCHRONOUS;
+ sb_mntdata.mntflags |= SB_SYNCHRONOUS;
if (mount_info->cloned != NULL && mount_info->cloned->sb != NULL)
- if (mount_info->cloned->sb->s_flags & MS_SYNCHRONOUS)
- sb_mntdata.mntflags |= MS_SYNCHRONOUS;
+ if (mount_info->cloned->sb->s_flags & SB_SYNCHRONOUS)
+ sb_mntdata.mntflags |= SB_SYNCHRONOUS;
/* Get a superblock - note that we may end up sharing one that already exists */
s = sget(nfs_mod->nfs_fs, compare_super, nfs_set_super, flags, &sb_mntdata);
if (error)
goto error_splat_root;
- s->s_flags |= MS_ACTIVE;
+ s->s_flags |= SB_ACTIVE;
out:
return mntroot;
struct list_head *grace_list = net_generic(net, grace_net_id);
spin_lock(&grace_lock);
- list_add(&lm->list, grace_list);
+ if (list_empty(&lm->list))
+ list_add(&lm->list, grace_list);
+ else
+ WARN(1, "double list_add attempt detected in net %x %s\n",
+ net->ns.inum, (net == &init_net) ? "(init_net)" : "");
spin_unlock(&grace_lock);
}
EXPORT_SYMBOL_GPL(locks_start_grace);
{
struct list_head *grace_list = net_generic(net, grace_net_id);
- BUG_ON(!list_empty(grace_list));
+ WARN_ONCE(!list_empty(grace_list),
+ "net %x %s: grace_list is not empty\n",
+ net->ns.inum, __func__);
}
static struct pernet_operations grace_net_ops = {
return NULL;
}
-static struct cache_detail svc_expkey_cache_template = {
+static const struct cache_detail svc_expkey_cache_template = {
.owner = THIS_MODULE,
.hash_size = EXPKEY_HASHMAX,
.name = "nfsd.fh",
return NULL;
}
-static struct cache_detail svc_export_cache_template = {
+static const struct cache_detail svc_export_cache_template = {
.owner = THIS_MODULE,
.hash_size = EXPORT_HASHMAX,
.name = "nfsd.export",
int rv;
struct nfsd_net *nn = net_generic(net, nfsd_net_id);
- dprintk("nfsd: initializing export module (net: %p).\n", net);
+ dprintk("nfsd: initializing export module (net: %x).\n", net->ns.inum);
nn->svc_export_cache = cache_create_net(&svc_export_cache_template, net);
if (IS_ERR(nn->svc_export_cache))
{
struct nfsd_net *nn = net_generic(net, nfsd_net_id);
- dprintk("nfsd: shutting down export module (net: %p).\n", net);
+ dprintk("nfsd: shutting down export module (net: %x).\n", net->ns.inum);
cache_unregister_net(nn->svc_expkey_cache, net);
cache_unregister_net(nn->svc_export_cache, net);
cache_destroy_net(nn->svc_export_cache, net);
svcauth_unix_purge(net);
- dprintk("nfsd: export shutdown complete (net: %p).\n", net);
+ dprintk("nfsd: export shutdown complete (net: %x).\n", net->ns.inum);
}
u32 clverifier_counter;
struct svc_serv *nfsd_serv;
+
+ wait_queue_head_t ntf_wq;
+ atomic_t ntf_refcnt;
};
/* Simple check to find out if a given net was properly initialized */
static struct ent *idtoname_update(struct cache_detail *, struct ent *,
struct ent *);
-static struct cache_detail idtoname_cache_template = {
+static const struct cache_detail idtoname_cache_template = {
.owner = THIS_MODULE,
.hash_size = ENT_HASHMAX,
.name = "nfs4.idtoname",
struct ent *);
static int nametoid_parse(struct cache_detail *, char *, int);
-static struct cache_detail nametoid_cache_template = {
+static const struct cache_detail nametoid_cache_template = {
.owner = THIS_MODULE,
.hash_size = ENT_HASHMAX,
.name = "nfs4.nametoid",
static const stateid_t currentstateid = {
.si_generation = 1,
};
+static const stateid_t close_stateid = {
+ .si_generation = 0xffffffffU,
+};
static u64 current_sessionid = 1;
#define ZERO_STATEID(stateid) (!memcmp((stateid), &zero_stateid, sizeof(stateid_t)))
#define ONE_STATEID(stateid) (!memcmp((stateid), &one_stateid, sizeof(stateid_t)))
#define CURRENT_STATEID(stateid) (!memcmp((stateid), ¤tstateid, sizeof(stateid_t)))
+#define CLOSE_STATEID(stateid) (!memcmp((stateid), &close_stateid, sizeof(stateid_t)))
/* forward declarations */
static bool check_for_locks(struct nfs4_file *fp, struct nfs4_lockowner *lowner);
*/
static DEFINE_SPINLOCK(state_lock);
+enum nfsd4_st_mutex_lock_subclass {
+ OPEN_STATEID_MUTEX = 0,
+ LOCK_STATEID_MUTEX = 1,
+};
+
/*
* A waitqueue for all in-progress 4.0 CLOSE operations that are waiting for
* the refcount on the open stateid to drop.
/* ignore lock owners */
if (local->st_stateowner->so_is_open_owner == 0)
continue;
- if (local->st_stateowner == &oo->oo_owner) {
+ if (local->st_stateowner != &oo->oo_owner)
+ continue;
+ if (local->st_stid.sc_type == NFS4_OPEN_STID) {
ret = local;
refcount_inc(&ret->st_stid.sc_count);
break;
return ret;
}
+static __be32
+nfsd4_verify_open_stid(struct nfs4_stid *s)
+{
+ __be32 ret = nfs_ok;
+
+ switch (s->sc_type) {
+ default:
+ break;
+ case NFS4_CLOSED_STID:
+ case NFS4_CLOSED_DELEG_STID:
+ ret = nfserr_bad_stateid;
+ break;
+ case NFS4_REVOKED_DELEG_STID:
+ ret = nfserr_deleg_revoked;
+ }
+ return ret;
+}
+
+/* Lock the stateid st_mutex, and deal with races with CLOSE */
+static __be32
+nfsd4_lock_ol_stateid(struct nfs4_ol_stateid *stp)
+{
+ __be32 ret;
+
+ mutex_lock_nested(&stp->st_mutex, LOCK_STATEID_MUTEX);
+ ret = nfsd4_verify_open_stid(&stp->st_stid);
+ if (ret != nfs_ok)
+ mutex_unlock(&stp->st_mutex);
+ return ret;
+}
+
+static struct nfs4_ol_stateid *
+nfsd4_find_and_lock_existing_open(struct nfs4_file *fp, struct nfsd4_open *open)
+{
+ struct nfs4_ol_stateid *stp;
+ for (;;) {
+ spin_lock(&fp->fi_lock);
+ stp = nfsd4_find_existing_open(fp, open);
+ spin_unlock(&fp->fi_lock);
+ if (!stp || nfsd4_lock_ol_stateid(stp) == nfs_ok)
+ break;
+ nfs4_put_stid(&stp->st_stid);
+ }
+ return stp;
+}
+
static struct nfs4_openowner *
alloc_init_open_stateowner(unsigned int strhashval, struct nfsd4_open *open,
struct nfsd4_compound_state *cstate)
stp = open->op_stp;
/* We are moving these outside of the spinlocks to avoid the warnings */
mutex_init(&stp->st_mutex);
- mutex_lock(&stp->st_mutex);
+ mutex_lock_nested(&stp->st_mutex, OPEN_STATEID_MUTEX);
+retry:
spin_lock(&oo->oo_owner.so_client->cl_lock);
spin_lock(&fp->fi_lock);
spin_unlock(&fp->fi_lock);
spin_unlock(&oo->oo_owner.so_client->cl_lock);
if (retstp) {
- mutex_lock(&retstp->st_mutex);
+ /* Handle races with CLOSE */
+ if (nfsd4_lock_ol_stateid(retstp) != nfs_ok) {
+ nfs4_put_stid(&retstp->st_stid);
+ goto retry;
+ }
/* To keep mutex tracking happy */
mutex_unlock(&stp->st_mutex);
stp = retstp;
struct nfs4_ol_stateid *stp = NULL;
struct nfs4_delegation *dp = NULL;
__be32 status;
+ bool new_stp = false;
/*
* Lookup file; if found, lookup stateid and check open request,
status = nfs4_check_deleg(cl, open, &dp);
if (status)
goto out;
- spin_lock(&fp->fi_lock);
- stp = nfsd4_find_existing_open(fp, open);
- spin_unlock(&fp->fi_lock);
+ stp = nfsd4_find_and_lock_existing_open(fp, open);
} else {
open->op_file = NULL;
status = nfserr_bad_stateid;
goto out;
}
+ if (!stp) {
+ stp = init_open_stateid(fp, open);
+ if (!open->op_stp)
+ new_stp = true;
+ }
+
/*
* OPEN the file, or upgrade an existing OPEN.
* If truncate fails, the OPEN fails.
+ *
+ * stp is already locked.
*/
- if (stp) {
+ if (!new_stp) {
/* Stateid was found, this is an OPEN upgrade */
- mutex_lock(&stp->st_mutex);
status = nfs4_upgrade_open(rqstp, fp, current_fh, stp, open);
if (status) {
mutex_unlock(&stp->st_mutex);
goto out;
}
} else {
- /* stp is returned locked. */
- stp = init_open_stateid(fp, open);
- /* See if we lost the race to some other thread */
- if (stp->st_access_bmap != 0) {
- status = nfs4_upgrade_open(rqstp, fp, current_fh,
- stp, open);
- if (status) {
- mutex_unlock(&stp->st_mutex);
- goto out;
- }
- goto upgrade_out;
- }
status = nfs4_get_vfs_file(rqstp, fp, current_fh, stp, open);
if (status) {
- mutex_unlock(&stp->st_mutex);
+ stp->st_stid.sc_type = NFS4_CLOSED_STID;
release_open_stateid(stp);
+ mutex_unlock(&stp->st_mutex);
goto out;
}
if (stp->st_clnt_odstate == open->op_odstate)
open->op_odstate = NULL;
}
-upgrade_out:
+
nfs4_inc_and_copy_stateid(&open->op_stateid, &stp->st_stid);
mutex_unlock(&stp->st_mutex);
spin_unlock(&nn->blocked_locks_lock);
while (!list_empty(&reaplist)) {
- nbl = list_first_entry(&nn->blocked_locks_lru,
+ nbl = list_first_entry(&reaplist,
struct nfsd4_blocked_lock, nbl_lru);
list_del_init(&nbl->nbl_lru);
posix_unblock_lock(&nbl->nbl_lock);
return nfserr_old_stateid;
}
+static __be32 nfsd4_stid_check_stateid_generation(stateid_t *in, struct nfs4_stid *s, bool has_session)
+{
+ __be32 ret;
+
+ spin_lock(&s->sc_lock);
+ ret = nfsd4_verify_open_stid(s);
+ if (ret == nfs_ok)
+ ret = check_stateid_generation(in, &s->sc_stateid, has_session);
+ spin_unlock(&s->sc_lock);
+ return ret;
+}
+
static __be32 nfsd4_check_openowner_confirmed(struct nfs4_ol_stateid *ols)
{
if (ols->st_stateowner->so_is_open_owner &&
struct nfs4_stid *s;
__be32 status = nfserr_bad_stateid;
- if (ZERO_STATEID(stateid) || ONE_STATEID(stateid))
+ if (ZERO_STATEID(stateid) || ONE_STATEID(stateid) ||
+ CLOSE_STATEID(stateid))
return status;
/* Client debugging aid. */
if (!same_clid(&stateid->si_opaque.so_clid, &cl->cl_clientid)) {
s = find_stateid_locked(cl, stateid);
if (!s)
goto out_unlock;
- status = check_stateid_generation(stateid, &s->sc_stateid, 1);
+ status = nfsd4_stid_check_stateid_generation(stateid, s, 1);
if (status)
goto out_unlock;
switch (s->sc_type) {
else if (typemask & NFS4_DELEG_STID)
typemask |= NFS4_REVOKED_DELEG_STID;
- if (ZERO_STATEID(stateid) || ONE_STATEID(stateid))
+ if (ZERO_STATEID(stateid) || ONE_STATEID(stateid) ||
+ CLOSE_STATEID(stateid))
return nfserr_bad_stateid;
status = lookup_clientid(&stateid->si_opaque.so_clid, cstate, nn);
if (status == nfserr_stale_clientid) {
&s, nn);
if (status)
return status;
- status = check_stateid_generation(stateid, &s->sc_stateid,
+ status = nfsd4_stid_check_stateid_generation(stateid, s,
nfsd4_has_session(cstate));
if (status)
goto out;
struct nfs4_ol_stateid *stp = openlockstateid(s);
__be32 ret;
- mutex_lock(&stp->st_mutex);
+ ret = nfsd4_lock_ol_stateid(stp);
+ if (ret)
+ goto out_put_stid;
ret = check_stateid_generation(stateid, &s->sc_stateid, 1);
if (ret)
lockowner(stp->st_stateowner)))
goto out;
+ stp->st_stid.sc_type = NFS4_CLOSED_STID;
release_lock_stateid(stp);
ret = nfs_ok;
out:
mutex_unlock(&stp->st_mutex);
+out_put_stid:
nfs4_put_stid(s);
return ret;
}
s = find_stateid_locked(cl, stateid);
if (!s)
goto out_unlock;
+ spin_lock(&s->sc_lock);
switch (s->sc_type) {
case NFS4_DELEG_STID:
ret = nfserr_locks_held;
ret = nfserr_locks_held;
break;
case NFS4_LOCK_STID:
+ spin_unlock(&s->sc_lock);
refcount_inc(&s->sc_count);
spin_unlock(&cl->cl_lock);
ret = nfsd4_free_lock_stateid(stateid, s);
goto out;
case NFS4_REVOKED_DELEG_STID:
+ spin_unlock(&s->sc_lock);
dp = delegstateid(s);
list_del_init(&dp->dl_recall_lru);
spin_unlock(&cl->cl_lock);
goto out;
/* Default falls through and returns nfserr_bad_stateid */
}
+ spin_unlock(&s->sc_lock);
out_unlock:
spin_unlock(&cl->cl_lock);
out:
status = nfsd4_check_seqid(cstate, sop, seqid);
if (status)
return status;
- if (stp->st_stid.sc_type == NFS4_CLOSED_STID
- || stp->st_stid.sc_type == NFS4_REVOKED_DELEG_STID)
- /*
- * "Closed" stateid's exist *only* to return
- * nfserr_replay_me from the previous step, and
- * revoked delegations are kept only for free_stateid.
- */
- return nfserr_bad_stateid;
- mutex_lock(&stp->st_mutex);
+ status = nfsd4_lock_ol_stateid(stp);
+ if (status != nfs_ok)
+ return status;
status = check_stateid_generation(stateid, &stp->st_stid.sc_stateid, nfsd4_has_session(cstate));
if (status == nfs_ok)
status = nfs4_check_fh(current_fh, &stp->st_stid);
bool unhashed;
LIST_HEAD(reaplist);
- s->st_stid.sc_type = NFS4_CLOSED_STID;
spin_lock(&clp->cl_lock);
unhashed = unhash_open_stateid(s, &reaplist);
nfsd4_bump_seqid(cstate, status);
if (status)
goto out;
+
+ stp->st_stid.sc_type = NFS4_CLOSED_STID;
nfs4_inc_and_copy_stateid(&close->cl_stateid, &stp->st_stid);
- mutex_unlock(&stp->st_mutex);
nfsd4_close_open_stateid(stp);
+ mutex_unlock(&stp->st_mutex);
+
+ /* See RFC5661 sectionm 18.2.4 */
+ if (stp->st_stid.sc_client->cl_minorversion)
+ memcpy(&close->cl_stateid, &close_stateid,
+ sizeof(close->cl_stateid));
/* put reference from nfs4_preprocess_seqid_op */
nfs4_put_stid(&stp->st_stid);
if (status)
goto out;
dp = delegstateid(s);
- status = check_stateid_generation(stateid, &dp->dl_stid.sc_stateid, nfsd4_has_session(cstate));
+ status = nfsd4_stid_check_stateid_generation(stateid, &dp->dl_stid, nfsd4_has_session(cstate));
if (status)
goto put_stateid;
return ret;
}
-static void
+static struct nfs4_ol_stateid *
+find_lock_stateid(struct nfs4_lockowner *lo, struct nfs4_file *fp)
+{
+ struct nfs4_ol_stateid *lst;
+ struct nfs4_client *clp = lo->lo_owner.so_client;
+
+ lockdep_assert_held(&clp->cl_lock);
+
+ list_for_each_entry(lst, &lo->lo_owner.so_stateids, st_perstateowner) {
+ if (lst->st_stid.sc_type != NFS4_LOCK_STID)
+ continue;
+ if (lst->st_stid.sc_file == fp) {
+ refcount_inc(&lst->st_stid.sc_count);
+ return lst;
+ }
+ }
+ return NULL;
+}
+
+static struct nfs4_ol_stateid *
init_lock_stateid(struct nfs4_ol_stateid *stp, struct nfs4_lockowner *lo,
struct nfs4_file *fp, struct inode *inode,
struct nfs4_ol_stateid *open_stp)
{
struct nfs4_client *clp = lo->lo_owner.so_client;
+ struct nfs4_ol_stateid *retstp;
- lockdep_assert_held(&clp->cl_lock);
+ mutex_init(&stp->st_mutex);
+ mutex_lock_nested(&stp->st_mutex, OPEN_STATEID_MUTEX);
+retry:
+ spin_lock(&clp->cl_lock);
+ spin_lock(&fp->fi_lock);
+ retstp = find_lock_stateid(lo, fp);
+ if (retstp)
+ goto out_unlock;
refcount_inc(&stp->st_stid.sc_count);
stp->st_stid.sc_type = NFS4_LOCK_STID;
stp->st_access_bmap = 0;
stp->st_deny_bmap = open_stp->st_deny_bmap;
stp->st_openstp = open_stp;
- mutex_init(&stp->st_mutex);
list_add(&stp->st_locks, &open_stp->st_locks);
list_add(&stp->st_perstateowner, &lo->lo_owner.so_stateids);
- spin_lock(&fp->fi_lock);
list_add(&stp->st_perfile, &fp->fi_stateids);
+out_unlock:
spin_unlock(&fp->fi_lock);
-}
-
-static struct nfs4_ol_stateid *
-find_lock_stateid(struct nfs4_lockowner *lo, struct nfs4_file *fp)
-{
- struct nfs4_ol_stateid *lst;
- struct nfs4_client *clp = lo->lo_owner.so_client;
-
- lockdep_assert_held(&clp->cl_lock);
-
- list_for_each_entry(lst, &lo->lo_owner.so_stateids, st_perstateowner) {
- if (lst->st_stid.sc_file == fp) {
- refcount_inc(&lst->st_stid.sc_count);
- return lst;
+ spin_unlock(&clp->cl_lock);
+ if (retstp) {
+ if (nfsd4_lock_ol_stateid(retstp) != nfs_ok) {
+ nfs4_put_stid(&retstp->st_stid);
+ goto retry;
}
+ /* To keep mutex tracking happy */
+ mutex_unlock(&stp->st_mutex);
+ stp = retstp;
}
- return NULL;
+ return stp;
}
static struct nfs4_ol_stateid *
struct nfs4_openowner *oo = openowner(ost->st_stateowner);
struct nfs4_client *clp = oo->oo_owner.so_client;
+ *new = false;
spin_lock(&clp->cl_lock);
lst = find_lock_stateid(lo, fi);
- if (lst == NULL) {
- spin_unlock(&clp->cl_lock);
- ns = nfs4_alloc_stid(clp, stateid_slab, nfs4_free_lock_stateid);
- if (ns == NULL)
- return NULL;
-
- spin_lock(&clp->cl_lock);
- lst = find_lock_stateid(lo, fi);
- if (likely(!lst)) {
- lst = openlockstateid(ns);
- init_lock_stateid(lst, lo, fi, inode, ost);
- ns = NULL;
- *new = true;
- }
- }
spin_unlock(&clp->cl_lock);
- if (ns)
+ if (lst != NULL) {
+ if (nfsd4_lock_ol_stateid(lst) == nfs_ok)
+ goto out;
+ nfs4_put_stid(&lst->st_stid);
+ }
+ ns = nfs4_alloc_stid(clp, stateid_slab, nfs4_free_lock_stateid);
+ if (ns == NULL)
+ return NULL;
+
+ lst = init_lock_stateid(openlockstateid(ns), lo, fi, inode, ost);
+ if (lst == openlockstateid(ns))
+ *new = true;
+ else
nfs4_put_stid(ns);
+out:
return lst;
}
struct nfs4_lockowner *lo;
struct nfs4_ol_stateid *lst;
unsigned int strhashval;
- bool hashed;
lo = find_lockowner_str(cl, &lock->lk_new_owner);
if (!lo) {
goto out;
}
-retry:
lst = find_or_create_lock_stateid(lo, fi, inode, ost, new);
if (lst == NULL) {
status = nfserr_jukebox;
goto out;
}
- mutex_lock(&lst->st_mutex);
-
- /* See if it's still hashed to avoid race with FREE_STATEID */
- spin_lock(&cl->cl_lock);
- hashed = !list_empty(&lst->st_perfile);
- spin_unlock(&cl->cl_lock);
-
- if (!hashed) {
- mutex_unlock(&lst->st_mutex);
- nfs4_put_stid(&lst->st_stid);
- goto retry;
- }
status = nfs_ok;
*plst = lst;
out:
seqid_mutating_err(ntohl(status)))
lock_sop->lo_owner.so_seqid++;
- mutex_unlock(&lock_stp->st_mutex);
-
/*
* If this is a new, never-before-used stateid, and we are
* returning an error, then just go ahead and release it.
*/
- if (status && new)
+ if (status && new) {
+ lock_stp->st_stid.sc_type = NFS4_CLOSED_STID;
release_lock_stateid(lock_stp);
+ }
+
+ mutex_unlock(&lock_stp->st_mutex);
nfs4_put_stid(&lock_stp->st_stid);
}
INIT_LIST_HEAD(&nn->sessionid_hashtbl[i]);
nn->conf_name_tree = RB_ROOT;
nn->unconf_name_tree = RB_ROOT;
+ nn->boot_time = get_seconds();
+ nn->grace_ended = false;
+ nn->nfsd4_manager.block_opens = true;
+ INIT_LIST_HEAD(&nn->nfsd4_manager.list);
INIT_LIST_HEAD(&nn->client_lru);
INIT_LIST_HEAD(&nn->close_lru);
INIT_LIST_HEAD(&nn->del_recall_lru);
ret = nfs4_state_create_net(net);
if (ret)
return ret;
- nn->boot_time = get_seconds();
- nn->grace_ended = false;
- nn->nfsd4_manager.block_opens = true;
locks_start_grace(net, &nn->nfsd4_manager);
nfsd4_client_tracking_init(net);
printk(KERN_INFO "NFSD: starting %ld-second grace period (net %x)\n",
spin_unlock(&nn->blocked_locks_lock);
while (!list_empty(&reaplist)) {
- nbl = list_first_entry(&nn->blocked_locks_lru,
+ nbl = list_first_entry(&reaplist,
struct nfsd4_blocked_lock, nbl_lru);
list_del_init(&nbl->nbl_lru);
posix_unblock_lock(&nbl->nbl_lock);
nn->nfsd4_grace = 90;
nn->clverifier_counter = prandom_u32();
nn->clientid_counter = prandom_u32();
+
+ atomic_set(&nn->ntf_refcnt, 0);
+ init_waitqueue_head(&nn->ntf_wq);
return 0;
out_idmap_error:
struct nfsd_net *nn = net_generic(net, nfsd_net_id);
struct sockaddr_in sin;
- if (event != NETDEV_DOWN)
+ if ((event != NETDEV_DOWN) ||
+ !atomic_inc_not_zero(&nn->ntf_refcnt))
goto out;
if (nn->nfsd_serv) {
sin.sin_addr.s_addr = ifa->ifa_local;
svc_age_temp_xprts_now(nn->nfsd_serv, (struct sockaddr *)&sin);
}
+ atomic_dec(&nn->ntf_refcnt);
+ wake_up(&nn->ntf_wq);
out:
return NOTIFY_DONE;
struct nfsd_net *nn = net_generic(net, nfsd_net_id);
struct sockaddr_in6 sin6;
- if (event != NETDEV_DOWN)
+ if ((event != NETDEV_DOWN) ||
+ !atomic_inc_not_zero(&nn->ntf_refcnt))
goto out;
if (nn->nfsd_serv) {
sin6.sin6_scope_id = ifa->idev->dev->ifindex;
svc_age_temp_xprts_now(nn->nfsd_serv, (struct sockaddr *)&sin6);
}
-
+ atomic_dec(&nn->ntf_refcnt);
+ wake_up(&nn->ntf_wq);
out:
return NOTIFY_DONE;
}
{
struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+ atomic_dec(&nn->ntf_refcnt);
/* check if the notifier still has clients */
if (atomic_dec_return(&nfsd_notifier_refcount) == 0) {
unregister_inetaddr_notifier(&nfsd_inetaddr_notifier);
unregister_inet6addr_notifier(&nfsd_inet6addr_notifier);
#endif
}
+ wait_event(nn->ntf_wq, atomic_read(&nn->ntf_refcnt) == 0);
/*
* write_ports can create the server without actually starting
register_inet6addr_notifier(&nfsd_inet6addr_notifier);
#endif
}
+ atomic_inc(&nn->ntf_refcnt);
ktime_get_real_ts64(&nn->nfssvc_boot); /* record boot time */
return 0;
}
struct the_nilfs *nilfs)
{
struct nilfs_inode_info *ii, *n;
- int during_mount = !(sci->sc_super->s_flags & MS_ACTIVE);
+ int during_mount = !(sci->sc_super->s_flags & SB_ACTIVE);
int defer_iput = false;
spin_lock(&nilfs->ns_inode_lock);
if (nilfs_test_opt(nilfs, ERRORS_RO)) {
printk(KERN_CRIT "Remounting filesystem read-only\n");
- sb->s_flags |= MS_RDONLY;
+ sb->s_flags |= SB_RDONLY;
}
}
/* FS independent flags */
#ifdef NILFS_ATIME_DISABLE
- sb->s_flags |= MS_NOATIME;
+ sb->s_flags |= SB_NOATIME;
#endif
nilfs_set_default_options(sb, sbp);
err = -EINVAL;
goto restore_opts;
}
- sb->s_flags = (sb->s_flags & ~MS_POSIXACL);
+ sb->s_flags = (sb->s_flags & ~SB_POSIXACL);
err = -EINVAL;
goto restore_opts;
}
- if ((bool)(*flags & MS_RDONLY) == sb_rdonly(sb))
+ if ((bool)(*flags & SB_RDONLY) == sb_rdonly(sb))
goto out;
- if (*flags & MS_RDONLY) {
+ if (*flags & SB_RDONLY) {
/* Shutting down log writer */
nilfs_detach_log_writer(sb);
- sb->s_flags |= MS_RDONLY;
+ sb->s_flags |= SB_RDONLY;
/*
* Remounting a valid RW partition RDONLY, so set
goto restore_opts;
}
- sb->s_flags &= ~MS_RDONLY;
+ sb->s_flags &= ~SB_RDONLY;
root = NILFS_I(d_inode(sb->s_root))->i_root;
err = nilfs_attach_log_writer(sb, root);
const char *msg = NULL;
int err;
- if (!(sd->flags & MS_RDONLY)) {
+ if (!(sd->flags & SB_RDONLY)) {
msg = "read-only option is not specified";
goto parse_error;
}
struct dentry *root_dentry;
int err, s_new = false;
- if (!(flags & MS_RDONLY))
+ if (!(flags & SB_RDONLY))
mode |= FMODE_WRITE;
sd.bdev = blkdev_get_by_path(dev_name, mode, fs_type);
snprintf(s->s_id, sizeof(s->s_id), "%pg", sd.bdev);
sb_set_blocksize(s, block_size(sd.bdev));
- err = nilfs_fill_super(s, data, flags & MS_SILENT ? 1 : 0);
+ err = nilfs_fill_super(s, data, flags & SB_SILENT ? 1 : 0);
if (err)
goto failed_super;
- s->s_flags |= MS_ACTIVE;
+ s->s_flags |= SB_ACTIVE;
} else if (!sd.cno) {
if (nilfs_tree_is_busy(s->s_root)) {
- if ((flags ^ s->s_flags) & MS_RDONLY) {
+ if ((flags ^ s->s_flags) & SB_RDONLY) {
nilfs_msg(s, KERN_ERR,
"the device already has a %s mount.",
sb_rdonly(s) ? "read-only" : "read/write");
if (!valid_fs) {
nilfs_msg(sb, KERN_WARNING, "mounting unchecked fs");
- if (s_flags & MS_RDONLY) {
+ if (s_flags & SB_RDONLY) {
nilfs_msg(sb, KERN_INFO,
"recovery required for readonly filesystem");
nilfs_msg(sb, KERN_INFO,
if (valid_fs)
goto skip_recovery;
- if (s_flags & MS_RDONLY) {
+ if (s_flags & SB_RDONLY) {
__u64 features;
if (nilfs_test_opt(nilfs, NORECOVERY)) {
err = -EROFS;
goto failed_unload;
}
- sb->s_flags &= ~MS_RDONLY;
+ sb->s_flags &= ~SB_RDONLY;
} else if (nilfs_test_opt(nilfs, NORECOVERY)) {
nilfs_msg(sb, KERN_ERR,
"recovery cancelled because norecovery option was specified for a read/write mount");
/*
* If i_count is zero, the inode cannot have any watches and
- * doing an __iget/iput with MS_ACTIVE clear would actually
+ * doing an __iget/iput with SB_ACTIVE clear would actually
* evict all inodes with zero i_count from icache which is
* unnecessarily violent and may in fact be illegal to do.
*/
nsfs_mnt = kern_mount(&nsfs);
if (IS_ERR(nsfs_mnt))
panic("can't set nsfs up\n");
- nsfs_mnt->mnt_sb->s_flags &= ~MS_NOUSER;
+ nsfs_mnt->mnt_sb->s_flags &= ~SB_NOUSER;
}
#ifndef NTFS_RW
/* For read-only compiled driver, enforce read-only flag. */
- *flags |= MS_RDONLY;
+ *flags |= SB_RDONLY;
#else /* NTFS_RW */
/*
* For the read-write compiled driver, if we are remounting read-write,
* When remounting read-only, mark the volume clean if no volume errors
* have occurred.
*/
- if (sb_rdonly(sb) && !(*flags & MS_RDONLY)) {
+ if (sb_rdonly(sb) && !(*flags & SB_RDONLY)) {
static const char *es = ". Cannot remount read-write.";
/* Remounting read-write. */
NVolSetErrors(vol);
return -EROFS;
}
- } else if (!sb_rdonly(sb) && (*flags & MS_RDONLY)) {
+ } else if (!sb_rdonly(sb) && (*flags & SB_RDONLY)) {
/* Remounting read-only. */
if (!NVolErrors(vol)) {
if (ntfs_clear_volume_flags(vol, VOLUME_IS_DIRTY))
es3);
goto iput_mirr_err_out;
}
- sb->s_flags |= MS_RDONLY;
+ sb->s_flags |= SB_RDONLY;
ntfs_error(sb, "%s. Mounting read-only%s",
!vol->mftmirr_ino ? es1 : es2, es3);
} else
es1, es2);
goto iput_vol_err_out;
}
- sb->s_flags |= MS_RDONLY;
+ sb->s_flags |= SB_RDONLY;
ntfs_error(sb, "%s. Mounting read-only%s", es1, es2);
} else
ntfs_warning(sb, "%s. Will not be able to remount "
}
goto iput_logfile_err_out;
}
- sb->s_flags |= MS_RDONLY;
+ sb->s_flags |= SB_RDONLY;
ntfs_error(sb, "%s. Mounting read-only%s", es1, es2);
} else
ntfs_warning(sb, "%s. Will not be able to remount "
es1, es2);
goto iput_root_err_out;
}
- sb->s_flags |= MS_RDONLY;
+ sb->s_flags |= SB_RDONLY;
ntfs_error(sb, "%s. Mounting read-only%s", es1, es2);
} else
ntfs_warning(sb, "%s. Will not be able to remount "
goto iput_root_err_out;
}
ntfs_error(sb, "%s. Mounting read-only%s", es1, es2);
- sb->s_flags |= MS_RDONLY;
+ sb->s_flags |= SB_RDONLY;
/*
* Do not set NVolErrors() because ntfs_remount() might manage
* to set the dirty flag in which case all would be well.
* If (still) a read-write mount, set the NT4 compatibility flag on
* newer NTFS version volumes.
*/
- if (!(sb->s_flags & MS_RDONLY) && (vol->major_ver > 1) &&
+ if (!(sb->s_flags & SB_RDONLY) && (vol->major_ver > 1) &&
ntfs_set_volume_flags(vol, VOLUME_MOUNTED_ON_NT4)) {
static const char *es1 = "Failed to set NT4 compatibility flag";
static const char *es2 = ". Run chkdsk.";
goto iput_root_err_out;
}
ntfs_error(sb, "%s. Mounting read-only%s", es1, es2);
- sb->s_flags |= MS_RDONLY;
+ sb->s_flags |= SB_RDONLY;
NVolSetErrors(vol);
}
#endif
goto iput_root_err_out;
}
ntfs_error(sb, "%s. Mounting read-only%s", es1, es2);
- sb->s_flags |= MS_RDONLY;
+ sb->s_flags |= SB_RDONLY;
NVolSetErrors(vol);
}
#endif /* NTFS_RW */
es1, es2);
goto iput_quota_err_out;
}
- sb->s_flags |= MS_RDONLY;
+ sb->s_flags |= SB_RDONLY;
ntfs_error(sb, "%s. Mounting read-only%s", es1, es2);
} else
ntfs_warning(sb, "%s. Will not be able to remount "
goto iput_quota_err_out;
}
ntfs_error(sb, "%s. Mounting read-only%s", es1, es2);
- sb->s_flags |= MS_RDONLY;
+ sb->s_flags |= SB_RDONLY;
NVolSetErrors(vol);
}
/*
es1, es2);
goto iput_usnjrnl_err_out;
}
- sb->s_flags |= MS_RDONLY;
+ sb->s_flags |= SB_RDONLY;
ntfs_error(sb, "%s. Mounting read-only%s", es1, es2);
} else
ntfs_warning(sb, "%s. Will not be able to remount "
goto iput_usnjrnl_err_out;
}
ntfs_error(sb, "%s. Mounting read-only%s", es1, es2);
- sb->s_flags |= MS_RDONLY;
+ sb->s_flags |= SB_RDONLY;
NVolSetErrors(vol);
}
#endif /* NTFS_RW */
lockdep_off();
ntfs_debug("Entering.");
#ifndef NTFS_RW
- sb->s_flags |= MS_RDONLY;
+ sb->s_flags |= SB_RDONLY;
#endif /* ! NTFS_RW */
/* Allocate a new ntfs_volume and place it in sb->s_fs_info. */
sb->s_fs_info = kmalloc(sizeof(ntfs_volume), GFP_NOFS);
return 0;
if ((inode->i_flags & S_NOATIME) ||
- ((inode->i_sb->s_flags & MS_NODIRATIME) && S_ISDIR(inode->i_mode)))
+ ((inode->i_sb->s_flags & SB_NODIRATIME) && S_ISDIR(inode->i_mode)))
return 0;
/*
}
/* We're going to/from readonly mode. */
- if ((bool)(*flags & MS_RDONLY) != sb_rdonly(sb)) {
+ if ((bool)(*flags & SB_RDONLY) != sb_rdonly(sb)) {
/* Disable quota accounting before remounting RO */
- if (*flags & MS_RDONLY) {
+ if (*flags & SB_RDONLY) {
ret = ocfs2_susp_quotas(osb, 0);
if (ret < 0)
goto out;
goto unlock_osb;
}
- if (*flags & MS_RDONLY) {
- sb->s_flags |= MS_RDONLY;
+ if (*flags & SB_RDONLY) {
+ sb->s_flags |= SB_RDONLY;
osb->osb_flags |= OCFS2_OSB_SOFT_RO;
} else {
if (osb->osb_flags & OCFS2_OSB_ERROR_FS) {
ret = -EINVAL;
goto unlock_osb;
}
- sb->s_flags &= ~MS_RDONLY;
+ sb->s_flags &= ~SB_RDONLY;
osb->osb_flags &= ~OCFS2_OSB_SOFT_RO;
}
trace_ocfs2_remount(sb->s_flags, osb->osb_flags, *flags);
unlock_osb:
spin_unlock(&osb->osb_lock);
/* Enable quota accounting after remounting RW */
- if (!ret && !(*flags & MS_RDONLY)) {
+ if (!ret && !(*flags & SB_RDONLY)) {
if (sb_any_quota_suspended(sb))
ret = ocfs2_susp_quotas(osb, 1);
else
if (ret < 0) {
/* Return back changes... */
spin_lock(&osb->osb_lock);
- sb->s_flags |= MS_RDONLY;
+ sb->s_flags |= SB_RDONLY;
osb->osb_flags |= OCFS2_OSB_SOFT_RO;
spin_unlock(&osb->osb_lock);
goto out;
if (!ocfs2_is_hard_readonly(osb))
ocfs2_set_journal_params(osb);
- sb->s_flags = (sb->s_flags & ~MS_POSIXACL) |
+ sb->s_flags = (sb->s_flags & ~SB_POSIXACL) |
((osb->s_mount_opt & OCFS2_MOUNT_POSIX_ACL) ?
- MS_POSIXACL : 0);
+ SB_POSIXACL : 0);
}
out:
return ret;
sb->s_magic = OCFS2_SUPER_MAGIC;
- sb->s_flags = (sb->s_flags & ~(MS_POSIXACL | MS_NOSEC)) |
- ((osb->s_mount_opt & OCFS2_MOUNT_POSIX_ACL) ? MS_POSIXACL : 0);
+ sb->s_flags = (sb->s_flags & ~(SB_POSIXACL | SB_NOSEC)) |
+ ((osb->s_mount_opt & OCFS2_MOUNT_POSIX_ACL) ? SB_POSIXACL : 0);
- /* Hard readonly mode only if: bdev_read_only, MS_RDONLY,
+ /* Hard readonly mode only if: bdev_read_only, SB_RDONLY,
* heartbeat=none */
if (bdev_read_only(sb->s_bdev)) {
if (!sb_rdonly(sb)) {
sb->s_quota_types = QTYPE_MASK_USR | QTYPE_MASK_GRP;
sb->s_xattr = ocfs2_xattr_handlers;
sb->s_time_gran = 1;
- sb->s_flags |= MS_NOATIME;
+ sb->s_flags |= SB_NOATIME;
/* this is needed to support O_LARGEFILE */
cbits = le32_to_cpu(di->id2.i_super.s_clustersize_bits);
bbits = le32_to_cpu(di->id2.i_super.s_blocksize_bits);
return rv;
pr_crit("OCFS2: File system is now read-only.\n");
- sb->s_flags |= MS_RDONLY;
+ sb->s_flags |= SB_RDONLY;
ocfs2_set_ro_flag(osb, 0);
}
case OCFS2_XATTR_INDEX_POSIX_ACL_ACCESS:
case OCFS2_XATTR_INDEX_POSIX_ACL_DEFAULT:
- if (!(sb->s_flags & MS_POSIXACL))
+ if (!(sb->s_flags & SB_POSIXACL))
return 0;
break;
static int openprom_remount(struct super_block *sb, int *flags, char *data)
{
sync_filesystem(sb);
- *flags |= MS_NOATIME;
+ *flags |= SB_NOATIME;
return 0;
}
struct op_inode_info *oi;
int ret;
- s->s_flags |= MS_NOATIME;
+ s->s_flags |= SB_NOATIME;
s->s_blocksize = 1024;
s->s_blocksize_bits = 10;
s->s_magic = OPENPROM_SUPER_MAGIC;
{
struct orangefs_sb_info_s *orangefs_sb = ORANGEFS_SB(root->d_sb);
- if (root->d_sb->s_flags & MS_POSIXACL)
+ if (root->d_sb->s_flags & SB_POSIXACL)
seq_puts(m, ",acl");
if (orangefs_sb->flags & ORANGEFS_OPT_INTR)
seq_puts(m, ",intr");
* Force any potential flags that might be set from the mount
* to zero, ie, initialize to unset.
*/
- sb->s_flags &= ~MS_POSIXACL;
+ sb->s_flags &= ~SB_POSIXACL;
orangefs_sb->flags &= ~ORANGEFS_OPT_INTR;
orangefs_sb->flags &= ~ORANGEFS_OPT_LOCAL_LOCK;
token = match_token(p, tokens, args);
switch (token) {
case Opt_acl:
- sb->s_flags |= MS_POSIXACL;
+ sb->s_flags |= SB_POSIXACL;
break;
case Opt_intr:
orangefs_sb->flags |= ORANGEFS_OPT_INTR;
ret = orangefs_fill_sb(sb,
&new_op->downcall.resp.fs_mount, data,
- flags & MS_SILENT ? 1 : 0);
+ flags & SB_SILENT ? 1 : 0);
if (ret) {
d = ERR_PTR(ret);
{
struct ovl_fs *ofs = sb->s_fs_info;
- if (!(*flags & MS_RDONLY) && ovl_force_readonly(ofs))
+ if (!(*flags & SB_RDONLY) && ovl_force_readonly(ofs))
return -EROFS;
return 0;
goto out_err;
if (!ofs->workdir)
- sb->s_flags |= MS_RDONLY;
+ sb->s_flags |= SB_RDONLY;
sb->s_stack_depth = ofs->upper_mnt->mnt_sb->s_stack_depth;
sb->s_time_gran = ofs->upper_mnt->mnt_sb->s_time_gran;
/* If the upper fs is nonexistent, we mark overlayfs r/o too */
if (!ofs->upper_mnt)
- sb->s_flags |= MS_RDONLY;
+ sb->s_flags |= SB_RDONLY;
else if (ofs->upper_mnt->mnt_sb != ofs->same_sb)
ofs->same_sb = NULL;
goto out_free_oe;
if (!ofs->indexdir)
- sb->s_flags |= MS_RDONLY;
+ sb->s_flags |= SB_RDONLY;
}
/* Show index=off/on in /proc/mounts for any of the reasons above */
sb->s_op = &ovl_super_operations;
sb->s_xattr = ovl_xattr_handlers;
sb->s_fs_info = ofs;
- sb->s_flags |= MS_POSIXACL | MS_NOREMOTELOCK;
+ sb->s_flags |= SB_POSIXACL | SB_NOREMOTELOCK;
err = -ENOMEM;
root_dentry = d_make_root(ovl_new_inode(sb, S_IFDIR, 0));
save_stack_trace_tsk(task, &trace);
for (i = 0; i < trace.nr_entries; i++) {
- seq_printf(m, "[<%pK>] %pB\n",
- (void *)entries[i], (void *)entries[i]);
+ seq_printf(m, "[<0>] %pB\n", (void *)entries[i]);
}
unlock_trace(task);
}
/* User space would break if executables or devices appear on proc */
s->s_iflags |= SB_I_USERNS_VISIBLE | SB_I_NOEXEC | SB_I_NODEV;
- s->s_flags |= MS_NODIRATIME | MS_NOSUID | MS_NOEXEC;
+ s->s_flags |= SB_NODIRATIME | SB_NOSUID | SB_NOEXEC;
s->s_blocksize = 1024;
s->s_blocksize_bits = 10;
s->s_magic = PROC_SUPER_MAGIC;
{
struct pid_namespace *ns;
- if (flags & MS_KERNMOUNT) {
+ if (flags & SB_KERNMOUNT) {
ns = data;
data = NULL;
} else {
static int show_sb_opts(struct seq_file *m, struct super_block *sb)
{
static const struct proc_fs_info fs_info[] = {
- { MS_SYNCHRONOUS, ",sync" },
- { MS_DIRSYNC, ",dirsync" },
- { MS_MANDLOCK, ",mand" },
- { MS_LAZYTIME, ",lazytime" },
+ { SB_SYNCHRONOUS, ",sync" },
+ { SB_DIRSYNC, ",dirsync" },
+ { SB_MANDLOCK, ",mand" },
+ { SB_LAZYTIME, ",lazytime" },
{ 0, NULL }
};
const struct proc_fs_info *fs_infop;
sync_filesystem(sb);
qs = qnx4_sb(sb);
qs->Version = QNX4_VERSION;
- *flags |= MS_RDONLY;
+ *flags |= SB_RDONLY;
return 0;
}
s->s_op = &qnx4_sops;
s->s_magic = QNX4_SUPER_MAGIC;
- s->s_flags |= MS_RDONLY; /* Yup, read-only yet */
+ s->s_flags |= SB_RDONLY; /* Yup, read-only yet */
/* Check the superblock signature. Since the qnx4 code is
dangerous, we should leave as quickly as possible
static int qnx6_remount(struct super_block *sb, int *flags, char *data)
{
sync_filesystem(sb);
- *flags |= MS_RDONLY;
+ *flags |= SB_RDONLY;
return 0;
}
}
s->s_op = &qnx6_sops;
s->s_magic = QNX6_SUPER_MAGIC;
- s->s_flags |= MS_RDONLY; /* Yup, read-only yet */
+ s->s_flags |= SB_RDONLY; /* Yup, read-only yet */
/* ease the later tree level calculations */
sbi = QNX6_SB(s);
}
/* This routine is guarded by s_umount semaphore */
-static void add_dquot_ref(struct super_block *sb, int type)
+static int add_dquot_ref(struct super_block *sb, int type)
{
struct inode *inode, *old_inode = NULL;
#ifdef CONFIG_QUOTA_DEBUG
int reserved = 0;
#endif
+ int err = 0;
spin_lock(&sb->s_inode_list_lock);
list_for_each_entry(inode, &sb->s_inodes, i_sb_list) {
reserved = 1;
#endif
iput(old_inode);
- __dquot_initialize(inode, type);
+ err = __dquot_initialize(inode, type);
+ if (err) {
+ iput(inode);
+ goto out;
+ }
/*
* We hold a reference to 'inode' so it couldn't have been
}
spin_unlock(&sb->s_inode_list_lock);
iput(old_inode);
-
+out:
#ifdef CONFIG_QUOTA_DEBUG
if (reserved) {
quota_error(sb, "Writes happened before quota was turned on "
"Please run quotacheck(8)");
}
#endif
+ return err;
}
/*
dqopt->flags |= dquot_state_flag(flags, type);
spin_unlock(&dq_state_lock);
- add_dquot_ref(sb, type);
-
- return 0;
+ error = add_dquot_ref(sb, type);
+ if (error)
+ dquot_disable(sb, type, flags);
+ return error;
out_file_init:
dqopt->files[type] = NULL;
iput(inode);
pr_info("VFS: Dquot-cache hash table entries: %ld (order %ld,"
" %ld bytes)\n", nr_hash, order, (PAGE_SIZE << order));
- register_shrinker(&dqcache_shrinker);
+ if (register_shrinker(&dqcache_shrinker))
+ panic("Cannot register dquot shrinker");
return 0;
}
journal_end(th);
goto out_inserted_sd;
}
- } else if (inode->i_sb->s_flags & MS_POSIXACL) {
+ } else if (inode->i_sb->s_flags & SB_POSIXACL) {
reiserfs_warning(inode->i_sb, "jdm-13090",
"ACLs aren't enabled in the fs, "
"but vfs thinks they are!");
/*
* Cancel flushing of old commits. Note that neither of these works
* will be requeued because superblock is being shutdown and doesn't
- * have MS_ACTIVE set.
+ * have SB_ACTIVE set.
*/
reiserfs_cancel_old_flush(sb);
/* wait for all commits to finish */
* Avoid queueing work when sb is being shut down. Transaction
* will be flushed on journal shutdown.
*/
- if (sb->s_flags & MS_ACTIVE)
+ if (sb->s_flags & SB_ACTIVE)
queue_delayed_work(REISERFS_SB(sb)->commit_wq,
&journal->j_work, HZ / 10);
}
if (!journal->j_errno)
journal->j_errno = errno;
- sb->s_flags |= MS_RDONLY;
+ sb->s_flags |= SB_RDONLY;
set_bit(J_ABORTED, &journal->j_state);
#ifdef CONFIG_REISERFS_CHECK
return;
reiserfs_info(sb, "Remounting filesystem read-only\n");
- sb->s_flags |= MS_RDONLY;
+ sb->s_flags |= SB_RDONLY;
reiserfs_abort_journal(sb, -EIO);
}
printk(KERN_CRIT "REISERFS abort (device %s): %s\n", sb->s_id,
error_buf);
- sb->s_flags |= MS_RDONLY;
+ sb->s_flags |= SB_RDONLY;
reiserfs_abort_journal(sb, errno);
}
* Avoid scheduling flush when sb is being shut down. It can race
* with journal shutdown and free still queued delayed work.
*/
- if (sb_rdonly(s) || !(s->s_flags & MS_ACTIVE))
+ if (sb_rdonly(s) || !(s->s_flags & SB_ACTIVE))
return;
spin_lock(&sbi->old_work_lock);
#ifdef CONFIG_QUOTA
/* Needed for iput() to work correctly and not trash data */
- if (s->s_flags & MS_ACTIVE) {
+ if (s->s_flags & SB_ACTIVE) {
ms_active_set = 0;
} else {
ms_active_set = 1;
- s->s_flags |= MS_ACTIVE;
+ s->s_flags |= SB_ACTIVE;
}
/* Turn on quotas so that they are updated correctly */
for (i = 0; i < REISERFS_MAXQUOTAS; i++) {
reiserfs_write_lock(s);
if (ms_active_set)
/* Restore the flag back */
- s->s_flags &= ~MS_ACTIVE;
+ s->s_flags &= ~SB_ACTIVE;
#endif
pathrelse(&path);
if (done)
goto out_err_unlock;
}
- if (*mount_flags & MS_RDONLY) {
+ if (*mount_flags & SB_RDONLY) {
reiserfs_write_unlock(s);
reiserfs_xattr_init(s, *mount_flags);
/* remount read-only */
REISERFS_SB(s)->s_mount_state = sb_umount_state(rs);
/* now it is safe to call journal_begin */
- s->s_flags &= ~MS_RDONLY;
+ s->s_flags &= ~SB_RDONLY;
err = journal_begin(&th, s, 10);
if (err)
goto out_err_unlock;
/* Mount a partition which is read-only, read-write */
reiserfs_prepare_for_journal(s, SB_BUFFER_WITH_SB(s), 1);
REISERFS_SB(s)->s_mount_state = sb_umount_state(rs);
- s->s_flags &= ~MS_RDONLY;
+ s->s_flags &= ~SB_RDONLY;
set_sb_umount_state(rs, REISERFS_ERROR_FS);
if (!old_format_only(s))
set_sb_mnt_count(rs, sb_mnt_count(rs) + 1);
goto out_err_unlock;
reiserfs_write_unlock(s);
- if (!(*mount_flags & MS_RDONLY)) {
+ if (!(*mount_flags & SB_RDONLY)) {
dquot_resume(s, -1);
reiserfs_write_lock(s);
finish_unfinished(s);
if (bdev_read_only(s->s_bdev) && !sb_rdonly(s)) {
SWARN(silent, s, "clm-7000",
"Detected readonly device, marking FS readonly");
- s->s_flags |= MS_RDONLY;
+ s->s_flags |= SB_RDONLY;
}
args.objectid = REISERFS_ROOT_OBJECTID;
args.dirid = REISERFS_ROOT_PARENT_OBJECTID;
return err;
if (inode->i_size < off + len - towrite)
i_size_write(inode, off + len - towrite);
- inode->i_version++;
inode->i_mtime = inode->i_ctime = current_time(inode);
mark_inode_dirty(inode);
return len - towrite;
/*
* We need to take a copy of the mount flags since things like
- * MS_RDONLY don't get set until *after* we're called.
+ * SB_RDONLY don't get set until *after* we're called.
* mount_flags != mount_options
*/
int reiserfs_xattr_init(struct super_block *s, int mount_flags)
if (err)
goto error;
- if (d_really_is_negative(privroot) && !(mount_flags & MS_RDONLY)) {
+ if (d_really_is_negative(privroot) && !(mount_flags & SB_RDONLY)) {
inode_lock(d_inode(s->s_root));
err = create_privroot(REISERFS_SB(s)->priv_root);
inode_unlock(d_inode(s->s_root));
clear_bit(REISERFS_POSIXACL, &REISERFS_SB(s)->s_mount_opt);
}
- /* The super_block MS_POSIXACL must mirror the (no)acl mount option. */
+ /* The super_block SB_POSIXACL must mirror the (no)acl mount option. */
if (reiserfs_posixacl(s))
- s->s_flags |= MS_POSIXACL;
+ s->s_flags |= SB_POSIXACL;
else
- s->s_flags &= ~MS_POSIXACL;
+ s->s_flags &= ~SB_POSIXACL;
return err;
}
static int romfs_remount(struct super_block *sb, int *flags, char *data)
{
sync_filesystem(sb);
- *flags |= MS_RDONLY;
+ *flags |= SB_RDONLY;
return 0;
}
sb->s_maxbytes = 0xFFFFFFFF;
sb->s_magic = ROMFS_MAGIC;
- sb->s_flags |= MS_RDONLY | MS_NOATIME;
+ sb->s_flags |= SB_RDONLY | SB_NOATIME;
sb->s_op = &romfs_super_ops;
#ifdef CONFIG_ROMFS_ON_MTD
(u64) le64_to_cpu(sblk->id_table_start));
sb->s_maxbytes = MAX_LFS_FILESIZE;
- sb->s_flags |= MS_RDONLY;
+ sb->s_flags |= SB_RDONLY;
sb->s_op = &squashfs_super_ops;
err = -ENOMEM;
static int squashfs_remount(struct super_block *sb, int *flags, char *data)
{
sync_filesystem(sb);
- *flags |= MS_RDONLY;
+ *flags |= SB_RDONLY;
return 0;
}
static int flags_by_sb(int s_flags)
{
int flags = 0;
- if (s_flags & MS_SYNCHRONOUS)
+ if (s_flags & SB_SYNCHRONOUS)
flags |= ST_SYNCHRONOUS;
- if (s_flags & MS_MANDLOCK)
+ if (s_flags & SB_MANDLOCK)
flags |= ST_MANDLOCK;
- if (s_flags & MS_RDONLY)
+ if (s_flags & SB_RDONLY)
flags |= ST_RDONLY;
return flags;
}
void *ns;
bool new_sb;
- if (!(flags & MS_KERNMOUNT)) {
+ if (!(flags & SB_KERNMOUNT)) {
if (!kobj_ns_current_may_mount(KOBJ_NS_TYPE_NET))
return ERR_PTR(-EPERM);
}
sync_filesystem(sb);
if (sbi->s_forced_ro)
- *flags |= MS_RDONLY;
+ *flags |= SB_RDONLY;
return 0;
}
/* set up enough so that it can read an inode */
sb->s_op = &sysv_sops;
if (sbi->s_forced_ro)
- sb->s_flags |= MS_RDONLY;
+ sb->s_flags |= SB_RDONLY;
if (sbi->s_truncate)
sb->s_d_op = &sysv_dentry_operations;
root_inode = sysv_iget(sb, SYSV_ROOT_INO);
if (flags & S_MTIME)
inode->i_mtime = *time;
- if (!(inode->i_sb->s_flags & MS_LAZYTIME))
+ if (!(inode->i_sb->s_flags & SB_LAZYTIME))
iflags |= I_DIRTY_SYNC;
release = ui->dirty;
if (!c->ro_error) {
c->ro_error = 1;
c->no_chk_data_crc = 0;
- c->vfs_sb->s_flags |= MS_RDONLY;
+ c->vfs_sb->s_flags |= SB_RDONLY;
ubifs_warn(c, "switched to read-only mode, error %d", err);
dump_stack();
}
pr_notice("UBIFS: parse %s\n", option);
if (!strcmp(option, "sync"))
- return MS_SYNCHRONOUS;
+ return SB_SYNCHRONOUS;
return 0;
}
size_t sz;
c->ro_mount = !!sb_rdonly(c->vfs_sb);
- /* Suppress error messages while probing if MS_SILENT is set */
- c->probing = !!(c->vfs_sb->s_flags & MS_SILENT);
+ /* Suppress error messages while probing if SB_SILENT is set */
+ c->probing = !!(c->vfs_sb->s_flags & SB_SILENT);
err = init_constants_early(c);
if (err)
return err;
}
- if (c->ro_mount && !(*flags & MS_RDONLY)) {
+ if (c->ro_mount && !(*flags & SB_RDONLY)) {
if (c->ro_error) {
ubifs_msg(c, "cannot re-mount R/W due to prior errors");
return -EROFS;
err = ubifs_remount_rw(c);
if (err)
return err;
- } else if (!c->ro_mount && (*flags & MS_RDONLY)) {
+ } else if (!c->ro_mount && (*flags & SB_RDONLY)) {
if (c->ro_error) {
ubifs_msg(c, "cannot re-mount R/O due to prior errors");
return -EROFS;
*/
ubi = open_ubi(name, UBI_READONLY);
if (IS_ERR(ubi)) {
- if (!(flags & MS_SILENT))
+ if (!(flags & SB_SILENT))
pr_err("UBIFS error (pid: %d): cannot open \"%s\", error %d",
current->pid, name, (int)PTR_ERR(ubi));
return ERR_CAST(ubi);
kfree(c);
/* A new mount point for already mounted UBIFS */
dbg_gen("this ubi volume is already mounted");
- if (!!(flags & MS_RDONLY) != c1->ro_mount) {
+ if (!!(flags & SB_RDONLY) != c1->ro_mount) {
err = -EBUSY;
goto out_deact;
}
} else {
- err = ubifs_fill_super(sb, data, flags & MS_SILENT ? 1 : 0);
+ err = ubifs_fill_super(sb, data, flags & SB_SILENT ? 1 : 0);
if (err)
goto out_deact;
/* We do not support atime */
- sb->s_flags |= MS_ACTIVE;
+ sb->s_flags |= SB_ACTIVE;
#ifndef CONFIG_UBIFS_ATIME_SUPPORT
- sb->s_flags |= MS_NOATIME;
+ sb->s_flags |= SB_NOATIME;
#else
ubifs_msg(c, "full atime support is enabled.");
#endif
* @need_recovery: %1 if the file-system needs recovery
* @replaying: %1 during journal replay
* @mounting: %1 while mounting
- * @probing: %1 while attempting to mount if MS_SILENT mount flag is set
+ * @probing: %1 while attempting to mount if SB_SILENT mount flag is set
* @remounting_rw: %1 while re-mounting from R/O mode to R/W mode
* @replay_list: temporary list used during journal replay
* @replay_buds: list of buds to replay
void ubifs_warn(const struct ubifs_info *c, const char *fmt, ...);
/*
* A conditional variant of 'ubifs_err()' which doesn't output anything
- * if probing (ie. MS_SILENT set).
+ * if probing (ie. SB_SILENT set).
*/
#define ubifs_errc(c, fmt, ...) \
do { \
sync_filesystem(sb);
if (lvidiu) {
int write_rev = le16_to_cpu(lvidiu->minUDFWriteRev);
- if (write_rev > UDF_MAX_WRITE_VERSION && !(*flags & MS_RDONLY))
+ if (write_rev > UDF_MAX_WRITE_VERSION && !(*flags & SB_RDONLY))
return -EACCES;
}
sbi->s_dmode = uopt.dmode;
write_unlock(&sbi->s_cred_lock);
- if ((bool)(*flags & MS_RDONLY) == sb_rdonly(sb))
+ if ((bool)(*flags & SB_RDONLY) == sb_rdonly(sb))
goto out_unlock;
- if (*flags & MS_RDONLY)
+ if (*flags & SB_RDONLY)
udf_close_lvid(sb);
else
udf_open_lvid(sb);
ubh_mark_buffer_dirty (USPI_UBH(uspi));
ubh_mark_buffer_dirty (UCPI_UBH(ucpi));
- if (sb->s_flags & MS_SYNCHRONOUS)
+ if (sb->s_flags & SB_SYNCHRONOUS)
ubh_sync_block(UCPI_UBH(ucpi));
ufs_mark_sb_dirty(sb);
ubh_mark_buffer_dirty (USPI_UBH(uspi));
ubh_mark_buffer_dirty (UCPI_UBH(ucpi));
- if (sb->s_flags & MS_SYNCHRONOUS)
+ if (sb->s_flags & SB_SYNCHRONOUS)
ubh_sync_block(UCPI_UBH(ucpi));
if (overflow) {
ubh_mark_buffer_dirty (USPI_UBH(uspi));
ubh_mark_buffer_dirty (UCPI_UBH(ucpi));
- if (sb->s_flags & MS_SYNCHRONOUS)
+ if (sb->s_flags & SB_SYNCHRONOUS)
ubh_sync_block(UCPI_UBH(ucpi));
ufs_mark_sb_dirty(sb);
succed:
ubh_mark_buffer_dirty (USPI_UBH(uspi));
ubh_mark_buffer_dirty (UCPI_UBH(ucpi));
- if (sb->s_flags & MS_SYNCHRONOUS)
+ if (sb->s_flags & SB_SYNCHRONOUS)
ubh_sync_block(UCPI_UBH(ucpi));
ufs_mark_sb_dirty(sb);
ubh_mark_buffer_dirty (USPI_UBH(uspi));
ubh_mark_buffer_dirty (UCPI_UBH(ucpi));
- if (sb->s_flags & MS_SYNCHRONOUS)
+ if (sb->s_flags & SB_SYNCHRONOUS)
ubh_sync_block(UCPI_UBH(ucpi));
ufs_mark_sb_dirty(sb);
set_buffer_uptodate(bh);
mark_buffer_dirty(bh);
unlock_buffer(bh);
- if (sb->s_flags & MS_SYNCHRONOUS)
+ if (sb->s_flags & SB_SYNCHRONOUS)
sync_dirty_buffer(bh);
brelse(bh);
}
fs32_add(sb, &ucg->cg_u.cg_u2.cg_initediblk, uspi->s_inopb);
ubh_mark_buffer_dirty(UCPI_UBH(ucpi));
- if (sb->s_flags & MS_SYNCHRONOUS)
+ if (sb->s_flags & SB_SYNCHRONOUS)
ubh_sync_block(UCPI_UBH(ucpi));
UFSD("EXIT\n");
}
ubh_mark_buffer_dirty (USPI_UBH(uspi));
ubh_mark_buffer_dirty (UCPI_UBH(ucpi));
- if (sb->s_flags & MS_SYNCHRONOUS)
+ if (sb->s_flags & SB_SYNCHRONOUS)
ubh_sync_block(UCPI_UBH(ucpi));
ufs_mark_sb_dirty(sb);
ufs2_inode->ui_birthnsec = cpu_to_fs32(sb, ts.tv_nsec);
mark_buffer_dirty(bh);
unlock_buffer(bh);
- if (sb->s_flags & MS_SYNCHRONOUS)
+ if (sb->s_flags & SB_SYNCHRONOUS)
sync_dirty_buffer(bh);
brelse(bh);
}
usb1->fs_clean = UFS_FSBAD;
ubh_mark_buffer_dirty(USPI_UBH(uspi));
ufs_mark_sb_dirty(sb);
- sb->s_flags |= MS_RDONLY;
+ sb->s_flags |= SB_RDONLY;
}
va_start(args, fmt);
vaf.fmt = fmt;
va_start(args, fmt);
vaf.fmt = fmt;
vaf.va = &args;
- sb->s_flags |= MS_RDONLY;
+ sb->s_flags |= SB_RDONLY;
pr_crit("panic (device %s): %s: %pV\n",
sb->s_id, function, &vaf);
va_end(args);
if (!sb_rdonly(sb)) {
if (!silent)
pr_info("ufstype=old is supported read-only\n");
- sb->s_flags |= MS_RDONLY;
+ sb->s_flags |= SB_RDONLY;
}
break;
if (!sb_rdonly(sb)) {
if (!silent)
pr_info("ufstype=nextstep is supported read-only\n");
- sb->s_flags |= MS_RDONLY;
+ sb->s_flags |= SB_RDONLY;
}
break;
if (!sb_rdonly(sb)) {
if (!silent)
pr_info("ufstype=nextstep-cd is supported read-only\n");
- sb->s_flags |= MS_RDONLY;
+ sb->s_flags |= SB_RDONLY;
}
break;
if (!sb_rdonly(sb)) {
if (!silent)
pr_info("ufstype=openstep is supported read-only\n");
- sb->s_flags |= MS_RDONLY;
+ sb->s_flags |= SB_RDONLY;
}
break;
if (!sb_rdonly(sb)) {
if (!silent)
pr_info("ufstype=hp is supported read-only\n");
- sb->s_flags |= MS_RDONLY;
+ sb->s_flags |= SB_RDONLY;
}
break;
default:
break;
case UFS_FSACTIVE:
pr_err("%s(): fs is active\n", __func__);
- sb->s_flags |= MS_RDONLY;
+ sb->s_flags |= SB_RDONLY;
break;
case UFS_FSBAD:
pr_err("%s(): fs is bad\n", __func__);
- sb->s_flags |= MS_RDONLY;
+ sb->s_flags |= SB_RDONLY;
break;
default:
pr_err("%s(): can't grok fs_clean 0x%x\n",
__func__, usb1->fs_clean);
- sb->s_flags |= MS_RDONLY;
+ sb->s_flags |= SB_RDONLY;
break;
}
} else {
pr_err("%s(): fs needs fsck\n", __func__);
- sb->s_flags |= MS_RDONLY;
+ sb->s_flags |= SB_RDONLY;
}
/*
return -EINVAL;
}
- if ((bool)(*mount_flags & MS_RDONLY) == sb_rdonly(sb)) {
+ if ((bool)(*mount_flags & SB_RDONLY) == sb_rdonly(sb)) {
UFS_SB(sb)->s_mount_opt = new_mount_opt;
mutex_unlock(&UFS_SB(sb)->s_lock);
return 0;
/*
* fs was mouted as rw, remounting ro
*/
- if (*mount_flags & MS_RDONLY) {
+ if (*mount_flags & SB_RDONLY) {
ufs_put_super_internal(sb);
usb1->fs_time = cpu_to_fs32(sb, get_seconds());
if ((flags & UFS_ST_MASK) == UFS_ST_SUN
ufs_set_fs_state(sb, usb1, usb3,
UFS_FSOK - fs32_to_cpu(sb, usb1->fs_time));
ubh_mark_buffer_dirty (USPI_UBH(uspi));
- sb->s_flags |= MS_RDONLY;
+ sb->s_flags |= SB_RDONLY;
} else {
/*
* fs was mounted as ro, remounting rw
mutex_unlock(&UFS_SB(sb)->s_lock);
return -EPERM;
}
- sb->s_flags &= ~MS_RDONLY;
+ sb->s_flags &= ~SB_RDONLY;
#endif
}
UFS_SB(sb)->s_mount_opt = new_mount_opt;
* something to an unlinked inode, the irele won't cause
* premature truncation and freeing of the inode, which results
* in log recovery failure. We have to evict the unreferenced
- * lru inodes after clearing MS_ACTIVE because we don't
+ * lru inodes after clearing SB_ACTIVE because we don't
* otherwise clean up the lru if there's a subsequent failure in
* xfs_mountfs, which leads to us leaking the inodes if nothing
* else (e.g. quotacheck) references the inodes before the
* mount failure occurs.
*/
- mp->m_super->s_flags |= MS_ACTIVE;
+ mp->m_super->s_flags |= SB_ACTIVE;
error = xlog_recover_finish(mp->m_log);
if (!error)
xfs_log_work_queue(mp);
- mp->m_super->s_flags &= ~MS_ACTIVE;
+ mp->m_super->s_flags &= ~SB_ACTIVE;
evict_inodes(mp->m_super);
/*
*/
if (sb_rdonly(sb))
mp->m_flags |= XFS_MOUNT_RDONLY;
- if (sb->s_flags & MS_DIRSYNC)
+ if (sb->s_flags & SB_DIRSYNC)
mp->m_flags |= XFS_MOUNT_DIRSYNC;
- if (sb->s_flags & MS_SYNCHRONOUS)
+ if (sb->s_flags & SB_SYNCHRONOUS)
mp->m_flags |= XFS_MOUNT_WSYNC;
/*
}
/* ro -> rw */
- if ((mp->m_flags & XFS_MOUNT_RDONLY) && !(*flags & MS_RDONLY)) {
+ if ((mp->m_flags & XFS_MOUNT_RDONLY) && !(*flags & SB_RDONLY)) {
if (mp->m_flags & XFS_MOUNT_NORECOVERY) {
xfs_warn(mp,
"ro->rw transition prohibited on norecovery mount");
}
/* rw -> ro */
- if (!(mp->m_flags & XFS_MOUNT_RDONLY) && (*flags & MS_RDONLY)) {
+ if (!(mp->m_flags & XFS_MOUNT_RDONLY) && (*flags & SB_RDONLY)) {
/* Free the per-AG metadata reservation pool. */
error = xfs_fs_unreserve_ag_blocks(mp);
if (error) {
#ifdef CONFIG_XFS_POSIX_ACL
# define XFS_ACL_STRING "ACLs, "
-# define set_posix_acl_flag(sb) ((sb)->s_flags |= MS_POSIXACL)
+# define set_posix_acl_flag(sb) ((sb)->s_flags |= SB_POSIXACL)
#else
# define XFS_ACL_STRING
# define set_posix_acl_flag(sb) do { } while (0)
ACPI_BUS_TYPE_THERMAL,
ACPI_BUS_TYPE_POWER_BUTTON,
ACPI_BUS_TYPE_SLEEP_BUTTON,
+ ACPI_BUS_TYPE_ECDT_EC,
ACPI_BUS_DEVICE_TYPE_COUNT
};
#define ACPI_VIDEO_HID "LNXVIDEO"
#define ACPI_BAY_HID "LNXIOBAY"
#define ACPI_DOCK_HID "LNXDOCK"
+#define ACPI_ECDT_HID "LNXEC"
/* Quirk for broken IBM BIOSes */
#define ACPI_SMBUS_IBM_HID "SMBUSIBM"
{
return 0;
}
-#ifndef __HAVE_ARCH_PMD_WRITE
+#ifndef pmd_write
static inline int pmd_write(pmd_t pmd)
{
BUG();
return 0;
}
-#endif /* __HAVE_ARCH_PMD_WRITE */
+#endif /* pmd_write */
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+#ifndef pud_write
+static inline int pud_write(pud_t pud)
+{
+ BUG();
+ return 0;
+}
+#endif /* pud_write */
+
#if !defined(CONFIG_TRANSPARENT_HUGEPAGE) || \
(defined(CONFIG_TRANSPARENT_HUGEPAGE) && \
!defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD))
unsigned int ivsize);
ssize_t af_alg_sendpage(struct socket *sock, struct page *page,
int offset, size_t size, int flags);
+void af_alg_free_resources(struct af_alg_async_req *areq);
void af_alg_async_cb(struct crypto_async_request *_req, int err);
unsigned int af_alg_poll(struct file *file, struct socket *sock,
poll_table *wait);
drm_hdmi_avi_infoframe_quant_range(struct hdmi_avi_infoframe *frame,
const struct drm_display_mode *mode,
enum hdmi_quantization_range rgb_quant_range,
- bool rgb_quant_range_selectable);
+ bool rgb_quant_range_selectable,
+ bool is_hdmi2_sink);
/**
* drm_eld_mnl - Get ELD monitor name length in bytes.
void ttm_pool_unpopulate(struct ttm_tt *ttm);
/**
+ * Populates and DMA maps pages to fullfil a ttm_dma_populate() request
+ */
+int ttm_populate_and_map_pages(struct device *dev, struct ttm_dma_tt *tt);
+
+/**
+ * Unpopulates and DMA unmaps pages as part of a
+ * ttm_dma_unpopulate() request */
+void ttm_unmap_and_unpopulate_pages(struct device *dev, struct ttm_dma_tt *tt);
+
+/**
* Output the state of pools to debugfs file
*/
int ttm_page_alloc_debugfs(struct seq_file *m, void *data);
-
#if defined(CONFIG_SWIOTLB) || defined(CONFIG_INTEL_IOMMU)
/**
* Initialize pool allocator.
int ttm_dma_populate(struct ttm_dma_tt *ttm_dma, struct device *dev);
void ttm_dma_unpopulate(struct ttm_dma_tt *ttm_dma, struct device *dev);
-
-/**
- * Populates and DMA maps pages to fullfil a ttm_dma_populate() request
- */
-int ttm_populate_and_map_pages(struct device *dev, struct ttm_dma_tt *tt);
-
-/**
- * Unpopulates and DMA unmaps pages as part of a
- * ttm_dma_unpopulate() request */
-void ttm_unmap_and_unpopulate_pages(struct device *dev, struct ttm_dma_tt *tt);
-
#else
static inline int ttm_dma_page_alloc_init(struct ttm_mem_global *glob,
unsigned max_pages)
struct device *dev)
{
}
-
-static inline int ttm_populate_and_map_pages(struct device *dev, struct ttm_dma_tt *tt)
-{
- return -ENOMEM;
-}
-
-static inline void ttm_unmap_and_unpopulate_pages(struct device *dev, struct ttm_dma_tt *tt)
-{
-}
-
#endif
#endif
*/
#define __IS_FLG(inode, flg) ((inode)->i_sb->s_flags & (flg))
-static inline bool sb_rdonly(const struct super_block *sb) { return sb->s_flags & MS_RDONLY; }
+static inline bool sb_rdonly(const struct super_block *sb) { return sb->s_flags & SB_RDONLY; }
#define IS_RDONLY(inode) sb_rdonly((inode)->i_sb)
#define IS_SYNC(inode) (__IS_FLG(inode, SB_SYNCHRONOUS) || \
((inode)->i_flags & S_SYNC))
static inline int vfs_fstatat(int dfd, const char __user *filename,
struct kstat *stat, int flags)
{
- return vfs_statx(dfd, filename, flags, stat, STATX_BASIC_STATS);
+ return vfs_statx(dfd, filename, flags | AT_NO_AUTOMOUNT,
+ stat, STATX_BASIC_STATS);
}
static inline int vfs_fstat(int fd, struct kstat *stat)
{
return vma->vm_file && IS_DAX(vma->vm_file->f_mapping->host);
}
+static inline bool vma_is_fsdax(struct vm_area_struct *vma)
+{
+ struct inode *inode;
+
+ if (!vma->vm_file)
+ return false;
+ if (!vma_is_dax(vma))
+ return false;
+ inode = file_inode(vma->vm_file);
+ if (inode->i_mode == S_IFCHR)
+ return false; /* device-dax */
+ return true;
+}
+
static inline int iocb_flags(struct file *file)
{
int res = 0;
}
#endif
-#ifndef pud_write
-static inline int pud_write(pud_t pud)
-{
- BUG();
- return 0;
-}
-#endif
-
#define HUGETLB_ANON_FILE "anon_hugepage"
enum {
#define KSYM_SYMBOL_LEN (sizeof("%s+%#lx/%#lx [%s]") + (KSYM_NAME_LEN - 1) + \
2*(BITS_PER_LONG*3/10) + (MODULE_NAME_LEN - 1) + 1)
-#ifndef CONFIG_64BIT
-# define KALLSYM_FMT "%08lx"
-#else
-# define KALLSYM_FMT "%016lx"
-#endif
-
struct module;
#ifdef CONFIG_KALLSYMS
unsigned long len);
void kvm_vcpu_mark_page_dirty(struct kvm_vcpu *vcpu, gfn_t gfn);
+void kvm_sigset_activate(struct kvm_vcpu *vcpu);
+void kvm_sigset_deactivate(struct kvm_vcpu *vcpu);
+
void kvm_vcpu_block(struct kvm_vcpu *vcpu);
void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu);
void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu);
new_page = __alloc_pages_nodemask(gfp_mask, order,
preferred_nid, nodemask);
- if (new_page && PageTransHuge(page))
+ if (new_page && PageTransHuge(new_page))
prep_transhuge_page(new_page);
return new_page;
struct vm_operations_struct {
void (*open)(struct vm_area_struct * area);
void (*close)(struct vm_area_struct * area);
+ int (*split)(struct vm_area_struct * area, unsigned long addr);
int (*mremap)(struct vm_area_struct * area);
int (*fault)(struct vm_fault *vmf);
int (*huge_fault)(struct vm_fault *vmf, enum page_entry_size pe_size);
unsigned int gup_flags, struct page **pages, int *locked);
long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages,
struct page **pages, unsigned int gup_flags);
+#ifdef CONFIG_FS_DAX
+long get_user_pages_longterm(unsigned long start, unsigned long nr_pages,
+ unsigned int gup_flags, struct page **pages,
+ struct vm_area_struct **vmas);
+#else
+static inline long get_user_pages_longterm(unsigned long start,
+ unsigned long nr_pages, unsigned int gup_flags,
+ struct page **pages, struct vm_area_struct **vmas)
+{
+ return get_user_pages(start, nr_pages, gup_flags, pages, vmas);
+}
+#endif /* CONFIG_FS_DAX */
+
int get_user_pages_fast(unsigned long start, int nr_pages, int write,
struct page **pages);
extern int cache_register_net(struct cache_detail *cd, struct net *net);
extern void cache_unregister_net(struct cache_detail *cd, struct net *net);
-extern struct cache_detail *cache_create_net(struct cache_detail *tmpl, struct net *net);
+extern struct cache_detail *cache_create_net(const struct cache_detail *tmpl, struct net *net);
extern void cache_destroy_net(struct cache_detail *cd, struct net *net);
extern void sunrpc_init_cache_detail(struct cache_detail *cd);
* ieee80211_nullfunc_get - retrieve a nullfunc template
* @hw: pointer obtained from ieee80211_alloc_hw().
* @vif: &struct ieee80211_vif pointer from the add_interface callback.
+ * @qos_ok: QoS NDP is acceptable to the caller, this should be set
+ * if at all possible
*
* Creates a Nullfunc template which can, for example, uploaded to
* hardware. The template must be updated after association so that correct
* BSSID and address is used.
*
+ * If @qos_ndp is set and the association is to an AP with QoS/WMM, the
+ * returned packet will be QoS NDP.
+ *
* Note: Caller (or hardware) is responsible for setting the
* &IEEE80211_FCTL_PM bit as well as Duration and Sequence Control fields.
*
* Return: The nullfunc template. %NULL on error.
*/
struct sk_buff *ieee80211_nullfunc_get(struct ieee80211_hw *hw,
- struct ieee80211_vif *vif);
+ struct ieee80211_vif *vif,
+ bool qos_ok);
/**
* ieee80211_probereq_get - retrieve a Probe Request template
/* This uses the crypto implementation of crc32c, which is either
* implemented w/ hardware support or resolves to __crc32c_le().
*/
- return crc32c(sum, buff, len);
+ return (__force __wsum)crc32c((__force __u32)sum, buff, len);
}
static inline __wsum sctp_csum_combine(__wsum csum, __wsum csum2,
int offset, int len)
{
- return __crc32c_le_combine(csum, csum2, len);
+ return (__force __wsum)__crc32c_le_combine((__force __u32)csum,
+ (__force __u32)csum2, len);
}
static inline __le32 sctp_compute_cksum(const struct sk_buff *skb,
unsigned int offset)
{
struct sctphdr *sh = sctp_hdr(skb);
- __le32 ret, old = sh->checksum;
const struct skb_checksum_ops ops = {
.update = sctp_csum_update,
.combine = sctp_csum_combine,
};
+ __le32 old = sh->checksum;
+ __wsum new;
sh->checksum = 0;
- ret = cpu_to_le32(~__skb_checksum(skb, offset, skb->len - offset,
- ~(__u32)0, &ops));
+ new = ~__skb_checksum(skb, offset, skb->len - offset, ~(__wsum)0, &ops);
sh->checksum = old;
- return ret;
+ return cpu_to_le32((__force __u32)new);
}
#endif /* __sctp_checksum_h__ */
int sctp_offload_init(void);
/*
+ * sctp/stream_sched.c
+ */
+void sctp_sched_ops_init(void);
+
+/*
* sctp/stream.c
*/
int sctp_send_reset_streams(struct sctp_association *asoc,
int sctp_sched_init_sid(struct sctp_stream *stream, __u16 sid, gfp_t gfp);
struct sctp_sched_ops *sctp_sched_ops_from_stream(struct sctp_stream *stream);
+void sctp_sched_ops_register(enum sctp_sched_type sched,
+ struct sctp_sched_ops *sched_ops);
+void sctp_sched_ops_prio_init(void);
+void sctp_sched_ops_rr_init(void);
+
#endif /* __sctp_stream_sched_h__ */
rxrpc_conn_put_client,
rxrpc_conn_put_service,
rxrpc_conn_queued,
+ rxrpc_conn_reap_service,
rxrpc_conn_seen,
};
enum rxrpc_timer_trace {
rxrpc_timer_begin,
+ rxrpc_timer_exp_ack,
+ rxrpc_timer_exp_hard,
+ rxrpc_timer_exp_idle,
+ rxrpc_timer_exp_keepalive,
+ rxrpc_timer_exp_lost_ack,
+ rxrpc_timer_exp_normal,
+ rxrpc_timer_exp_ping,
+ rxrpc_timer_exp_resend,
rxrpc_timer_expired,
rxrpc_timer_init_for_reply,
rxrpc_timer_init_for_send_reply,
+ rxrpc_timer_restart,
rxrpc_timer_set_for_ack,
+ rxrpc_timer_set_for_hard,
+ rxrpc_timer_set_for_idle,
+ rxrpc_timer_set_for_keepalive,
+ rxrpc_timer_set_for_lost_ack,
+ rxrpc_timer_set_for_normal,
rxrpc_timer_set_for_ping,
rxrpc_timer_set_for_resend,
rxrpc_timer_set_for_send,
enum rxrpc_propose_ack_trace {
rxrpc_propose_ack_client_tx_end,
rxrpc_propose_ack_input_data,
+ rxrpc_propose_ack_ping_for_keepalive,
rxrpc_propose_ack_ping_for_lost_ack,
rxrpc_propose_ack_ping_for_lost_reply,
rxrpc_propose_ack_ping_for_params,
EM(rxrpc_conn_put_client, "PTc") \
EM(rxrpc_conn_put_service, "PTs") \
EM(rxrpc_conn_queued, "QUE") \
+ EM(rxrpc_conn_reap_service, "RPs") \
E_(rxrpc_conn_seen, "SEE")
#define rxrpc_client_traces \
#define rxrpc_timer_traces \
EM(rxrpc_timer_begin, "Begin ") \
EM(rxrpc_timer_expired, "*EXPR*") \
+ EM(rxrpc_timer_exp_ack, "ExpAck") \
+ EM(rxrpc_timer_exp_hard, "ExpHrd") \
+ EM(rxrpc_timer_exp_idle, "ExpIdl") \
+ EM(rxrpc_timer_exp_keepalive, "ExpKA ") \
+ EM(rxrpc_timer_exp_lost_ack, "ExpLoA") \
+ EM(rxrpc_timer_exp_normal, "ExpNml") \
+ EM(rxrpc_timer_exp_ping, "ExpPng") \
+ EM(rxrpc_timer_exp_resend, "ExpRsn") \
EM(rxrpc_timer_init_for_reply, "IniRpl") \
EM(rxrpc_timer_init_for_send_reply, "SndRpl") \
+ EM(rxrpc_timer_restart, "Restrt") \
EM(rxrpc_timer_set_for_ack, "SetAck") \
+ EM(rxrpc_timer_set_for_hard, "SetHrd") \
+ EM(rxrpc_timer_set_for_idle, "SetIdl") \
+ EM(rxrpc_timer_set_for_keepalive, "KeepAl") \
+ EM(rxrpc_timer_set_for_lost_ack, "SetLoA") \
+ EM(rxrpc_timer_set_for_normal, "SetNml") \
EM(rxrpc_timer_set_for_ping, "SetPng") \
EM(rxrpc_timer_set_for_resend, "SetRTx") \
- E_(rxrpc_timer_set_for_send, "SetTx ")
+ E_(rxrpc_timer_set_for_send, "SetSnd")
#define rxrpc_propose_ack_traces \
EM(rxrpc_propose_ack_client_tx_end, "ClTxEnd") \
EM(rxrpc_propose_ack_input_data, "DataIn ") \
+ EM(rxrpc_propose_ack_ping_for_keepalive, "KeepAlv") \
EM(rxrpc_propose_ack_ping_for_lost_ack, "LostAck") \
EM(rxrpc_propose_ack_ping_for_lost_reply, "LostRpl") \
EM(rxrpc_propose_ack_ping_for_params, "Params ") \
TRACE_EVENT(rxrpc_timer,
TP_PROTO(struct rxrpc_call *call, enum rxrpc_timer_trace why,
- ktime_t now, unsigned long now_j),
+ unsigned long now),
- TP_ARGS(call, why, now, now_j),
+ TP_ARGS(call, why, now),
TP_STRUCT__entry(
__field(struct rxrpc_call *, call )
__field(enum rxrpc_timer_trace, why )
- __field_struct(ktime_t, now )
- __field_struct(ktime_t, expire_at )
- __field_struct(ktime_t, ack_at )
- __field_struct(ktime_t, resend_at )
- __field(unsigned long, now_j )
- __field(unsigned long, timer )
+ __field(long, now )
+ __field(long, ack_at )
+ __field(long, ack_lost_at )
+ __field(long, resend_at )
+ __field(long, ping_at )
+ __field(long, expect_rx_by )
+ __field(long, expect_req_by )
+ __field(long, expect_term_by )
+ __field(long, timer )
),
TP_fast_assign(
- __entry->call = call;
- __entry->why = why;
- __entry->now = now;
- __entry->expire_at = call->expire_at;
- __entry->ack_at = call->ack_at;
- __entry->resend_at = call->resend_at;
- __entry->now_j = now_j;
- __entry->timer = call->timer.expires;
+ __entry->call = call;
+ __entry->why = why;
+ __entry->now = now;
+ __entry->ack_at = call->ack_at;
+ __entry->ack_lost_at = call->ack_lost_at;
+ __entry->resend_at = call->resend_at;
+ __entry->expect_rx_by = call->expect_rx_by;
+ __entry->expect_req_by = call->expect_req_by;
+ __entry->expect_term_by = call->expect_term_by;
+ __entry->timer = call->timer.expires;
),
- TP_printk("c=%p %s x=%lld a=%lld r=%lld t=%ld",
+ TP_printk("c=%p %s a=%ld la=%ld r=%ld xr=%ld xq=%ld xt=%ld t=%ld",
__entry->call,
__print_symbolic(__entry->why, rxrpc_timer_traces),
- ktime_to_ns(ktime_sub(__entry->expire_at, __entry->now)),
- ktime_to_ns(ktime_sub(__entry->ack_at, __entry->now)),
- ktime_to_ns(ktime_sub(__entry->resend_at, __entry->now)),
- __entry->timer - __entry->now_j)
+ __entry->ack_at - __entry->now,
+ __entry->ack_lost_at - __entry->now,
+ __entry->resend_at - __entry->now,
+ __entry->expect_rx_by - __entry->now,
+ __entry->expect_req_by - __entry->now,
+ __entry->expect_term_by - __entry->now,
+ __entry->timer - __entry->now)
);
TRACE_EVENT(rxrpc_rx_lose,
memcpy(&__entry->sum, summary, sizeof(__entry->sum));
),
- TP_printk("c=%p %08x %s %08x %s cw=%u ss=%u nr=%u,%u nw=%u,%u r=%u b=%u u=%u d=%u l=%x%s%s%s",
+ TP_printk("c=%p r=%08x %s q=%08x %s cw=%u ss=%u nr=%u,%u nw=%u,%u r=%u b=%u u=%u d=%u l=%x%s%s%s",
__entry->call,
__entry->ack_serial,
__print_symbolic(__entry->sum.ack_reason, rxrpc_ack_names),
#define PTR_CHECK_DEV ((1 << PTR_DEV_BITS) - 1)
-#define PTR(gen, offset, dev) \
+#define MAKE_PTR(gen, offset, dev) \
((((__u64) dev) << 51) | ((__u64) offset) << 8 | gen)
/* Bkey utility code */
#define BFS_FILEBLOCKS(ip) \
((ip)->i_sblock == 0 ? 0 : (le32_to_cpu((ip)->i_eblock) + 1) - le32_to_cpu((ip)->i_sblock))
#define BFS_UNCLEAN(bfs_sb, sb) \
- ((le32_to_cpu(bfs_sb->s_from) != -1) && (le32_to_cpu(bfs_sb->s_to) != -1) && !(sb->s_flags & MS_RDONLY))
+ ((le32_to_cpu(bfs_sb->s_from) != -1) && (le32_to_cpu(bfs_sb->s_to) != -1) && !(sb->s_flags & SB_RDONLY))
#endif /* _LINUX_BFS_FS_H */
};
struct kfd_ioctl_set_scratch_backing_va_args {
- uint64_t va_addr; /* to KFD */
- uint32_t gpu_id; /* to KFD */
- uint32_t pad;
+ __u64 va_addr; /* to KFD */
+ __u32 gpu_id; /* to KFD */
+ __u32 pad;
};
struct kfd_ioctl_get_tile_config_args {
/* to KFD: pointer to tile array */
- uint64_t tile_config_ptr;
+ __u64 tile_config_ptr;
/* to KFD: pointer to macro tile array */
- uint64_t macro_tile_config_ptr;
+ __u64 macro_tile_config_ptr;
/* to KFD: array size allocated by user mode
* from KFD: array size filled by kernel
*/
- uint32_t num_tile_configs;
+ __u32 num_tile_configs;
/* to KFD: array size allocated by user mode
* from KFD: array size filled by kernel
*/
- uint32_t num_macro_tile_configs;
+ __u32 num_macro_tile_configs;
- uint32_t gpu_id; /* to KFD */
- uint32_t gb_addr_config; /* from KFD */
- uint32_t num_banks; /* from KFD */
- uint32_t num_ranks; /* from KFD */
+ __u32 gpu_id; /* to KFD */
+ __u32 gb_addr_config; /* from KFD */
+ __u32 num_banks; /* from KFD */
+ __u32 num_ranks; /* from KFD */
/* struct size can be extended later if needed
* without breaking ABI compatibility
*/
RXRPC_EXCLUSIVE_CALL = 10, /* s-: Call should be on exclusive connection */
RXRPC_UPGRADE_SERVICE = 11, /* s-: Request service upgrade for client call */
RXRPC_TX_LENGTH = 12, /* s-: Total length of Tx data */
+ RXRPC_SET_CALL_TIMEOUT = 13, /* s-: Set one or more call timeouts */
RXRPC__SUPPORTED
};
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
/* AF_VSOCK sock_diag(7) interface for querying open sockets */
#ifndef _UAPI__VM_SOCKETS_DIAG_H__
void *data)
{
struct ipc_namespace *ns;
- if (flags & MS_KERNMOUNT) {
+ if (flags & SB_KERNMOUNT) {
ns = data;
data = NULL;
} else {
static int s_show(struct seq_file *m, void *p)
{
- unsigned long value;
+ void *value;
struct kallsym_iter *iter = m->private;
/* Some debugging symbols have no name. Ignore them. */
if (!iter->name[0])
return 0;
- value = iter->show_value ? iter->value : 0;
+ value = iter->show_value ? (void *)iter->value : NULL;
if (iter->module_name[0]) {
char type;
*/
type = iter->exported ? toupper(iter->type) :
tolower(iter->type);
- seq_printf(m, KALLSYM_FMT " %c %s\t[%s]\n", value,
+ seq_printf(m, "%px %c %s\t[%s]\n", value,
type, iter->name, iter->module_name);
} else
- seq_printf(m, KALLSYM_FMT " %c %s\n", value,
+ seq_printf(m, "%px %c %s\n", value,
iter->type, iter->name);
return 0;
}
{
struct module *mod = list_entry(p, struct module, list);
char buf[MODULE_FLAGS_BUF_SIZE];
- unsigned long value;
+ void *value;
/* We always ignore unformed modules. */
if (mod->state == MODULE_STATE_UNFORMED)
mod->state == MODULE_STATE_COMING ? "Loading" :
"Live");
/* Used by oprofile and other similar tools. */
- value = m->private ? 0 : (unsigned long)mod->core_layout.base;
- seq_printf(m, " 0x" KALLSYM_FMT, value);
+ value = m->private ? NULL : mod->core_layout.base;
+ seq_printf(m, " 0x%px", value);
/* Taints info */
if (mod->taints)
return ret;
if (copy_to_user(arg, &buts, sizeof(buts))) {
- blk_trace_remove(q);
+ __blk_trace_remove(q);
return -EFAULT;
}
return 0;
return ret;
if (copy_to_user(arg, &buts.name, ARRAY_SIZE(buts.name))) {
- blk_trace_remove(q);
+ __blk_trace_remove(q);
return -EFAULT;
}
*
**/
static void blk_add_trace_bio(struct request_queue *q, struct bio *bio,
- u32 what, int error, union kernfs_node_id *cgid)
+ u32 what, int error)
{
struct blk_trace *bt = q->blk_trace;
return;
__blk_add_trace(bt, bio->bi_iter.bi_sector, bio->bi_iter.bi_size,
- bio_op(bio), bio->bi_opf, what, error, 0, NULL, cgid);
+ bio_op(bio), bio->bi_opf, what, error, 0, NULL,
+ blk_trace_bio_get_cgid(q, bio));
}
static void blk_add_trace_bio_bounce(void *ignore,
struct request_queue *q, struct bio *bio)
{
- blk_add_trace_bio(q, bio, BLK_TA_BOUNCE, 0,
- blk_trace_bio_get_cgid(q, bio));
+ blk_add_trace_bio(q, bio, BLK_TA_BOUNCE, 0);
}
static void blk_add_trace_bio_complete(void *ignore,
struct request_queue *q, struct bio *bio,
int error)
{
- blk_add_trace_bio(q, bio, BLK_TA_COMPLETE, error,
- blk_trace_bio_get_cgid(q, bio));
+ blk_add_trace_bio(q, bio, BLK_TA_COMPLETE, error);
}
static void blk_add_trace_bio_backmerge(void *ignore,
struct request *rq,
struct bio *bio)
{
- blk_add_trace_bio(q, bio, BLK_TA_BACKMERGE, 0,
- blk_trace_bio_get_cgid(q, bio));
+ blk_add_trace_bio(q, bio, BLK_TA_BACKMERGE, 0);
}
static void blk_add_trace_bio_frontmerge(void *ignore,
struct request *rq,
struct bio *bio)
{
- blk_add_trace_bio(q, bio, BLK_TA_FRONTMERGE, 0,
- blk_trace_bio_get_cgid(q, bio));
+ blk_add_trace_bio(q, bio, BLK_TA_FRONTMERGE, 0);
}
static void blk_add_trace_bio_queue(void *ignore,
struct request_queue *q, struct bio *bio)
{
- blk_add_trace_bio(q, bio, BLK_TA_QUEUE, 0,
- blk_trace_bio_get_cgid(q, bio));
+ blk_add_trace_bio(q, bio, BLK_TA_QUEUE, 0);
}
static void blk_add_trace_getrq(void *ignore,
struct bio *bio, int rw)
{
if (bio)
- blk_add_trace_bio(q, bio, BLK_TA_GETRQ, 0,
- blk_trace_bio_get_cgid(q, bio));
+ blk_add_trace_bio(q, bio, BLK_TA_GETRQ, 0);
else {
struct blk_trace *bt = q->blk_trace;
struct bio *bio, int rw)
{
if (bio)
- blk_add_trace_bio(q, bio, BLK_TA_SLEEPRQ, 0,
- blk_trace_bio_get_cgid(q, bio));
+ blk_add_trace_bio(q, bio, BLK_TA_SLEEPRQ, 0);
else {
struct blk_trace *bt = q->blk_trace;
#include <linux/export.h>
-#include <lib/libgcc.h>
+#include <linux/libgcc.h>
long long notrace __ashldi3(long long u, word_type b)
{
#include <linux/export.h>
-#include <lib/libgcc.h>
+#include <linux/libgcc.h>
long long notrace __ashrdi3(long long u, word_type b)
{
#include <linux/export.h>
-#include <lib/libgcc.h>
+#include <linux/libgcc.h>
word_type notrace __cmpdi2(long long a, long long b)
{
*/
#include <linux/module.h>
-#include <lib/libgcc.h>
+#include <linux/libgcc.h>
long long notrace __lshrdi3(long long u, word_type b)
{
*/
#include <linux/export.h>
-#include <lib/libgcc.h>
+#include <linux/libgcc.h>
#define W_TYPE_SIZE 32
#define PAD_SIZE 16
#define FILL_CHAR '$'
-#define PTR1 ((void*)0x01234567)
-#define PTR2 ((void*)(long)(int)0xfedcba98)
-
-#if BITS_PER_LONG == 64
-#define PTR1_ZEROES "000000000"
-#define PTR1_SPACES " "
-#define PTR1_STR "1234567"
-#define PTR2_STR "fffffffffedcba98"
-#define PTR_WIDTH 16
-#else
-#define PTR1_ZEROES "0"
-#define PTR1_SPACES " "
-#define PTR1_STR "1234567"
-#define PTR2_STR "fedcba98"
-#define PTR_WIDTH 8
-#endif
-#define PTR_WIDTH_STR stringify(PTR_WIDTH)
-
static unsigned total_tests __initdata;
static unsigned failed_tests __initdata;
static char *test_buffer __initdata;
test("a | | ", "%-3.s|%-3.0s|%-3.*s", "a", "b", 0, "c");
}
+#define PLAIN_BUF_SIZE 64 /* leave some space so we don't oops */
+
+#if BITS_PER_LONG == 64
+
+#define PTR_WIDTH 16
+#define PTR ((void *)0xffff0123456789ab)
+#define PTR_STR "ffff0123456789ab"
+#define ZEROS "00000000" /* hex 32 zero bits */
+
+static int __init
+plain_format(void)
+{
+ char buf[PLAIN_BUF_SIZE];
+ int nchars;
+
+ nchars = snprintf(buf, PLAIN_BUF_SIZE, "%p", PTR);
+
+ if (nchars != PTR_WIDTH || strncmp(buf, ZEROS, strlen(ZEROS)) != 0)
+ return -1;
+
+ return 0;
+}
+
+#else
+
+#define PTR_WIDTH 8
+#define PTR ((void *)0x456789ab)
+#define PTR_STR "456789ab"
+
+static int __init
+plain_format(void)
+{
+ /* Format is implicitly tested for 32 bit machines by plain_hash() */
+ return 0;
+}
+
+#endif /* BITS_PER_LONG == 64 */
+
+static int __init
+plain_hash(void)
+{
+ char buf[PLAIN_BUF_SIZE];
+ int nchars;
+
+ nchars = snprintf(buf, PLAIN_BUF_SIZE, "%p", PTR);
+
+ if (nchars != PTR_WIDTH || strncmp(buf, PTR_STR, PTR_WIDTH) == 0)
+ return -1;
+
+ return 0;
+}
+
+/*
+ * We can't use test() to test %p because we don't know what output to expect
+ * after an address is hashed.
+ */
static void __init
plain(void)
{
- test(PTR1_ZEROES PTR1_STR " " PTR2_STR, "%p %p", PTR1, PTR2);
- /*
- * The field width is overloaded for some %p extensions to
- * pass another piece of information. For plain pointers, the
- * behaviour is slightly odd: One cannot pass either the 0
- * flag nor a precision to %p without gcc complaining, and if
- * one explicitly gives a field width, the number is no longer
- * zero-padded.
- */
- test("|" PTR1_STR PTR1_SPACES " | " PTR1_SPACES PTR1_STR "|",
- "|%-*p|%*p|", PTR_WIDTH+2, PTR1, PTR_WIDTH+2, PTR1);
- test("|" PTR2_STR " | " PTR2_STR "|",
- "|%-*p|%*p|", PTR_WIDTH+2, PTR2, PTR_WIDTH+2, PTR2);
+ int err;
- /*
- * Unrecognized %p extensions are treated as plain %p, but the
- * alphanumeric suffix is ignored (that is, does not occur in
- * the output.)
- */
- test("|"PTR1_ZEROES PTR1_STR"|", "|%p0y|", PTR1);
- test("|"PTR2_STR"|", "|%p0y|", PTR2);
+ err = plain_hash();
+ if (err) {
+ pr_warn("plain 'p' does not appear to be hashed\n");
+ failed_tests++;
+ return;
+ }
+
+ err = plain_format();
+ if (err) {
+ pr_warn("hashing plain 'p' has unexpected format\n");
+ failed_tests++;
+ }
}
static void __init
static void __init
kernel_ptr(void)
{
+ /* We can't test this without access to kptr_restrict. */
}
static void __init
*/
#include <linux/module.h>
-#include <lib/libgcc.h>
+#include <linux/libgcc.h>
word_type __ucmpdi2(unsigned long long a, unsigned long long b)
{
#include <linux/uuid.h>
#include <linux/of.h>
#include <net/addrconf.h>
+#include <linux/siphash.h>
+#include <linux/compiler.h>
#ifdef CONFIG_BLOCK
#include <linux/blkdev.h>
#endif
return string(buf, end, uuid, spec);
}
+int kptr_restrict __read_mostly;
+
+static noinline_for_stack
+char *restricted_pointer(char *buf, char *end, const void *ptr,
+ struct printf_spec spec)
+{
+ spec.base = 16;
+ spec.flags |= SMALL;
+ if (spec.field_width == -1) {
+ spec.field_width = 2 * sizeof(ptr);
+ spec.flags |= ZEROPAD;
+ }
+
+ switch (kptr_restrict) {
+ case 0:
+ /* Always print %pK values */
+ break;
+ case 1: {
+ const struct cred *cred;
+
+ /*
+ * kptr_restrict==1 cannot be used in IRQ context
+ * because its test for CAP_SYSLOG would be meaningless.
+ */
+ if (in_irq() || in_serving_softirq() || in_nmi())
+ return string(buf, end, "pK-error", spec);
+
+ /*
+ * Only print the real pointer value if the current
+ * process has CAP_SYSLOG and is running with the
+ * same credentials it started with. This is because
+ * access to files is checked at open() time, but %pK
+ * checks permission at read() time. We don't want to
+ * leak pointer values if a binary opens a file using
+ * %pK and then elevates privileges before reading it.
+ */
+ cred = current_cred();
+ if (!has_capability_noaudit(current, CAP_SYSLOG) ||
+ !uid_eq(cred->euid, cred->uid) ||
+ !gid_eq(cred->egid, cred->gid))
+ ptr = NULL;
+ break;
+ }
+ case 2:
+ default:
+ /* Always print 0's for %pK */
+ ptr = NULL;
+ break;
+ }
+
+ return number(buf, end, (unsigned long)ptr, spec);
+}
+
static noinline_for_stack
char *netdev_bits(char *buf, char *end, const void *addr, const char *fmt)
{
return widen_string(buf, buf - buf_start, end, spec);
}
-int kptr_restrict __read_mostly;
+static noinline_for_stack
+char *pointer_string(char *buf, char *end, const void *ptr,
+ struct printf_spec spec)
+{
+ spec.base = 16;
+ spec.flags |= SMALL;
+ if (spec.field_width == -1) {
+ spec.field_width = 2 * sizeof(ptr);
+ spec.flags |= ZEROPAD;
+ }
+
+ return number(buf, end, (unsigned long int)ptr, spec);
+}
+
+static bool have_filled_random_ptr_key __read_mostly;
+static siphash_key_t ptr_key __read_mostly;
+
+static void fill_random_ptr_key(struct random_ready_callback *unused)
+{
+ get_random_bytes(&ptr_key, sizeof(ptr_key));
+ /*
+ * have_filled_random_ptr_key==true is dependent on get_random_bytes().
+ * ptr_to_id() needs to see have_filled_random_ptr_key==true
+ * after get_random_bytes() returns.
+ */
+ smp_mb();
+ WRITE_ONCE(have_filled_random_ptr_key, true);
+}
+
+static struct random_ready_callback random_ready = {
+ .func = fill_random_ptr_key
+};
+
+static int __init initialize_ptr_random(void)
+{
+ int ret = add_random_ready_callback(&random_ready);
+
+ if (!ret) {
+ return 0;
+ } else if (ret == -EALREADY) {
+ fill_random_ptr_key(&random_ready);
+ return 0;
+ }
+
+ return ret;
+}
+early_initcall(initialize_ptr_random);
+
+/* Maps a pointer to a 32 bit unique identifier. */
+static char *ptr_to_id(char *buf, char *end, void *ptr, struct printf_spec spec)
+{
+ unsigned long hashval;
+ const int default_width = 2 * sizeof(ptr);
+
+ if (unlikely(!have_filled_random_ptr_key)) {
+ spec.field_width = default_width;
+ /* string length must be less than default_width */
+ return string(buf, end, "(ptrval)", spec);
+ }
+
+#ifdef CONFIG_64BIT
+ hashval = (unsigned long)siphash_1u64((u64)ptr, &ptr_key);
+ /*
+ * Mask off the first 32 bits, this makes explicit that we have
+ * modified the address (and 32 bits is plenty for a unique ID).
+ */
+ hashval = hashval & 0xffffffff;
+#else
+ hashval = (unsigned long)siphash_1u32((u32)ptr, &ptr_key);
+#endif
+
+ spec.flags |= SMALL;
+ if (spec.field_width == -1) {
+ spec.field_width = default_width;
+ spec.flags |= ZEROPAD;
+ }
+ spec.base = 16;
+
+ return number(buf, end, hashval, spec);
+}
/*
* Show a '%p' thing. A kernel extension is that the '%p' is followed
* c major compatible string
* C full compatible string
*
+ * - 'x' For printing the address. Equivalent to "%lx".
+ *
* ** Please update also Documentation/printk-formats.txt when making changes **
*
* Note: The difference between 'S' and 'F' is that on ia64 and ppc64
* function pointers are really function descriptors, which contain a
* pointer to the real address.
+ *
+ * Note: The default behaviour (unadorned %p) is to hash the address,
+ * rendering it useful as a unique identifier.
*/
static noinline_for_stack
char *pointer(const char *fmt, char *buf, char *end, void *ptr,
return buf;
}
case 'K':
- switch (kptr_restrict) {
- case 0:
- /* Always print %pK values */
- break;
- case 1: {
- const struct cred *cred;
-
- /*
- * kptr_restrict==1 cannot be used in IRQ context
- * because its test for CAP_SYSLOG would be meaningless.
- */
- if (in_irq() || in_serving_softirq() || in_nmi()) {
- if (spec.field_width == -1)
- spec.field_width = default_width;
- return string(buf, end, "pK-error", spec);
- }
-
- /*
- * Only print the real pointer value if the current
- * process has CAP_SYSLOG and is running with the
- * same credentials it started with. This is because
- * access to files is checked at open() time, but %pK
- * checks permission at read() time. We don't want to
- * leak pointer values if a binary opens a file using
- * %pK and then elevates privileges before reading it.
- */
- cred = current_cred();
- if (!has_capability_noaudit(current, CAP_SYSLOG) ||
- !uid_eq(cred->euid, cred->uid) ||
- !gid_eq(cred->egid, cred->gid))
- ptr = NULL;
- break;
- }
- case 2:
- default:
- /* Always print 0's for %pK */
- ptr = NULL;
+ if (!kptr_restrict)
break;
- }
- break;
-
+ return restricted_pointer(buf, end, ptr, spec);
case 'N':
return netdev_bits(buf, end, ptr, fmt);
case 'a':
case 'F':
return device_node_string(buf, end, ptr, spec, fmt + 1);
}
+ case 'x':
+ return pointer_string(buf, end, ptr, spec);
}
- spec.flags |= SMALL;
- if (spec.field_width == -1) {
- spec.field_width = default_width;
- spec.flags |= ZEROPAD;
- }
- spec.base = 16;
- return number(buf, end, (unsigned long) ptr, spec);
+ /* default is to _not_ leak addresses, hash before printing */
+ return ptr_to_id(buf, end, ptr, spec);
}
/*
.release = single_release,
};
-static void bdi_debug_register(struct backing_dev_info *bdi, const char *name)
+static int bdi_debug_register(struct backing_dev_info *bdi, const char *name)
{
+ if (!bdi_debug_root)
+ return -ENOMEM;
+
bdi->debug_dir = debugfs_create_dir(name, bdi_debug_root);
+ if (!bdi->debug_dir)
+ return -ENOMEM;
+
bdi->debug_stats = debugfs_create_file("stats", 0444, bdi->debug_dir,
bdi, &bdi_debug_stats_fops);
+ if (!bdi->debug_stats) {
+ debugfs_remove(bdi->debug_dir);
+ return -ENOMEM;
+ }
+
+ return 0;
}
static void bdi_debug_unregister(struct backing_dev_info *bdi)
static inline void bdi_debug_init(void)
{
}
-static inline void bdi_debug_register(struct backing_dev_info *bdi,
+static inline int bdi_debug_register(struct backing_dev_info *bdi,
const char *name)
{
+ return 0;
}
static inline void bdi_debug_unregister(struct backing_dev_info *bdi)
{
if (IS_ERR(dev))
return PTR_ERR(dev);
+ if (bdi_debug_register(bdi, dev_name(dev))) {
+ device_destroy(bdi_class, dev->devt);
+ return -ENOMEM;
+ }
cgwb_bdi_register(bdi);
bdi->dev = dev;
- bdi_debug_register(bdi, dev_name(dev));
set_bit(WB_registered, &bdi->wb.state);
spin_lock_bh(&bdi_lock);
ret = -EFAULT;
goto out;
}
+
+ /*
+ * While get_vaddr_frames() could be used for transient (kernel
+ * controlled lifetime) pinning of memory pages all current
+ * users establish long term (userspace controlled lifetime)
+ * page pinning. Treat get_vaddr_frames() like
+ * get_user_pages_longterm() and disallow it for filesystem-dax
+ * mappings.
+ */
+ if (vma_is_fsdax(vma))
+ return -EOPNOTSUPP;
+
if (!(vma->vm_flags & (VM_IO | VM_PFNMAP))) {
vec->got_ref = true;
vec->is_pfns = false;
*/
static inline bool can_follow_write_pte(pte_t pte, unsigned int flags)
{
- return pte_write(pte) ||
+ return pte_access_permitted(pte, WRITE) ||
((flags & FOLL_FORCE) && (flags & FOLL_COW) && pte_dirty(pte));
}
}
EXPORT_SYMBOL(get_user_pages);
+#ifdef CONFIG_FS_DAX
+/*
+ * This is the same as get_user_pages() in that it assumes we are
+ * operating on the current task's mm, but it goes further to validate
+ * that the vmas associated with the address range are suitable for
+ * longterm elevated page reference counts. For example, filesystem-dax
+ * mappings are subject to the lifetime enforced by the filesystem and
+ * we need guarantees that longterm users like RDMA and V4L2 only
+ * establish mappings that have a kernel enforced revocation mechanism.
+ *
+ * "longterm" == userspace controlled elevated page count lifetime.
+ * Contrast this to iov_iter_get_pages() usages which are transient.
+ */
+long get_user_pages_longterm(unsigned long start, unsigned long nr_pages,
+ unsigned int gup_flags, struct page **pages,
+ struct vm_area_struct **vmas_arg)
+{
+ struct vm_area_struct **vmas = vmas_arg;
+ struct vm_area_struct *vma_prev = NULL;
+ long rc, i;
+
+ if (!pages)
+ return -EINVAL;
+
+ if (!vmas) {
+ vmas = kcalloc(nr_pages, sizeof(struct vm_area_struct *),
+ GFP_KERNEL);
+ if (!vmas)
+ return -ENOMEM;
+ }
+
+ rc = get_user_pages(start, nr_pages, gup_flags, pages, vmas);
+
+ for (i = 0; i < rc; i++) {
+ struct vm_area_struct *vma = vmas[i];
+
+ if (vma == vma_prev)
+ continue;
+
+ vma_prev = vma;
+
+ if (vma_is_fsdax(vma))
+ break;
+ }
+
+ /*
+ * Either get_user_pages() failed, or the vma validation
+ * succeeded, in either case we don't need to put_page() before
+ * returning.
+ */
+ if (i >= rc)
+ goto out;
+
+ for (i = 0; i < rc; i++)
+ put_page(pages[i]);
+ rc = -EOPNOTSUPP;
+out:
+ if (vmas != vmas_arg)
+ kfree(vmas);
+ return rc;
+}
+EXPORT_SYMBOL(get_user_pages_longterm);
+#endif /* CONFIG_FS_DAX */
+
/**
* populate_vma_page_range() - populate a range of pages in the vma.
* @vma: target vma
if (pmd_protnone(pmd))
return hmm_vma_walk_clear(start, end, walk);
- if (write_fault && !pmd_write(pmd))
+ if (!pmd_access_permitted(pmd, write_fault))
return hmm_vma_walk_clear(start, end, walk);
pfn = pmd_pfn(pmd) + pte_index(addr);
- flag |= pmd_write(pmd) ? HMM_PFN_WRITE : 0;
+ flag |= pmd_access_permitted(pmd, WRITE) ? HMM_PFN_WRITE : 0;
for (; addr < end; addr += PAGE_SIZE, i++, pfn++)
pfns[i] = hmm_pfn_t_from_pfn(pfn) | flag;
return 0;
continue;
}
- if (write_fault && !pte_write(pte))
+ if (!pte_access_permitted(pte, write_fault))
goto fault;
pfns[i] = hmm_pfn_t_from_pfn(pte_pfn(pte)) | flag;
- pfns[i] |= pte_write(pte) ? HMM_PFN_WRITE : 0;
+ pfns[i] |= pte_access_permitted(pte, WRITE) ? HMM_PFN_WRITE : 0;
continue;
fault:
#endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */
static void touch_pmd(struct vm_area_struct *vma, unsigned long addr,
- pmd_t *pmd)
+ pmd_t *pmd, int flags)
{
pmd_t _pmd;
- /*
- * We should set the dirty bit only for FOLL_WRITE but for now
- * the dirty bit in the pmd is meaningless. And if the dirty
- * bit will become meaningful and we'll only set it with
- * FOLL_WRITE, an atomic set_bit will be required on the pmd to
- * set the young bit, instead of the current set_pmd_at.
- */
- _pmd = pmd_mkyoung(pmd_mkdirty(*pmd));
+ _pmd = pmd_mkyoung(*pmd);
+ if (flags & FOLL_WRITE)
+ _pmd = pmd_mkdirty(_pmd);
if (pmdp_set_access_flags(vma, addr & HPAGE_PMD_MASK,
- pmd, _pmd, 1))
+ pmd, _pmd, flags & FOLL_WRITE))
update_mmu_cache_pmd(vma, addr, pmd);
}
*/
WARN_ONCE(flags & FOLL_COW, "mm: In follow_devmap_pmd with FOLL_COW set");
- if (flags & FOLL_WRITE && !pmd_write(*pmd))
+ if (!pmd_access_permitted(*pmd, flags & FOLL_WRITE))
return NULL;
if (pmd_present(*pmd) && pmd_devmap(*pmd))
return NULL;
if (flags & FOLL_TOUCH)
- touch_pmd(vma, addr, pmd);
+ touch_pmd(vma, addr, pmd, flags);
/*
* device mapped pages can only be returned if the
#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
static void touch_pud(struct vm_area_struct *vma, unsigned long addr,
- pud_t *pud)
+ pud_t *pud, int flags)
{
pud_t _pud;
- /*
- * We should set the dirty bit only for FOLL_WRITE but for now
- * the dirty bit in the pud is meaningless. And if the dirty
- * bit will become meaningful and we'll only set it with
- * FOLL_WRITE, an atomic set_bit will be required on the pud to
- * set the young bit, instead of the current set_pud_at.
- */
- _pud = pud_mkyoung(pud_mkdirty(*pud));
+ _pud = pud_mkyoung(*pud);
+ if (flags & FOLL_WRITE)
+ _pud = pud_mkdirty(_pud);
if (pudp_set_access_flags(vma, addr & HPAGE_PUD_MASK,
- pud, _pud, 1))
+ pud, _pud, flags & FOLL_WRITE))
update_mmu_cache_pud(vma, addr, pud);
}
assert_spin_locked(pud_lockptr(mm, pud));
- if (flags & FOLL_WRITE && !pud_write(*pud))
+ if (!pud_access_permitted(*pud, flags & FOLL_WRITE))
return NULL;
if (pud_present(*pud) && pud_devmap(*pud))
return NULL;
if (flags & FOLL_TOUCH)
- touch_pud(vma, addr, pud);
+ touch_pud(vma, addr, pud, flags);
/*
* device mapped pages can only be returned if the
*/
static inline bool can_follow_write_pmd(pmd_t pmd, unsigned int flags)
{
- return pmd_write(pmd) ||
+ return pmd_access_permitted(pmd, WRITE) ||
((flags & FOLL_FORCE) && (flags & FOLL_COW) && pmd_dirty(pmd));
}
page = pmd_page(*pmd);
VM_BUG_ON_PAGE(!PageHead(page) && !is_zone_device_page(page), page);
if (flags & FOLL_TOUCH)
- touch_pmd(vma, addr, pmd);
+ touch_pmd(vma, addr, pmd, flags);
if ((flags & FOLL_MLOCK) && (vma->vm_flags & VM_LOCKED)) {
/*
* We don't mlock() pte-mapped THPs. This way we can avoid
}
}
+static int hugetlb_vm_op_split(struct vm_area_struct *vma, unsigned long addr)
+{
+ if (addr & ~(huge_page_mask(hstate_vma(vma))))
+ return -EINVAL;
+ return 0;
+}
+
/*
* We cannot handle pagefaults against hugetlb pages at all. They cause
* handle_mm_fault() to try to instantiate regular-sized pages in the
.fault = hugetlb_vm_op_fault,
.open = hugetlb_vm_op_open,
.close = hugetlb_vm_op_close,
+ .split = hugetlb_vm_op_split,
};
static pte_t make_huge_pte(struct vm_area_struct *vma, struct page *page,
pte_t *pte = NULL;
pgd = pgd_offset(mm, addr);
- p4d = p4d_offset(pgd, addr);
+ p4d = p4d_alloc(mm, pgd, addr);
+ if (!p4d)
+ return NULL;
pud = pud_alloc(mm, p4d, addr);
if (pud) {
if (sz == PUD_SIZE) {
pr_err("BUG: KASAN: %s in %pS\n",
bug_type, (void *)info->ip);
- pr_err("%s of size %zu at addr %p by task %s/%d\n",
+ pr_err("%s of size %zu at addr %px by task %s/%d\n",
info->is_write ? "Write" : "Read", info->access_size,
info->access_addr, current->comm, task_pid_nr(current));
}
const char *rel_type;
int rel_bytes;
- pr_err("The buggy address belongs to the object at %p\n"
+ pr_err("The buggy address belongs to the object at %px\n"
" which belongs to the cache %s of size %d\n",
object, cache->name, cache->object_size);
}
pr_err("The buggy address is located %d bytes %s of\n"
- " %d-byte region [%p, %p)\n",
+ " %d-byte region [%px, %px)\n",
rel_bytes, rel_type, cache->object_size, (void *)object_addr,
(void *)(object_addr + cache->object_size));
}
char shadow_buf[SHADOW_BYTES_PER_ROW];
snprintf(buffer, sizeof(buffer),
- (i == 0) ? ">%p: " : " %p: ", kaddr);
+ (i == 0) ? ">%px: " : " %px: ", kaddr);
/*
* We should not pass a shadow pointer to generic
* function, because generic functions may try to
if (page_count(page) == 0)
continue;
scan_block(page, page + 1, NULL);
+ if (!(pfn % (MAX_SCAN_SIZE / sizeof(*page))))
+ cond_resched();
}
}
put_online_mems();
{
struct file *file = vma->vm_file;
+ *prev = vma;
#ifdef CONFIG_SWAP
if (!file) {
- *prev = vma;
force_swapin_readahead(vma, start, end);
return 0;
}
if (shmem_mapping(file->f_mapping)) {
- *prev = vma;
force_shm_swapin_readahead(vma, start, end,
file->f_mapping);
return 0;
return 0;
}
- *prev = vma;
start = ((start - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff;
if (end > vma->vm_end)
end = vma->vm_end;
memcg_check_events(memcg, page);
if (!mem_cgroup_is_root(memcg))
- css_put(&memcg->css);
+ css_put_many(&memcg->css, nr_entries);
}
/**
if (unlikely(!pte_same(*vmf->pte, entry)))
goto unlock;
if (vmf->flags & FAULT_FLAG_WRITE) {
- if (!pte_write(entry))
+ if (!pte_access_permitted(entry, WRITE))
return do_wp_page(vmf);
entry = pte_mkdirty(entry);
}
/* NUMA case for anonymous PUDs would go here */
- if (dirty && !pud_write(orig_pud)) {
+ if (dirty && !pud_access_permitted(orig_pud, WRITE)) {
ret = wp_huge_pud(&vmf, orig_pud);
if (!(ret & VM_FAULT_FALLBACK))
return ret;
if (pmd_protnone(orig_pmd) && vma_is_accessible(vma))
return do_huge_pmd_numa_page(&vmf, orig_pmd);
- if (dirty && !pmd_write(orig_pmd)) {
+ if (dirty && !pmd_access_permitted(orig_pmd, WRITE)) {
ret = wp_huge_pmd(&vmf, orig_pmd);
if (!(ret & VM_FAULT_FALLBACK))
return ret;
goto out;
pte = *ptep;
- if ((flags & FOLL_WRITE) && !pte_write(pte))
+ if (!pte_access_permitted(pte, flags & FOLL_WRITE))
goto unlock;
*prot = pgprot_val(pte_pgprot(pte));
struct vm_area_struct *new;
int err;
- if (is_vm_hugetlb_page(vma) && (addr &
- ~(huge_page_mask(hstate_vma(vma)))))
- return -EINVAL;
+ if (vma->vm_ops && vma->vm_ops->split) {
+ err = vma->vm_ops->split(vma, addr);
+ if (err)
+ return err;
+ }
new = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL);
if (!new)
*/
set_bit(MMF_UNSTABLE, &mm->flags);
- tlb_gather_mmu(&tlb, mm, 0, -1);
for (vma = mm->mmap ; vma; vma = vma->vm_next) {
if (!can_madv_dontneed_vma(vma))
continue;
* we do not want to block exit_mmap by keeping mm ref
* count elevated without a good reason.
*/
- if (vma_is_anonymous(vma) || !(vma->vm_flags & VM_SHARED))
+ if (vma_is_anonymous(vma) || !(vma->vm_flags & VM_SHARED)) {
+ tlb_gather_mmu(&tlb, mm, vma->vm_start, vma->vm_end);
unmap_page_range(&tlb, vma, vma->vm_start, vma->vm_end,
NULL);
+ tlb_finish_mmu(&tlb, vma->vm_start, vma->vm_end);
+ }
}
- tlb_finish_mmu(&tlb, 0, -1);
pr_info("oom_reaper: reaped process %d (%s), now anon-rss:%lukB, file-rss:%lukB, shmem-rss:%lukB\n",
task_pid_nr(tsk), tsk->comm,
K(get_mm_counter(mm, MM_ANONPAGES)),
else
bg_thresh = (bg_ratio * available_memory) / PAGE_SIZE;
- if (unlikely(bg_thresh >= thresh)) {
- pr_warn("vm direct limit must be set greater than background limit.\n");
+ if (bg_thresh >= thresh)
bg_thresh = thresh / 2;
- }
-
tsk = current;
if (tsk->flags & PF_LESS_THROTTLE || rt_task(tsk)) {
bg_thresh += bg_thresh / 4 + global_wb_domain.dirty_limit / 32;
if (WARN_ON_ONCE(!mm_percpu_wq))
return;
- /* Workqueues cannot recurse */
- if (current->flags & PF_WQ_WORKER)
- return;
-
/*
* Do not drain if one is already in progress unless it's specific to
* a zone. Such callers are primarily CMA and memory hotplug and need
/*
* In case of -EBUSY, we'd like to know which page causes problem.
- * So, just fall through. We will check it in test_pages_isolated().
+ * So, just fall through. test_pages_isolated() has a tracepoint
+ * which will report the busy page.
+ *
+ * It is possible that busy pages could become available before
+ * the call to test_pages_isolated, and the range will actually be
+ * allocated. So, if we fall through be sure to clear ret so that
+ * -EBUSY is not accidentally used or returned to caller.
*/
ret = __alloc_contig_migrate_range(&cc, start, end);
if (ret && ret != -EBUSY)
goto done;
+ ret =0;
/*
* Pages from [start, end) are within a MAX_ORDER_NR_PAGES
* tmpfs instance, limiting inodes to one per page of lowmem;
* but the internal instance is left unlimited.
*/
- if (!(sb->s_flags & MS_KERNMOUNT)) {
+ if (!(sb->s_flags & SB_KERNMOUNT)) {
sbinfo->max_blocks = shmem_default_max_blocks();
sbinfo->max_inodes = shmem_default_max_inodes();
if (shmem_parse_options(data, sbinfo, false)) {
goto failed;
}
} else {
- sb->s_flags |= MS_NOUSER;
+ sb->s_flags |= SB_NOUSER;
}
sb->s_export_op = &shmem_export_ops;
- sb->s_flags |= MS_NOSEC;
+ sb->s_flags |= SB_NOSEC;
#else
- sb->s_flags |= MS_NOUSER;
+ sb->s_flags |= SB_NOUSER;
#endif
spin_lock_init(&sbinfo->stat_lock);
sb->s_xattr = shmem_xattr_handlers;
#endif
#ifdef CONFIG_TMPFS_POSIX_ACL
- sb->s_flags |= MS_POSIXACL;
+ sb->s_flags |= SB_POSIXACL;
#endif
uuid_gen(&sb->s_uuid);
INIT_LIST_HEAD(&dst->list);
list_add_tail(&dsa_tree_list, &dst->list);
- /* Initialize the reference counter to the number of switches, not 1 */
kref_init(&dst->refcount);
- refcount_set(&dst->refcount.refcount, 0);
return dst;
}
kfree(dst);
}
-static struct dsa_switch_tree *dsa_tree_touch(int index)
+static struct dsa_switch_tree *dsa_tree_get(struct dsa_switch_tree *dst)
{
- struct dsa_switch_tree *dst;
-
- dst = dsa_tree_find(index);
- if (!dst)
- dst = dsa_tree_alloc(index);
+ if (dst)
+ kref_get(&dst->refcount);
return dst;
}
-static void dsa_tree_get(struct dsa_switch_tree *dst)
+static struct dsa_switch_tree *dsa_tree_touch(int index)
{
- kref_get(&dst->refcount);
+ struct dsa_switch_tree *dst;
+
+ dst = dsa_tree_find(index);
+ if (dst)
+ return dsa_tree_get(dst);
+ else
+ return dsa_tree_alloc(index);
}
static void dsa_tree_release(struct kref *ref)
static void dsa_tree_put(struct dsa_switch_tree *dst)
{
- kref_put(&dst->refcount, dsa_tree_release);
+ if (dst)
+ kref_put(&dst->refcount, dsa_tree_release);
}
static bool dsa_port_is_dsa(struct dsa_port *port)
mutex_lock(&dsa2_mutex);
err = dsa_switch_probe(ds);
+ dsa_tree_put(ds->dst);
mutex_unlock(&dsa2_mutex);
return err;
mutex_lock(&sta->ampdu_mlme.mtx);
for (i = 0; i < IEEE80211_NUM_TIDS; i++) {
- ___ieee80211_stop_tx_ba_session(sta, i, reason);
___ieee80211_stop_rx_ba_session(sta, i, WLAN_BACK_RECIPIENT,
WLAN_REASON_QSTA_LEAVE_QBSS,
reason != AGG_STOP_DESTROY_STA &&
}
mutex_unlock(&sta->ampdu_mlme.mtx);
+ for (i = 0; i < IEEE80211_NUM_TIDS; i++)
+ ___ieee80211_stop_tx_ba_session(sta, i, reason);
+
/* stopping might queue the work again - so cancel only afterwards */
cancel_work_sync(&sta->ampdu_mlme.work);
struct mesh_path *mpath;
u8 ttl, flags, hopcount;
const u8 *orig_addr;
- u32 orig_sn, metric, metric_txsta, interval;
+ u32 orig_sn, new_metric, orig_metric, last_hop_metric, interval;
bool root_is_gate;
ttl = rann->rann_ttl;
interval = le32_to_cpu(rann->rann_interval);
hopcount = rann->rann_hopcount;
hopcount++;
- metric = le32_to_cpu(rann->rann_metric);
+ orig_metric = le32_to_cpu(rann->rann_metric);
/* Ignore our own RANNs */
if (ether_addr_equal(orig_addr, sdata->vif.addr))
return;
}
- metric_txsta = airtime_link_metric_get(local, sta);
+ last_hop_metric = airtime_link_metric_get(local, sta);
+ new_metric = orig_metric + last_hop_metric;
+ if (new_metric < orig_metric)
+ new_metric = MAX_METRIC;
mpath = mesh_path_lookup(sdata, orig_addr);
if (!mpath) {
}
if (!(SN_LT(mpath->sn, orig_sn)) &&
- !(mpath->sn == orig_sn && metric < mpath->rann_metric)) {
+ !(mpath->sn == orig_sn && new_metric < mpath->rann_metric)) {
rcu_read_unlock();
return;
}
}
mpath->sn = orig_sn;
- mpath->rann_metric = metric + metric_txsta;
+ mpath->rann_metric = new_metric;
mpath->is_root = true;
/* Recording RANNs sender address to send individually
* addressed PREQs destined for root mesh STA */
mesh_path_sel_frame_tx(MPATH_RANN, flags, orig_addr,
orig_sn, 0, NULL, 0, broadcast_addr,
hopcount, ttl, interval,
- metric + metric_txsta, 0, sdata);
+ new_metric, 0, sdata);
}
rcu_read_unlock();
struct ieee80211_hdr_3addr *nullfunc;
struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
- skb = ieee80211_nullfunc_get(&local->hw, &sdata->vif);
+ skb = ieee80211_nullfunc_get(&local->hw, &sdata->vif, true);
if (!skb)
return;
EXPORT_SYMBOL(ieee80211_pspoll_get);
struct sk_buff *ieee80211_nullfunc_get(struct ieee80211_hw *hw,
- struct ieee80211_vif *vif)
+ struct ieee80211_vif *vif,
+ bool qos_ok)
{
struct ieee80211_hdr_3addr *nullfunc;
struct ieee80211_sub_if_data *sdata;
struct ieee80211_if_managed *ifmgd;
struct ieee80211_local *local;
struct sk_buff *skb;
+ bool qos = false;
if (WARN_ON(vif->type != NL80211_IFTYPE_STATION))
return NULL;
ifmgd = &sdata->u.mgd;
local = sdata->local;
- skb = dev_alloc_skb(local->hw.extra_tx_headroom + sizeof(*nullfunc));
+ if (qos_ok) {
+ struct sta_info *sta;
+
+ rcu_read_lock();
+ sta = sta_info_get(sdata, ifmgd->bssid);
+ qos = sta && sta->sta.wme;
+ rcu_read_unlock();
+ }
+
+ skb = dev_alloc_skb(local->hw.extra_tx_headroom +
+ sizeof(*nullfunc) + 2);
if (!skb)
return NULL;
nullfunc->frame_control = cpu_to_le16(IEEE80211_FTYPE_DATA |
IEEE80211_STYPE_NULLFUNC |
IEEE80211_FCTL_TODS);
+ if (qos) {
+ __le16 qos = cpu_to_le16(7);
+
+ BUILD_BUG_ON((IEEE80211_STYPE_QOS_NULLFUNC |
+ IEEE80211_STYPE_NULLFUNC) !=
+ IEEE80211_STYPE_QOS_NULLFUNC);
+ nullfunc->frame_control |=
+ cpu_to_le16(IEEE80211_STYPE_QOS_NULLFUNC);
+ skb->priority = 7;
+ skb_set_queue_mapping(skb, IEEE80211_AC_VO);
+ skb_put_data(skb, &qos, sizeof(qos));
+ }
+
memcpy(nullfunc->addr1, ifmgd->bssid, ETH_ALEN);
memcpy(nullfunc->addr2, vif->addr, ETH_ALEN);
memcpy(nullfunc->addr3, ifmgd->bssid, ETH_ALEN);
const struct dp_upcall_info *upcall_info,
uint32_t cutlen)
{
- unsigned short gso_type = skb_shinfo(skb)->gso_type;
+ unsigned int gso_type = skb_shinfo(skb)->gso_type;
struct sw_flow_key later_key;
struct sk_buff *segs, *nskb;
int err;
#define MAX_ACTIONS_BUFSIZE (32 * 1024)
-static struct sw_flow_actions *nla_alloc_flow_actions(int size, bool log)
+static struct sw_flow_actions *nla_alloc_flow_actions(int size)
{
struct sw_flow_actions *sfa;
- if (size > MAX_ACTIONS_BUFSIZE) {
- OVS_NLERR(log, "Flow action size %u bytes exceeds max", size);
- return ERR_PTR(-EINVAL);
- }
+ WARN_ON_ONCE(size > MAX_ACTIONS_BUFSIZE);
sfa = kmalloc(sizeof(*sfa) + size, GFP_KERNEL);
if (!sfa)
new_acts_size = ksize(*sfa) * 2;
if (new_acts_size > MAX_ACTIONS_BUFSIZE) {
- if ((MAX_ACTIONS_BUFSIZE - next_offset) < req_size)
+ if ((MAX_ACTIONS_BUFSIZE - next_offset) < req_size) {
+ OVS_NLERR(log, "Flow action size exceeds max %u",
+ MAX_ACTIONS_BUFSIZE);
return ERR_PTR(-EMSGSIZE);
+ }
new_acts_size = MAX_ACTIONS_BUFSIZE;
}
- acts = nla_alloc_flow_actions(new_acts_size, log);
+ acts = nla_alloc_flow_actions(new_acts_size);
if (IS_ERR(acts))
return (void *)acts;
{
int err;
- *sfa = nla_alloc_flow_actions(nla_len(attr), log);
+ *sfa = nla_alloc_flow_actions(min(nla_len(attr), MAX_ACTIONS_BUFSIZE));
if (IS_ERR(*sfa))
return PTR_ERR(*sfa);
atomic_long_set(&rollover->num, 0);
atomic_long_set(&rollover->num_huge, 0);
atomic_long_set(&rollover->num_failed, 0);
- po->rollover = rollover;
}
if (type_flags & PACKET_FANOUT_FLAG_UNIQUEID) {
if (refcount_read(&match->sk_ref) < PACKET_FANOUT_MAX) {
__dev_remove_pack(&po->prot_hook);
po->fanout = match;
+ po->rollover = rollover;
+ rollover = NULL;
refcount_set(&match->sk_ref, refcount_read(&match->sk_ref) + 1);
__fanout_link(sk, po);
err = 0;
}
out:
- if (err && rollover) {
- kfree_rcu(rollover, rcu);
- po->rollover = NULL;
- }
+ kfree(rollover);
mutex_unlock(&fanout_mutex);
return err;
}
list_del(&f->list);
else
f = NULL;
-
- if (po->rollover) {
- kfree_rcu(po->rollover, rcu);
- po->rollover = NULL;
- }
}
mutex_unlock(&fanout_mutex);
synchronize_net();
if (f) {
+ kfree(po->rollover);
fanout_release_data(f);
kfree(f);
}
if (need_rehook) {
if (po->running) {
rcu_read_unlock();
+ /* prevents packet_notifier() from calling
+ * register_prot_hook()
+ */
+ po->num = 0;
__unregister_prot_hook(sk, true);
rcu_read_lock();
dev_curr = po->prot_hook.dev;
dev->ifindex);
}
+ BUG_ON(po->running);
po->num = proto;
po->prot_hook.type = proto;
void *data = &val;
union tpacket_stats_u st;
struct tpacket_rollover_stats rstats;
- struct packet_rollover *rollover;
if (level != SOL_PACKET)
return -ENOPROTOOPT;
0);
break;
case PACKET_ROLLOVER_STATS:
- rcu_read_lock();
- rollover = rcu_dereference(po->rollover);
- if (rollover) {
- rstats.tp_all = atomic_long_read(&rollover->num);
- rstats.tp_huge = atomic_long_read(&rollover->num_huge);
- rstats.tp_failed = atomic_long_read(&rollover->num_failed);
- data = &rstats;
- lv = sizeof(rstats);
- }
- rcu_read_unlock();
- if (!rollover)
+ if (!po->rollover)
return -EINVAL;
+ rstats.tp_all = atomic_long_read(&po->rollover->num);
+ rstats.tp_huge = atomic_long_read(&po->rollover->num_huge);
+ rstats.tp_failed = atomic_long_read(&po->rollover->num_failed);
+ data = &rstats;
+ lv = sizeof(rstats);
break;
case PACKET_TX_HAS_OFF:
val = po->tp_tx_has_off;
struct packet_rollover {
int sock;
- struct rcu_head rcu;
atomic_long_t num;
atomic_long_t num_huge;
atomic_long_t num_failed;
bool upgrade)
{
struct rxrpc_conn_parameters cp;
+ struct rxrpc_call_params p;
struct rxrpc_call *call;
struct rxrpc_sock *rx = rxrpc_sk(sock->sk);
int ret;
if (key && !key->payload.data[0])
key = NULL; /* a no-security key */
+ memset(&p, 0, sizeof(p));
+ p.user_call_ID = user_call_ID;
+ p.tx_total_len = tx_total_len;
+
memset(&cp, 0, sizeof(cp));
cp.local = rx->local;
cp.key = key;
cp.exclusive = false;
cp.upgrade = upgrade;
cp.service_id = srx->srx_service;
- call = rxrpc_new_client_call(rx, &cp, srx, user_call_ID, tx_total_len,
- gfp);
+ call = rxrpc_new_client_call(rx, &cp, srx, &p, gfp);
/* The socket has been unlocked. */
if (!IS_ERR(call)) {
call->notify_rx = notify_rx;
sock_orphan(sk);
sk->sk_shutdown = SHUTDOWN_MASK;
+ /* We want to kill off all connections from a service socket
+ * as fast as possible because we can't share these; client
+ * sockets, on the other hand, can share an endpoint.
+ */
+ switch (sk->sk_state) {
+ case RXRPC_SERVER_BOUND:
+ case RXRPC_SERVER_BOUND2:
+ case RXRPC_SERVER_LISTENING:
+ case RXRPC_SERVER_LISTEN_DISABLED:
+ rx->local->service_closed = true;
+ break;
+ }
+
spin_lock_bh(&sk->sk_receive_queue.lock);
sk->sk_state = RXRPC_CLOSE;
spin_unlock_bh(&sk->sk_receive_queue.lock);
rxrpc_release_calls_on_socket(rx);
flush_workqueue(rxrpc_workqueue);
rxrpc_purge_queue(&sk->sk_receive_queue);
+ rxrpc_queue_work(&rx->local->rxnet->service_conn_reaper);
+ rxrpc_queue_work(&rx->local->rxnet->client_conn_reaper);
rxrpc_put_local(rx->local);
rx->local = NULL;
struct list_head conn_proc_list; /* List of conns in this namespace for proc */
struct list_head service_conns; /* Service conns in this namespace */
rwlock_t conn_lock; /* Lock for ->conn_proc_list, ->service_conns */
- struct delayed_work service_conn_reaper;
+ struct work_struct service_conn_reaper;
+ struct timer_list service_conn_reap_timer;
unsigned int nr_client_conns;
unsigned int nr_active_client_conns;
bool kill_all_client_conns;
+ bool live;
spinlock_t client_conn_cache_lock; /* Lock for ->*_client_conns */
spinlock_t client_conn_discard_lock; /* Prevent multiple discarders */
struct list_head waiting_client_conns;
struct list_head active_client_conns;
struct list_head idle_client_conns;
- struct delayed_work client_conn_reaper;
+ struct work_struct client_conn_reaper;
+ struct timer_list client_conn_reap_timer;
struct list_head local_endpoints;
struct mutex local_mutex; /* Lock for ->local_endpoints */
rwlock_t services_lock; /* lock for services list */
int debug_id; /* debug ID for printks */
bool dead;
+ bool service_closed; /* Service socket closed */
struct sockaddr_rxrpc srx; /* local address */
};
RXRPC_CONN_DONT_REUSE, /* Don't reuse this connection */
RXRPC_CONN_COUNTED, /* Counted by rxrpc_nr_client_conns */
RXRPC_CONN_PROBING_FOR_UPGRADE, /* Probing for service upgrade */
+ RXRPC_CONN_FINAL_ACK_0, /* Need final ACK for channel 0 */
+ RXRPC_CONN_FINAL_ACK_1, /* Need final ACK for channel 1 */
+ RXRPC_CONN_FINAL_ACK_2, /* Need final ACK for channel 2 */
+ RXRPC_CONN_FINAL_ACK_3, /* Need final ACK for channel 3 */
};
+#define RXRPC_CONN_FINAL_ACK_MASK ((1UL << RXRPC_CONN_FINAL_ACK_0) | \
+ (1UL << RXRPC_CONN_FINAL_ACK_1) | \
+ (1UL << RXRPC_CONN_FINAL_ACK_2) | \
+ (1UL << RXRPC_CONN_FINAL_ACK_3))
+
/*
* Events that can be raised upon a connection.
*/
#define RXRPC_ACTIVE_CHANS_MASK ((1 << RXRPC_MAXCALLS) - 1)
struct list_head waiting_calls; /* Calls waiting for channels */
struct rxrpc_channel {
+ unsigned long final_ack_at; /* Time at which to issue final ACK */
struct rxrpc_call __rcu *call; /* Active call */
u32 call_id; /* ID of current call */
u32 call_counter; /* Call ID counter */
};
} channels[RXRPC_MAXCALLS];
+ struct timer_list timer; /* Conn event timer */
struct work_struct processor; /* connection event processor */
union {
struct rb_node client_node; /* Node in local->client_conns */
enum rxrpc_call_event {
RXRPC_CALL_EV_ACK, /* need to generate ACK */
RXRPC_CALL_EV_ABORT, /* need to generate abort */
- RXRPC_CALL_EV_TIMER, /* Timer expired */
RXRPC_CALL_EV_RESEND, /* Tx resend required */
RXRPC_CALL_EV_PING, /* Ping send required */
+ RXRPC_CALL_EV_EXPIRED, /* Expiry occurred */
+ RXRPC_CALL_EV_ACK_LOST, /* ACK may be lost, send ping */
};
/*
struct rxrpc_peer *peer; /* Peer record for remote address */
struct rxrpc_sock __rcu *socket; /* socket responsible */
struct mutex user_mutex; /* User access mutex */
- ktime_t ack_at; /* When deferred ACK needs to happen */
- ktime_t resend_at; /* When next resend needs to happen */
- ktime_t ping_at; /* When next to send a ping */
- ktime_t expire_at; /* When the call times out */
+ unsigned long ack_at; /* When deferred ACK needs to happen */
+ unsigned long ack_lost_at; /* When ACK is figured as lost */
+ unsigned long resend_at; /* When next resend needs to happen */
+ unsigned long ping_at; /* When next to send a ping */
+ unsigned long keepalive_at; /* When next to send a keepalive ping */
+ unsigned long expect_rx_by; /* When we expect to get a packet by */
+ unsigned long expect_req_by; /* When we expect to get a request DATA packet by */
+ unsigned long expect_term_by; /* When we expect call termination by */
+ u32 next_rx_timo; /* Timeout for next Rx packet (jif) */
+ u32 next_req_timo; /* Timeout for next Rx request packet (jif) */
struct timer_list timer; /* Combined event timer */
struct work_struct processor; /* Event processor */
rxrpc_notify_rx_t notify_rx; /* kernel service Rx notification function */
ktime_t acks_latest_ts; /* Timestamp of latest ACK received */
rxrpc_serial_t acks_latest; /* serial number of latest ACK received */
rxrpc_seq_t acks_lowest_nak; /* Lowest NACK in the buffer (or ==tx_hard_ack) */
+ rxrpc_seq_t acks_lost_top; /* tx_top at the time lost-ack ping sent */
+ rxrpc_serial_t acks_lost_ping; /* Serial number of probe ACK */
};
/*
u8 cumulative_acks;
};
+/*
+ * sendmsg() cmsg-specified parameters.
+ */
+enum rxrpc_command {
+ RXRPC_CMD_SEND_DATA, /* send data message */
+ RXRPC_CMD_SEND_ABORT, /* request abort generation */
+ RXRPC_CMD_ACCEPT, /* [server] accept incoming call */
+ RXRPC_CMD_REJECT_BUSY, /* [server] reject a call as busy */
+};
+
+struct rxrpc_call_params {
+ s64 tx_total_len; /* Total Tx data length (if send data) */
+ unsigned long user_call_ID; /* User's call ID */
+ struct {
+ u32 hard; /* Maximum lifetime (sec) */
+ u32 idle; /* Max time since last data packet (msec) */
+ u32 normal; /* Max time since last call packet (msec) */
+ } timeouts;
+ u8 nr_timeouts; /* Number of timeouts specified */
+};
+
+struct rxrpc_send_params {
+ struct rxrpc_call_params call;
+ u32 abort_code; /* Abort code to Tx (if abort) */
+ enum rxrpc_command command : 8; /* The command to implement */
+ bool exclusive; /* Shared or exclusive call */
+ bool upgrade; /* If the connection is upgradeable */
+};
+
#include <trace/events/rxrpc.h>
/*
/*
* call_event.c
*/
-void __rxrpc_set_timer(struct rxrpc_call *, enum rxrpc_timer_trace, ktime_t);
-void rxrpc_set_timer(struct rxrpc_call *, enum rxrpc_timer_trace, ktime_t);
void rxrpc_propose_ACK(struct rxrpc_call *, u8, u16, u32, bool, bool,
enum rxrpc_propose_ack_trace);
void rxrpc_process_call(struct work_struct *);
+static inline void rxrpc_reduce_call_timer(struct rxrpc_call *call,
+ unsigned long expire_at,
+ unsigned long now,
+ enum rxrpc_timer_trace why)
+{
+ trace_rxrpc_timer(call, why, now);
+ timer_reduce(&call->timer, expire_at);
+}
+
/*
* call_object.c
*/
extern struct kmem_cache *rxrpc_call_jar;
struct rxrpc_call *rxrpc_find_call_by_user_ID(struct rxrpc_sock *, unsigned long);
-struct rxrpc_call *rxrpc_alloc_call(gfp_t);
+struct rxrpc_call *rxrpc_alloc_call(struct rxrpc_sock *, gfp_t);
struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *,
struct rxrpc_conn_parameters *,
struct sockaddr_rxrpc *,
- unsigned long, s64, gfp_t);
+ struct rxrpc_call_params *, gfp_t);
int rxrpc_retry_client_call(struct rxrpc_sock *,
struct rxrpc_call *,
struct rxrpc_conn_parameters *,
*/
extern unsigned int rxrpc_max_client_connections;
extern unsigned int rxrpc_reap_client_connections;
-extern unsigned int rxrpc_conn_idle_client_expiry;
-extern unsigned int rxrpc_conn_idle_client_fast_expiry;
+extern unsigned long rxrpc_conn_idle_client_expiry;
+extern unsigned long rxrpc_conn_idle_client_fast_expiry;
extern struct idr rxrpc_client_conn_ids;
void rxrpc_destroy_client_conn_ids(void);
* conn_object.c
*/
extern unsigned int rxrpc_connection_expiry;
+extern unsigned int rxrpc_closed_conn_expiry;
struct rxrpc_connection *rxrpc_alloc_connection(gfp_t);
struct rxrpc_connection *rxrpc_find_connection_rcu(struct rxrpc_local *,
rxrpc_put_service_conn(conn);
}
+static inline void rxrpc_reduce_conn_timer(struct rxrpc_connection *conn,
+ unsigned long expire_at)
+{
+ timer_reduce(&conn->timer, expire_at);
+}
+
/*
* conn_service.c
*/
* misc.c
*/
extern unsigned int rxrpc_max_backlog __read_mostly;
-extern unsigned int rxrpc_requested_ack_delay;
-extern unsigned int rxrpc_soft_ack_delay;
-extern unsigned int rxrpc_idle_ack_delay;
+extern unsigned long rxrpc_requested_ack_delay;
+extern unsigned long rxrpc_soft_ack_delay;
+extern unsigned long rxrpc_idle_ack_delay;
extern unsigned int rxrpc_rx_window_size;
extern unsigned int rxrpc_rx_mtu;
extern unsigned int rxrpc_rx_jumbo_max;
-extern unsigned int rxrpc_resend_timeout;
+extern unsigned long rxrpc_resend_timeout;
extern const s8 rxrpc_ack_priority[];
/*
* output.c
*/
-int rxrpc_send_ack_packet(struct rxrpc_call *, bool);
+int rxrpc_send_ack_packet(struct rxrpc_call *, bool, rxrpc_serial_t *);
int rxrpc_send_abort_packet(struct rxrpc_call *);
int rxrpc_send_data_packet(struct rxrpc_call *, struct sk_buff *, bool);
void rxrpc_reject_packets(struct rxrpc_local *);
/* Now it gets complicated, because calls get registered with the
* socket here, particularly if a user ID is preassigned by the user.
*/
- call = rxrpc_alloc_call(gfp);
+ call = rxrpc_alloc_call(rx, gfp);
if (!call)
return -ENOMEM;
call->flags |= (1 << RXRPC_CALL_IS_SERVICE);
#include "ar-internal.h"
/*
- * Set the timer
- */
-void __rxrpc_set_timer(struct rxrpc_call *call, enum rxrpc_timer_trace why,
- ktime_t now)
-{
- unsigned long t_j, now_j = jiffies;
- ktime_t t;
- bool queue = false;
-
- if (call->state < RXRPC_CALL_COMPLETE) {
- t = call->expire_at;
- if (!ktime_after(t, now)) {
- trace_rxrpc_timer(call, why, now, now_j);
- queue = true;
- goto out;
- }
-
- if (!ktime_after(call->resend_at, now)) {
- call->resend_at = call->expire_at;
- if (!test_and_set_bit(RXRPC_CALL_EV_RESEND, &call->events))
- queue = true;
- } else if (ktime_before(call->resend_at, t)) {
- t = call->resend_at;
- }
-
- if (!ktime_after(call->ack_at, now)) {
- call->ack_at = call->expire_at;
- if (!test_and_set_bit(RXRPC_CALL_EV_ACK, &call->events))
- queue = true;
- } else if (ktime_before(call->ack_at, t)) {
- t = call->ack_at;
- }
-
- if (!ktime_after(call->ping_at, now)) {
- call->ping_at = call->expire_at;
- if (!test_and_set_bit(RXRPC_CALL_EV_PING, &call->events))
- queue = true;
- } else if (ktime_before(call->ping_at, t)) {
- t = call->ping_at;
- }
-
- t_j = nsecs_to_jiffies(ktime_to_ns(ktime_sub(t, now)));
- t_j += jiffies;
-
- /* We have to make sure that the calculated jiffies value falls
- * at or after the nsec value, or we may loop ceaselessly
- * because the timer times out, but we haven't reached the nsec
- * timeout yet.
- */
- t_j++;
-
- if (call->timer.expires != t_j || !timer_pending(&call->timer)) {
- mod_timer(&call->timer, t_j);
- trace_rxrpc_timer(call, why, now, now_j);
- }
- }
-
-out:
- if (queue)
- rxrpc_queue_call(call);
-}
-
-/*
- * Set the timer
- */
-void rxrpc_set_timer(struct rxrpc_call *call, enum rxrpc_timer_trace why,
- ktime_t now)
-{
- read_lock_bh(&call->state_lock);
- __rxrpc_set_timer(call, why, now);
- read_unlock_bh(&call->state_lock);
-}
-
-/*
* Propose a PING ACK be sent.
*/
static void rxrpc_propose_ping(struct rxrpc_call *call,
!test_and_set_bit(RXRPC_CALL_EV_PING, &call->events))
rxrpc_queue_call(call);
} else {
- ktime_t now = ktime_get_real();
- ktime_t ping_at = ktime_add_ms(now, rxrpc_idle_ack_delay);
+ unsigned long now = jiffies;
+ unsigned long ping_at = now + rxrpc_idle_ack_delay;
- if (ktime_before(ping_at, call->ping_at)) {
- call->ping_at = ping_at;
- rxrpc_set_timer(call, rxrpc_timer_set_for_ping, now);
+ if (time_before(ping_at, call->ping_at)) {
+ WRITE_ONCE(call->ping_at, ping_at);
+ rxrpc_reduce_call_timer(call, ping_at, now,
+ rxrpc_timer_set_for_ping);
}
}
}
enum rxrpc_propose_ack_trace why)
{
enum rxrpc_propose_ack_outcome outcome = rxrpc_propose_ack_use;
- unsigned int expiry = rxrpc_soft_ack_delay;
- ktime_t now, ack_at;
+ unsigned long expiry = rxrpc_soft_ack_delay;
s8 prior = rxrpc_ack_priority[ack_reason];
/* Pings are handled specially because we don't want to accidentally
background)
rxrpc_queue_call(call);
} else {
- now = ktime_get_real();
- ack_at = ktime_add_ms(now, expiry);
- if (ktime_before(ack_at, call->ack_at)) {
- call->ack_at = ack_at;
- rxrpc_set_timer(call, rxrpc_timer_set_for_ack, now);
+ unsigned long now = jiffies, ack_at;
+
+ if (call->peer->rtt_usage > 0)
+ ack_at = nsecs_to_jiffies(call->peer->rtt);
+ else
+ ack_at = expiry;
+
+ ack_at = jiffies + expiry;
+ if (time_before(ack_at, call->ack_at)) {
+ WRITE_ONCE(call->ack_at, ack_at);
+ rxrpc_reduce_call_timer(call, ack_at, now,
+ rxrpc_timer_set_for_ack);
}
}
/*
* Perform retransmission of NAK'd and unack'd packets.
*/
-static void rxrpc_resend(struct rxrpc_call *call, ktime_t now)
+static void rxrpc_resend(struct rxrpc_call *call, unsigned long now_j)
{
struct rxrpc_skb_priv *sp;
struct sk_buff *skb;
+ unsigned long resend_at;
rxrpc_seq_t cursor, seq, top;
- ktime_t max_age, oldest, ack_ts;
+ ktime_t now, max_age, oldest, ack_ts, timeout, min_timeo;
int ix;
u8 annotation, anno_type, retrans = 0, unacked = 0;
_enter("{%d,%d}", call->tx_hard_ack, call->tx_top);
- max_age = ktime_sub_ms(now, rxrpc_resend_timeout);
+ if (call->peer->rtt_usage > 1)
+ timeout = ns_to_ktime(call->peer->rtt * 3 / 2);
+ else
+ timeout = ms_to_ktime(rxrpc_resend_timeout);
+ min_timeo = ns_to_ktime((1000000000 / HZ) * 4);
+ if (ktime_before(timeout, min_timeo))
+ timeout = min_timeo;
+
+ now = ktime_get_real();
+ max_age = ktime_sub(now, timeout);
spin_lock_bh(&call->lock);
ktime_to_ns(ktime_sub(skb->tstamp, max_age)));
}
- call->resend_at = ktime_add_ms(oldest, rxrpc_resend_timeout);
+ resend_at = nsecs_to_jiffies(ktime_to_ns(ktime_sub(oldest, now)));
+ resend_at += jiffies + rxrpc_resend_timeout;
+ WRITE_ONCE(call->resend_at, resend_at);
if (unacked)
rxrpc_congestion_timeout(call);
* retransmitting data.
*/
if (!retrans) {
- rxrpc_set_timer(call, rxrpc_timer_set_for_resend, now);
+ rxrpc_reduce_call_timer(call, resend_at, now,
+ rxrpc_timer_set_for_resend);
spin_unlock_bh(&call->lock);
ack_ts = ktime_sub(now, call->acks_latest_ts);
if (ktime_to_ns(ack_ts) < call->peer->rtt)
goto out;
rxrpc_propose_ACK(call, RXRPC_ACK_PING, 0, 0, true, false,
rxrpc_propose_ack_ping_for_lost_ack);
- rxrpc_send_ack_packet(call, true);
+ rxrpc_send_ack_packet(call, true, NULL);
goto out;
}
{
struct rxrpc_call *call =
container_of(work, struct rxrpc_call, processor);
- ktime_t now;
+ rxrpc_serial_t *send_ack;
+ unsigned long now, next, t;
rxrpc_see_call(call);
goto out_put;
}
- now = ktime_get_real();
- if (ktime_before(call->expire_at, now)) {
+ /* Work out if any timeouts tripped */
+ now = jiffies;
+ t = READ_ONCE(call->expect_rx_by);
+ if (time_after_eq(now, t)) {
+ trace_rxrpc_timer(call, rxrpc_timer_exp_normal, now);
+ set_bit(RXRPC_CALL_EV_EXPIRED, &call->events);
+ }
+
+ t = READ_ONCE(call->expect_req_by);
+ if (call->state == RXRPC_CALL_SERVER_RECV_REQUEST &&
+ time_after_eq(now, t)) {
+ trace_rxrpc_timer(call, rxrpc_timer_exp_idle, now);
+ set_bit(RXRPC_CALL_EV_EXPIRED, &call->events);
+ }
+
+ t = READ_ONCE(call->expect_term_by);
+ if (time_after_eq(now, t)) {
+ trace_rxrpc_timer(call, rxrpc_timer_exp_hard, now);
+ set_bit(RXRPC_CALL_EV_EXPIRED, &call->events);
+ }
+
+ t = READ_ONCE(call->ack_at);
+ if (time_after_eq(now, t)) {
+ trace_rxrpc_timer(call, rxrpc_timer_exp_ack, now);
+ cmpxchg(&call->ack_at, t, now + MAX_JIFFY_OFFSET);
+ set_bit(RXRPC_CALL_EV_ACK, &call->events);
+ }
+
+ t = READ_ONCE(call->ack_lost_at);
+ if (time_after_eq(now, t)) {
+ trace_rxrpc_timer(call, rxrpc_timer_exp_lost_ack, now);
+ cmpxchg(&call->ack_lost_at, t, now + MAX_JIFFY_OFFSET);
+ set_bit(RXRPC_CALL_EV_ACK_LOST, &call->events);
+ }
+
+ t = READ_ONCE(call->keepalive_at);
+ if (time_after_eq(now, t)) {
+ trace_rxrpc_timer(call, rxrpc_timer_exp_keepalive, now);
+ cmpxchg(&call->keepalive_at, t, now + MAX_JIFFY_OFFSET);
+ rxrpc_propose_ACK(call, RXRPC_ACK_PING, 0, 0, true, true,
+ rxrpc_propose_ack_ping_for_keepalive);
+ set_bit(RXRPC_CALL_EV_PING, &call->events);
+ }
+
+ t = READ_ONCE(call->ping_at);
+ if (time_after_eq(now, t)) {
+ trace_rxrpc_timer(call, rxrpc_timer_exp_ping, now);
+ cmpxchg(&call->ping_at, t, now + MAX_JIFFY_OFFSET);
+ set_bit(RXRPC_CALL_EV_PING, &call->events);
+ }
+
+ t = READ_ONCE(call->resend_at);
+ if (time_after_eq(now, t)) {
+ trace_rxrpc_timer(call, rxrpc_timer_exp_resend, now);
+ cmpxchg(&call->resend_at, t, now + MAX_JIFFY_OFFSET);
+ set_bit(RXRPC_CALL_EV_RESEND, &call->events);
+ }
+
+ /* Process events */
+ if (test_and_clear_bit(RXRPC_CALL_EV_EXPIRED, &call->events)) {
rxrpc_abort_call("EXP", call, 0, RX_USER_ABORT, -ETIME);
set_bit(RXRPC_CALL_EV_ABORT, &call->events);
goto recheck_state;
}
- if (test_and_clear_bit(RXRPC_CALL_EV_ACK, &call->events)) {
+ send_ack = NULL;
+ if (test_and_clear_bit(RXRPC_CALL_EV_ACK_LOST, &call->events)) {
+ call->acks_lost_top = call->tx_top;
+ rxrpc_propose_ACK(call, RXRPC_ACK_PING, 0, 0, true, false,
+ rxrpc_propose_ack_ping_for_lost_ack);
+ send_ack = &call->acks_lost_ping;
+ }
+
+ if (test_and_clear_bit(RXRPC_CALL_EV_ACK, &call->events) ||
+ send_ack) {
if (call->ackr_reason) {
- rxrpc_send_ack_packet(call, false);
+ rxrpc_send_ack_packet(call, false, send_ack);
goto recheck_state;
}
}
if (test_and_clear_bit(RXRPC_CALL_EV_PING, &call->events)) {
- rxrpc_send_ack_packet(call, true);
+ rxrpc_send_ack_packet(call, true, NULL);
goto recheck_state;
}
goto recheck_state;
}
- rxrpc_set_timer(call, rxrpc_timer_set_for_resend, now);
+ /* Make sure the timer is restarted */
+ next = call->expect_rx_by;
+
+#define set(T) { t = READ_ONCE(T); if (time_before(t, next)) next = t; }
+
+ set(call->expect_req_by);
+ set(call->expect_term_by);
+ set(call->ack_at);
+ set(call->ack_lost_at);
+ set(call->resend_at);
+ set(call->keepalive_at);
+ set(call->ping_at);
+
+ now = jiffies;
+ if (time_after_eq(now, next))
+ goto recheck_state;
+
+ rxrpc_reduce_call_timer(call, next, now, rxrpc_timer_restart);
/* other events may have been raised since we started checking */
if (call->events && call->state < RXRPC_CALL_COMPLETE) {
_enter("%d", call->debug_id);
- if (call->state < RXRPC_CALL_COMPLETE)
- rxrpc_set_timer(call, rxrpc_timer_expired, ktime_get_real());
+ if (call->state < RXRPC_CALL_COMPLETE) {
+ trace_rxrpc_timer(call, rxrpc_timer_expired, jiffies);
+ rxrpc_queue_call(call);
+ }
}
+static struct lock_class_key rxrpc_call_user_mutex_lock_class_key;
+
/*
* find an extant server call
* - called in process context with IRQs enabled
/*
* allocate a new call
*/
-struct rxrpc_call *rxrpc_alloc_call(gfp_t gfp)
+struct rxrpc_call *rxrpc_alloc_call(struct rxrpc_sock *rx, gfp_t gfp)
{
struct rxrpc_call *call;
goto nomem_2;
mutex_init(&call->user_mutex);
+
+ /* Prevent lockdep reporting a deadlock false positive between the afs
+ * filesystem and sys_sendmsg() via the mmap sem.
+ */
+ if (rx->sk.sk_kern_sock)
+ lockdep_set_class(&call->user_mutex,
+ &rxrpc_call_user_mutex_lock_class_key);
+
timer_setup(&call->timer, rxrpc_call_timer_expired, 0);
INIT_WORK(&call->processor, &rxrpc_process_call);
INIT_LIST_HEAD(&call->link);
atomic_set(&call->usage, 1);
call->debug_id = atomic_inc_return(&rxrpc_debug_id);
call->tx_total_len = -1;
+ call->next_rx_timo = 20 * HZ;
+ call->next_req_timo = 1 * HZ;
memset(&call->sock_node, 0xed, sizeof(call->sock_node));
/*
* Allocate a new client call.
*/
-static struct rxrpc_call *rxrpc_alloc_client_call(struct sockaddr_rxrpc *srx,
+static struct rxrpc_call *rxrpc_alloc_client_call(struct rxrpc_sock *rx,
+ struct sockaddr_rxrpc *srx,
gfp_t gfp)
{
struct rxrpc_call *call;
_enter("");
- call = rxrpc_alloc_call(gfp);
+ call = rxrpc_alloc_call(rx, gfp);
if (!call)
return ERR_PTR(-ENOMEM);
call->state = RXRPC_CALL_CLIENT_AWAIT_CONN;
*/
static void rxrpc_start_call_timer(struct rxrpc_call *call)
{
- ktime_t now = ktime_get_real(), expire_at;
-
- expire_at = ktime_add_ms(now, rxrpc_max_call_lifetime);
- call->expire_at = expire_at;
- call->ack_at = expire_at;
- call->ping_at = expire_at;
- call->resend_at = expire_at;
- call->timer.expires = jiffies + LONG_MAX / 2;
- rxrpc_set_timer(call, rxrpc_timer_begin, now);
+ unsigned long now = jiffies;
+ unsigned long j = now + MAX_JIFFY_OFFSET;
+
+ call->ack_at = j;
+ call->ack_lost_at = j;
+ call->resend_at = j;
+ call->ping_at = j;
+ call->expect_rx_by = j;
+ call->expect_req_by = j;
+ call->expect_term_by = j;
+ call->timer.expires = now;
}
/*
struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx,
struct rxrpc_conn_parameters *cp,
struct sockaddr_rxrpc *srx,
- unsigned long user_call_ID,
- s64 tx_total_len,
+ struct rxrpc_call_params *p,
gfp_t gfp)
__releases(&rx->sk.sk_lock.slock)
{
const void *here = __builtin_return_address(0);
int ret;
- _enter("%p,%lx", rx, user_call_ID);
+ _enter("%p,%lx", rx, p->user_call_ID);
- call = rxrpc_alloc_client_call(srx, gfp);
+ call = rxrpc_alloc_client_call(rx, srx, gfp);
if (IS_ERR(call)) {
release_sock(&rx->sk);
_leave(" = %ld", PTR_ERR(call));
return call;
}
- call->tx_total_len = tx_total_len;
+ call->tx_total_len = p->tx_total_len;
trace_rxrpc_call(call, rxrpc_call_new_client, atomic_read(&call->usage),
- here, (const void *)user_call_ID);
+ here, (const void *)p->user_call_ID);
/* We need to protect a partially set up call against the user as we
* will be acting outside the socket lock.
parent = *pp;
xcall = rb_entry(parent, struct rxrpc_call, sock_node);
- if (user_call_ID < xcall->user_call_ID)
+ if (p->user_call_ID < xcall->user_call_ID)
pp = &(*pp)->rb_left;
- else if (user_call_ID > xcall->user_call_ID)
+ else if (p->user_call_ID > xcall->user_call_ID)
pp = &(*pp)->rb_right;
else
goto error_dup_user_ID;
}
rcu_assign_pointer(call->socket, rx);
- call->user_call_ID = user_call_ID;
+ call->user_call_ID = p->user_call_ID;
__set_bit(RXRPC_CALL_HAS_USERID, &call->flags);
rxrpc_get_call(call, rxrpc_call_got_userid);
rb_link_node(&call->sock_node, parent, pp);
__read_mostly unsigned int rxrpc_max_client_connections = 1000;
__read_mostly unsigned int rxrpc_reap_client_connections = 900;
-__read_mostly unsigned int rxrpc_conn_idle_client_expiry = 2 * 60 * HZ;
-__read_mostly unsigned int rxrpc_conn_idle_client_fast_expiry = 2 * HZ;
+__read_mostly unsigned long rxrpc_conn_idle_client_expiry = 2 * 60 * HZ;
+__read_mostly unsigned long rxrpc_conn_idle_client_fast_expiry = 2 * HZ;
/*
* We use machine-unique IDs for our client connections.
trace_rxrpc_client(conn, channel, rxrpc_client_chan_activate);
+ /* Cancel the final ACK on the previous call if it hasn't been sent yet
+ * as the DATA packet will implicitly ACK it.
+ */
+ clear_bit(RXRPC_CONN_FINAL_ACK_0 + channel, &conn->flags);
+
write_lock_bh(&call->state_lock);
if (!test_bit(RXRPC_CALL_TX_LASTQ, &call->flags))
call->state = RXRPC_CALL_CLIENT_SEND_REQUEST;
_enter("{%d,%lx},", call->debug_id, call->user_call_ID);
- rxrpc_discard_expired_client_conns(&rxnet->client_conn_reaper.work);
+ rxrpc_discard_expired_client_conns(&rxnet->client_conn_reaper);
rxrpc_cull_active_client_conns(rxnet);
ret = rxrpc_get_client_conn(call, cp, srx, gfp);
}
/*
+ * Set the reap timer.
+ */
+static void rxrpc_set_client_reap_timer(struct rxrpc_net *rxnet)
+{
+ unsigned long now = jiffies;
+ unsigned long reap_at = now + rxrpc_conn_idle_client_expiry;
+
+ if (rxnet->live)
+ timer_reduce(&rxnet->client_conn_reap_timer, reap_at);
+}
+
+/*
* Disconnect a client call.
*/
void rxrpc_disconnect_client_call(struct rxrpc_call *call)
goto out_2;
}
+ /* Schedule the final ACK to be transmitted in a short while so that it
+ * can be skipped if we find a follow-on call. The first DATA packet
+ * of the follow on call will implicitly ACK this call.
+ */
+ if (test_bit(RXRPC_CALL_EXPOSED, &call->flags)) {
+ unsigned long final_ack_at = jiffies + 2;
+
+ WRITE_ONCE(chan->final_ack_at, final_ack_at);
+ smp_wmb(); /* vs rxrpc_process_delayed_final_acks() */
+ set_bit(RXRPC_CONN_FINAL_ACK_0 + channel, &conn->flags);
+ rxrpc_reduce_conn_timer(conn, final_ack_at);
+ }
+
/* Things are more complex and we need the cache lock. We might be
* able to simply idle the conn or it might now be lurking on the wait
* list. It might even get moved back to the active list whilst we're
list_move_tail(&conn->cache_link, &rxnet->idle_client_conns);
if (rxnet->idle_client_conns.next == &conn->cache_link &&
!rxnet->kill_all_client_conns)
- queue_delayed_work(rxrpc_workqueue,
- &rxnet->client_conn_reaper,
- rxrpc_conn_idle_client_expiry);
+ rxrpc_set_client_reap_timer(rxnet);
} else {
trace_rxrpc_client(conn, channel, rxrpc_client_to_inactive);
conn->cache_state = RXRPC_CONN_CLIENT_INACTIVE;
{
struct rxrpc_connection *conn;
struct rxrpc_net *rxnet =
- container_of(to_delayed_work(work),
- struct rxrpc_net, client_conn_reaper);
+ container_of(work, struct rxrpc_net, client_conn_reaper);
unsigned long expiry, conn_expires_at, now;
unsigned int nr_conns;
bool did_discard = false;
expiry = rxrpc_conn_idle_client_expiry;
if (nr_conns > rxrpc_reap_client_connections)
expiry = rxrpc_conn_idle_client_fast_expiry;
+ if (conn->params.local->service_closed)
+ expiry = rxrpc_closed_conn_expiry * HZ;
conn_expires_at = conn->idle_timestamp + expiry;
*/
_debug("not yet");
if (!rxnet->kill_all_client_conns)
- queue_delayed_work(rxrpc_workqueue,
- &rxnet->client_conn_reaper,
- conn_expires_at - now);
+ timer_reduce(&rxnet->client_conn_reap_timer,
+ conn_expires_at);
out:
spin_unlock(&rxnet->client_conn_cache_lock);
rxnet->kill_all_client_conns = true;
spin_unlock(&rxnet->client_conn_cache_lock);
- cancel_delayed_work(&rxnet->client_conn_reaper);
+ del_timer_sync(&rxnet->client_conn_reap_timer);
- if (!queue_delayed_work(rxrpc_workqueue, &rxnet->client_conn_reaper, 0))
+ if (!rxrpc_queue_work(&rxnet->client_conn_reaper))
_debug("destroy: queue failed");
_leave("");
* Retransmit terminal ACK or ABORT of the previous call.
*/
static void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn,
- struct sk_buff *skb)
+ struct sk_buff *skb,
+ unsigned int channel)
{
- struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
+ struct rxrpc_skb_priv *sp = skb ? rxrpc_skb(skb) : NULL;
struct rxrpc_channel *chan;
struct msghdr msg;
struct kvec iov;
_enter("%d", conn->debug_id);
- chan = &conn->channels[sp->hdr.cid & RXRPC_CHANNELMASK];
+ chan = &conn->channels[channel];
/* If the last call got moved on whilst we were waiting to run, just
* ignore this packet.
call_id = READ_ONCE(chan->last_call);
/* Sync with __rxrpc_disconnect_call() */
smp_rmb();
- if (call_id != sp->hdr.callNumber)
+ if (skb && call_id != sp->hdr.callNumber)
return;
msg.msg_name = &conn->params.peer->srx.transport;
msg.msg_controllen = 0;
msg.msg_flags = 0;
- pkt.whdr.epoch = htonl(sp->hdr.epoch);
- pkt.whdr.cid = htonl(sp->hdr.cid);
- pkt.whdr.callNumber = htonl(sp->hdr.callNumber);
+ pkt.whdr.epoch = htonl(conn->proto.epoch);
+ pkt.whdr.cid = htonl(conn->proto.cid);
+ pkt.whdr.callNumber = htonl(call_id);
pkt.whdr.seq = 0;
pkt.whdr.type = chan->last_type;
pkt.whdr.flags = conn->out_clientflag;
mtu = conn->params.peer->if_mtu;
mtu -= conn->params.peer->hdrsize;
pkt.ack.bufferSpace = 0;
- pkt.ack.maxSkew = htons(skb->priority);
- pkt.ack.firstPacket = htonl(chan->last_seq);
- pkt.ack.previousPacket = htonl(chan->last_seq - 1);
- pkt.ack.serial = htonl(sp->hdr.serial);
- pkt.ack.reason = RXRPC_ACK_DUPLICATE;
+ pkt.ack.maxSkew = htons(skb ? skb->priority : 0);
+ pkt.ack.firstPacket = htonl(chan->last_seq + 1);
+ pkt.ack.previousPacket = htonl(chan->last_seq);
+ pkt.ack.serial = htonl(skb ? sp->hdr.serial : 0);
+ pkt.ack.reason = skb ? RXRPC_ACK_DUPLICATE : RXRPC_ACK_IDLE;
pkt.ack.nAcks = 0;
pkt.info.rxMTU = htonl(rxrpc_rx_mtu);
pkt.info.maxMTU = htonl(mtu);
switch (sp->hdr.type) {
case RXRPC_PACKET_TYPE_DATA:
case RXRPC_PACKET_TYPE_ACK:
- rxrpc_conn_retransmit_call(conn, skb);
+ rxrpc_conn_retransmit_call(conn, skb,
+ sp->hdr.cid & RXRPC_CHANNELMASK);
return 0;
case RXRPC_PACKET_TYPE_BUSY:
}
/*
+ * Process delayed final ACKs that we haven't subsumed into a subsequent call.
+ */
+static void rxrpc_process_delayed_final_acks(struct rxrpc_connection *conn)
+{
+ unsigned long j = jiffies, next_j;
+ unsigned int channel;
+ bool set;
+
+again:
+ next_j = j + LONG_MAX;
+ set = false;
+ for (channel = 0; channel < RXRPC_MAXCALLS; channel++) {
+ struct rxrpc_channel *chan = &conn->channels[channel];
+ unsigned long ack_at;
+
+ if (!test_bit(RXRPC_CONN_FINAL_ACK_0 + channel, &conn->flags))
+ continue;
+
+ smp_rmb(); /* vs rxrpc_disconnect_client_call */
+ ack_at = READ_ONCE(chan->final_ack_at);
+
+ if (time_before(j, ack_at)) {
+ if (time_before(ack_at, next_j)) {
+ next_j = ack_at;
+ set = true;
+ }
+ continue;
+ }
+
+ if (test_and_clear_bit(RXRPC_CONN_FINAL_ACK_0 + channel,
+ &conn->flags))
+ rxrpc_conn_retransmit_call(conn, NULL, channel);
+ }
+
+ j = jiffies;
+ if (time_before_eq(next_j, j))
+ goto again;
+ if (set)
+ rxrpc_reduce_conn_timer(conn, next_j);
+}
+
+/*
* connection-level event processor
*/
void rxrpc_process_connection(struct work_struct *work)
if (test_and_clear_bit(RXRPC_CONN_EV_CHALLENGE, &conn->events))
rxrpc_secure_connection(conn);
+ /* Process delayed ACKs whose time has come. */
+ if (conn->flags & RXRPC_CONN_FINAL_ACK_MASK)
+ rxrpc_process_delayed_final_acks(conn);
+
/* go through the conn-level event packets, releasing the ref on this
* connection that each one has when we've finished with it */
while ((skb = skb_dequeue(&conn->rx_queue))) {
/*
* Time till a connection expires after last use (in seconds).
*/
-unsigned int rxrpc_connection_expiry = 10 * 60;
+unsigned int __read_mostly rxrpc_connection_expiry = 10 * 60;
+unsigned int __read_mostly rxrpc_closed_conn_expiry = 10;
static void rxrpc_destroy_connection(struct rcu_head *);
+static void rxrpc_connection_timer(struct timer_list *timer)
+{
+ struct rxrpc_connection *conn =
+ container_of(timer, struct rxrpc_connection, timer);
+
+ rxrpc_queue_conn(conn);
+}
+
/*
* allocate a new connection
*/
INIT_LIST_HEAD(&conn->cache_link);
spin_lock_init(&conn->channel_lock);
INIT_LIST_HEAD(&conn->waiting_calls);
+ timer_setup(&conn->timer, &rxrpc_connection_timer, 0);
INIT_WORK(&conn->processor, &rxrpc_process_connection);
INIT_LIST_HEAD(&conn->proc_link);
INIT_LIST_HEAD(&conn->link);
}
/*
+ * Set the service connection reap timer.
+ */
+static void rxrpc_set_service_reap_timer(struct rxrpc_net *rxnet,
+ unsigned long reap_at)
+{
+ if (rxnet->live)
+ timer_reduce(&rxnet->service_conn_reap_timer, reap_at);
+}
+
+/*
* Release a service connection
*/
void rxrpc_put_service_conn(struct rxrpc_connection *conn)
{
- struct rxrpc_net *rxnet;
const void *here = __builtin_return_address(0);
int n;
n = atomic_dec_return(&conn->usage);
trace_rxrpc_conn(conn, rxrpc_conn_put_service, n, here);
ASSERTCMP(n, >=, 0);
- if (n == 0) {
- rxnet = conn->params.local->rxnet;
- rxrpc_queue_delayed_work(&rxnet->service_conn_reaper, 0);
- }
+ if (n == 1)
+ rxrpc_set_service_reap_timer(conn->params.local->rxnet,
+ jiffies + rxrpc_connection_expiry);
}
/*
_net("DESTROY CONN %d", conn->debug_id);
+ del_timer_sync(&conn->timer);
rxrpc_purge_queue(&conn->rx_queue);
conn->security->clear(conn);
{
struct rxrpc_connection *conn, *_p;
struct rxrpc_net *rxnet =
- container_of(to_delayed_work(work),
- struct rxrpc_net, service_conn_reaper);
- unsigned long reap_older_than, earliest, idle_timestamp, now;
+ container_of(work, struct rxrpc_net, service_conn_reaper);
+ unsigned long expire_at, earliest, idle_timestamp, now;
LIST_HEAD(graveyard);
_enter("");
now = jiffies;
- reap_older_than = now - rxrpc_connection_expiry * HZ;
- earliest = ULONG_MAX;
+ earliest = now + MAX_JIFFY_OFFSET;
write_lock(&rxnet->conn_lock);
list_for_each_entry_safe(conn, _p, &rxnet->service_conns, link) {
if (conn->state == RXRPC_CONN_SERVICE_PREALLOC)
continue;
- idle_timestamp = READ_ONCE(conn->idle_timestamp);
- _debug("reap CONN %d { u=%d,t=%ld }",
- conn->debug_id, atomic_read(&conn->usage),
- (long)reap_older_than - (long)idle_timestamp);
-
- if (time_after(idle_timestamp, reap_older_than)) {
- if (time_before(idle_timestamp, earliest))
- earliest = idle_timestamp;
- continue;
+ if (rxnet->live) {
+ idle_timestamp = READ_ONCE(conn->idle_timestamp);
+ expire_at = idle_timestamp + rxrpc_connection_expiry * HZ;
+ if (conn->params.local->service_closed)
+ expire_at = idle_timestamp + rxrpc_closed_conn_expiry * HZ;
+
+ _debug("reap CONN %d { u=%d,t=%ld }",
+ conn->debug_id, atomic_read(&conn->usage),
+ (long)expire_at - (long)now);
+
+ if (time_before(now, expire_at)) {
+ if (time_before(expire_at, earliest))
+ earliest = expire_at;
+ continue;
+ }
}
/* The usage count sits at 1 whilst the object is unused on the
*/
if (atomic_cmpxchg(&conn->usage, 1, 0) != 1)
continue;
+ trace_rxrpc_conn(conn, rxrpc_conn_reap_service, 0, 0);
if (rxrpc_conn_is_client(conn))
BUG();
}
write_unlock(&rxnet->conn_lock);
- if (earliest != ULONG_MAX) {
- _debug("reschedule reaper %ld", (long) earliest - now);
+ if (earliest != now + MAX_JIFFY_OFFSET) {
+ _debug("reschedule reaper %ld", (long)earliest - (long)now);
ASSERT(time_after(earliest, now));
- rxrpc_queue_delayed_work(&rxnet->client_conn_reaper,
- earliest - now);
+ rxrpc_set_service_reap_timer(rxnet, earliest);
}
while (!list_empty(&graveyard)) {
rxrpc_destroy_all_client_connections(rxnet);
- rxrpc_connection_expiry = 0;
- cancel_delayed_work(&rxnet->client_conn_reaper);
- rxrpc_queue_delayed_work(&rxnet->client_conn_reaper, 0);
+ del_timer_sync(&rxnet->service_conn_reap_timer);
+ rxrpc_queue_work(&rxnet->service_conn_reaper);
flush_workqueue(rxrpc_workqueue);
write_lock(&rxnet->conn_lock);
static bool rxrpc_receiving_reply(struct rxrpc_call *call)
{
struct rxrpc_ack_summary summary = { 0 };
+ unsigned long now, timo;
rxrpc_seq_t top = READ_ONCE(call->tx_top);
if (call->ackr_reason) {
spin_lock_bh(&call->lock);
call->ackr_reason = 0;
- call->resend_at = call->expire_at;
- call->ack_at = call->expire_at;
spin_unlock_bh(&call->lock);
- rxrpc_set_timer(call, rxrpc_timer_init_for_reply,
- ktime_get_real());
+ now = jiffies;
+ timo = now + MAX_JIFFY_OFFSET;
+ WRITE_ONCE(call->resend_at, timo);
+ WRITE_ONCE(call->ack_at, timo);
+ trace_rxrpc_timer(call, rxrpc_timer_init_for_reply, now);
}
if (!test_bit(RXRPC_CALL_TX_LAST, &call->flags))
if (state >= RXRPC_CALL_COMPLETE)
return;
+ if (call->state == RXRPC_CALL_SERVER_RECV_REQUEST) {
+ unsigned long timo = READ_ONCE(call->next_req_timo);
+ unsigned long now, expect_req_by;
+
+ if (timo) {
+ now = jiffies;
+ expect_req_by = now + timo;
+ WRITE_ONCE(call->expect_req_by, expect_req_by);
+ rxrpc_reduce_call_timer(call, expect_req_by, now,
+ rxrpc_timer_set_for_idle);
+ }
+ }
+
/* Received data implicitly ACKs all of the request packets we sent
* when we're acting as a client.
*/
}
/*
+ * Process the response to a ping that we sent to find out if we lost an ACK.
+ *
+ * If we got back a ping response that indicates a lower tx_top than what we
+ * had at the time of the ping transmission, we adjudge all the DATA packets
+ * sent between the response tx_top and the ping-time tx_top to have been lost.
+ */
+static void rxrpc_input_check_for_lost_ack(struct rxrpc_call *call)
+{
+ rxrpc_seq_t top, bottom, seq;
+ bool resend = false;
+
+ spin_lock_bh(&call->lock);
+
+ bottom = call->tx_hard_ack + 1;
+ top = call->acks_lost_top;
+ if (before(bottom, top)) {
+ for (seq = bottom; before_eq(seq, top); seq++) {
+ int ix = seq & RXRPC_RXTX_BUFF_MASK;
+ u8 annotation = call->rxtx_annotations[ix];
+ u8 anno_type = annotation & RXRPC_TX_ANNO_MASK;
+
+ if (anno_type != RXRPC_TX_ANNO_UNACK)
+ continue;
+ annotation &= ~RXRPC_TX_ANNO_MASK;
+ annotation |= RXRPC_TX_ANNO_RETRANS;
+ call->rxtx_annotations[ix] = annotation;
+ resend = true;
+ }
+ }
+
+ spin_unlock_bh(&call->lock);
+
+ if (resend && !test_and_set_bit(RXRPC_CALL_EV_RESEND, &call->events))
+ rxrpc_queue_call(call);
+}
+
+/*
* Process a ping response.
*/
static void rxrpc_input_ping_response(struct rxrpc_call *call,
smp_rmb();
ping_serial = call->ping_serial;
+ if (orig_serial == call->acks_lost_ping)
+ rxrpc_input_check_for_lost_ack(call);
+
if (!test_bit(RXRPC_CALL_PINGING, &call->flags) ||
before(orig_serial, ping_serial))
return;
struct sk_buff *skb, u16 skew)
{
struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
+ unsigned long timo;
_enter("%p,%p", call, skb);
+ timo = READ_ONCE(call->next_rx_timo);
+ if (timo) {
+ unsigned long now = jiffies, expect_rx_by;
+
+ expect_rx_by = jiffies + timo;
+ WRITE_ONCE(call->expect_rx_by, expect_rx_by);
+ rxrpc_reduce_call_timer(call, expect_rx_by, now,
+ rxrpc_timer_set_for_normal);
+ }
+
switch (sp->hdr.type) {
case RXRPC_PACKET_TYPE_DATA:
rxrpc_input_data(call, skb, skew);
unsigned int rxrpc_max_backlog __read_mostly = 10;
/*
- * Maximum lifetime of a call (in mx).
- */
-unsigned int rxrpc_max_call_lifetime = 60 * 1000;
-
-/*
* How long to wait before scheduling ACK generation after seeing a
- * packet with RXRPC_REQUEST_ACK set (in ms).
+ * packet with RXRPC_REQUEST_ACK set (in jiffies).
*/
-unsigned int rxrpc_requested_ack_delay = 1;
+unsigned long rxrpc_requested_ack_delay = 1;
/*
- * How long to wait before scheduling an ACK with subtype DELAY (in ms).
+ * How long to wait before scheduling an ACK with subtype DELAY (in jiffies).
*
* We use this when we've received new data packets. If those packets aren't
* all consumed within this time we will send a DELAY ACK if an ACK was not
* requested to let the sender know it doesn't need to resend.
*/
-unsigned int rxrpc_soft_ack_delay = 1 * 1000;
+unsigned long rxrpc_soft_ack_delay = HZ;
/*
- * How long to wait before scheduling an ACK with subtype IDLE (in ms).
+ * How long to wait before scheduling an ACK with subtype IDLE (in jiffies).
*
* We use this when we've consumed some previously soft-ACK'd packets when
* further packets aren't immediately received to decide when to send an IDLE
* ACK let the other end know that it can free up its Tx buffer space.
*/
-unsigned int rxrpc_idle_ack_delay = 0.5 * 1000;
+unsigned long rxrpc_idle_ack_delay = HZ / 2;
/*
* Receive window size in packets. This indicates the maximum number of
/*
* Time till packet resend (in milliseconds).
*/
-unsigned int rxrpc_resend_timeout = 4 * 1000;
+unsigned long rxrpc_resend_timeout = 4 * HZ;
const s8 rxrpc_ack_priority[] = {
[0] = 0,
unsigned int rxrpc_net_id;
+static void rxrpc_client_conn_reap_timeout(struct timer_list *timer)
+{
+ struct rxrpc_net *rxnet =
+ container_of(timer, struct rxrpc_net, client_conn_reap_timer);
+
+ if (rxnet->live)
+ rxrpc_queue_work(&rxnet->client_conn_reaper);
+}
+
+static void rxrpc_service_conn_reap_timeout(struct timer_list *timer)
+{
+ struct rxrpc_net *rxnet =
+ container_of(timer, struct rxrpc_net, service_conn_reap_timer);
+
+ if (rxnet->live)
+ rxrpc_queue_work(&rxnet->service_conn_reaper);
+}
+
/*
* Initialise a per-network namespace record.
*/
struct rxrpc_net *rxnet = rxrpc_net(net);
int ret;
+ rxnet->live = true;
get_random_bytes(&rxnet->epoch, sizeof(rxnet->epoch));
rxnet->epoch |= RXRPC_RANDOM_EPOCH;
INIT_LIST_HEAD(&rxnet->conn_proc_list);
INIT_LIST_HEAD(&rxnet->service_conns);
rwlock_init(&rxnet->conn_lock);
- INIT_DELAYED_WORK(&rxnet->service_conn_reaper,
- rxrpc_service_connection_reaper);
+ INIT_WORK(&rxnet->service_conn_reaper,
+ rxrpc_service_connection_reaper);
+ timer_setup(&rxnet->service_conn_reap_timer,
+ rxrpc_service_conn_reap_timeout, 0);
rxnet->nr_client_conns = 0;
rxnet->nr_active_client_conns = 0;
INIT_LIST_HEAD(&rxnet->waiting_client_conns);
INIT_LIST_HEAD(&rxnet->active_client_conns);
INIT_LIST_HEAD(&rxnet->idle_client_conns);
- INIT_DELAYED_WORK(&rxnet->client_conn_reaper,
- rxrpc_discard_expired_client_conns);
+ INIT_WORK(&rxnet->client_conn_reaper,
+ rxrpc_discard_expired_client_conns);
+ timer_setup(&rxnet->client_conn_reap_timer,
+ rxrpc_client_conn_reap_timeout, 0);
INIT_LIST_HEAD(&rxnet->local_endpoints);
mutex_init(&rxnet->local_mutex);
return 0;
err_proc:
+ rxnet->live = false;
return ret;
}
{
struct rxrpc_net *rxnet = rxrpc_net(net);
+ rxnet->live = false;
rxrpc_destroy_all_calls(rxnet);
rxrpc_destroy_all_connections(rxnet);
rxrpc_destroy_all_locals(rxnet);
};
/*
+ * Arrange for a keepalive ping a certain time after we last transmitted. This
+ * lets the far side know we're still interested in this call and helps keep
+ * the route through any intervening firewall open.
+ *
+ * Receiving a response to the ping will prevent the ->expect_rx_by timer from
+ * expiring.
+ */
+static void rxrpc_set_keepalive(struct rxrpc_call *call)
+{
+ unsigned long now = jiffies, keepalive_at = call->next_rx_timo / 6;
+
+ keepalive_at += now;
+ WRITE_ONCE(call->keepalive_at, keepalive_at);
+ rxrpc_reduce_call_timer(call, keepalive_at, now,
+ rxrpc_timer_set_for_keepalive);
+}
+
+/*
* Fill out an ACK packet.
*/
static size_t rxrpc_fill_out_ack(struct rxrpc_connection *conn,
/*
* Send an ACK call packet.
*/
-int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping)
+int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping,
+ rxrpc_serial_t *_serial)
{
struct rxrpc_connection *conn = NULL;
struct rxrpc_ack_buffer *pkt;
ntohl(pkt->ack.firstPacket),
ntohl(pkt->ack.serial),
pkt->ack.reason, pkt->ack.nAcks);
+ if (_serial)
+ *_serial = serial;
if (ping) {
call->ping_serial = serial;
call->ackr_seen = top;
spin_unlock_bh(&call->lock);
}
+
+ rxrpc_set_keepalive(call);
}
out:
* ACKs if a DATA packet appears to have been lost.
*/
if (!(sp->hdr.flags & RXRPC_LAST_PACKET) &&
- (retrans ||
+ (test_and_clear_bit(RXRPC_CALL_EV_ACK_LOST, &call->events) ||
+ retrans ||
call->cong_mode == RXRPC_CALL_SLOW_START ||
(call->peer->rtt_usage < 3 && sp->hdr.seq & 1) ||
ktime_before(ktime_add_ms(call->peer->rtt_last_req, 1000),
if (whdr.flags & RXRPC_REQUEST_ACK) {
call->peer->rtt_last_req = now;
trace_rxrpc_rtt_tx(call, rxrpc_rtt_tx_data, serial);
+ if (call->peer->rtt_usage > 1) {
+ unsigned long nowj = jiffies, ack_lost_at;
+
+ ack_lost_at = nsecs_to_jiffies(2 * call->peer->rtt);
+ if (ack_lost_at < 1)
+ ack_lost_at = 1;
+
+ ack_lost_at += nowj;
+ WRITE_ONCE(call->ack_lost_at, ack_lost_at);
+ rxrpc_reduce_call_timer(call, ack_lost_at, nowj,
+ rxrpc_timer_set_for_lost_ack);
+ }
}
}
+
+ rxrpc_set_keepalive(call);
+
_leave(" = %d [%u]", ret, call->peer->maxdata);
return ret;
trace_rxrpc_receive(call, rxrpc_receive_end, 0, call->rx_top);
ASSERTCMP(call->rx_hard_ack, ==, call->rx_top);
+#if 0 // TODO: May want to transmit final ACK under some circumstances anyway
if (call->state == RXRPC_CALL_CLIENT_RECV_REPLY) {
rxrpc_propose_ACK(call, RXRPC_ACK_IDLE, 0, serial, true, false,
rxrpc_propose_ack_terminal_ack);
- rxrpc_send_ack_packet(call, false);
+ rxrpc_send_ack_packet(call, false, NULL);
}
+#endif
write_lock_bh(&call->state_lock);
case RXRPC_CALL_SERVER_RECV_REQUEST:
call->tx_phase = true;
call->state = RXRPC_CALL_SERVER_ACK_REQUEST;
- call->ack_at = call->expire_at;
+ call->expect_req_by = jiffies + MAX_JIFFY_OFFSET;
write_unlock_bh(&call->state_lock);
rxrpc_propose_ACK(call, RXRPC_ACK_DELAY, 0, serial, false, true,
rxrpc_propose_ack_processing_op);
after_eq(top, call->ackr_seen + 2) ||
(hard_ack == top && after(hard_ack, call->ackr_consumed)))
rxrpc_propose_ACK(call, RXRPC_ACK_DELAY, 0, serial,
- true, false,
+ true, true,
rxrpc_propose_ack_rotate_rx);
- if (call->ackr_reason)
- rxrpc_send_ack_packet(call, false);
+ if (call->ackr_reason && call->ackr_reason != RXRPC_ACK_DELAY)
+ rxrpc_send_ack_packet(call, false, NULL);
}
}
#include <net/af_rxrpc.h>
#include "ar-internal.h"
-enum rxrpc_command {
- RXRPC_CMD_SEND_DATA, /* send data message */
- RXRPC_CMD_SEND_ABORT, /* request abort generation */
- RXRPC_CMD_ACCEPT, /* [server] accept incoming call */
- RXRPC_CMD_REJECT_BUSY, /* [server] reject a call as busy */
-};
-
-struct rxrpc_send_params {
- s64 tx_total_len; /* Total Tx data length (if send data) */
- unsigned long user_call_ID; /* User's call ID */
- u32 abort_code; /* Abort code to Tx (if abort) */
- enum rxrpc_command command : 8; /* The command to implement */
- bool exclusive; /* Shared or exclusive call */
- bool upgrade; /* If the connection is upgradeable */
-};
-
/*
* Wait for space to appear in the Tx queue or a signal to occur.
*/
rxrpc_notify_end_tx_t notify_end_tx)
{
struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
+ unsigned long now;
rxrpc_seq_t seq = sp->hdr.seq;
int ret, ix;
u8 annotation = RXRPC_TX_ANNO_UNACK;
break;
case RXRPC_CALL_SERVER_ACK_REQUEST:
call->state = RXRPC_CALL_SERVER_SEND_REPLY;
- call->ack_at = call->expire_at;
+ now = jiffies;
+ WRITE_ONCE(call->ack_at, now + MAX_JIFFY_OFFSET);
if (call->ackr_reason == RXRPC_ACK_DELAY)
call->ackr_reason = 0;
- __rxrpc_set_timer(call, rxrpc_timer_init_for_send_reply,
- ktime_get_real());
+ trace_rxrpc_timer(call, rxrpc_timer_init_for_send_reply, now);
if (!last)
break;
/* Fall through */
_debug("need instant resend %d", ret);
rxrpc_instant_resend(call, ix);
} else {
- ktime_t now = ktime_get_real(), resend_at;
-
- resend_at = ktime_add_ms(now, rxrpc_resend_timeout);
-
- if (ktime_before(resend_at, call->resend_at)) {
- call->resend_at = resend_at;
- rxrpc_set_timer(call, rxrpc_timer_set_for_send, now);
- }
+ unsigned long now = jiffies, resend_at;
+
+ if (call->peer->rtt_usage > 1)
+ resend_at = nsecs_to_jiffies(call->peer->rtt * 3 / 2);
+ else
+ resend_at = rxrpc_resend_timeout;
+ if (resend_at < 1)
+ resend_at = 1;
+
+ resend_at = now + rxrpc_resend_timeout;
+ WRITE_ONCE(call->resend_at, resend_at);
+ rxrpc_reduce_call_timer(call, resend_at, now,
+ rxrpc_timer_set_for_send);
}
rxrpc_free_skb(skb, rxrpc_skb_tx_freed);
do {
/* Check to see if there's a ping ACK to reply to. */
if (call->ackr_reason == RXRPC_ACK_PING_RESPONSE)
- rxrpc_send_ack_packet(call, false);
+ rxrpc_send_ack_packet(call, false, NULL);
if (!skb) {
size_t size, chunk, max, space;
if (msg->msg_flags & MSG_CMSG_COMPAT) {
if (len != sizeof(u32))
return -EINVAL;
- p->user_call_ID = *(u32 *)CMSG_DATA(cmsg);
+ p->call.user_call_ID = *(u32 *)CMSG_DATA(cmsg);
} else {
if (len != sizeof(unsigned long))
return -EINVAL;
- p->user_call_ID = *(unsigned long *)
+ p->call.user_call_ID = *(unsigned long *)
CMSG_DATA(cmsg);
}
got_user_ID = true;
break;
case RXRPC_TX_LENGTH:
- if (p->tx_total_len != -1 || len != sizeof(__s64))
+ if (p->call.tx_total_len != -1 || len != sizeof(__s64))
+ return -EINVAL;
+ p->call.tx_total_len = *(__s64 *)CMSG_DATA(cmsg);
+ if (p->call.tx_total_len < 0)
return -EINVAL;
- p->tx_total_len = *(__s64 *)CMSG_DATA(cmsg);
- if (p->tx_total_len < 0)
+ break;
+
+ case RXRPC_SET_CALL_TIMEOUT:
+ if (len & 3 || len < 4 || len > 12)
return -EINVAL;
+ memcpy(&p->call.timeouts, CMSG_DATA(cmsg), len);
+ p->call.nr_timeouts = len / 4;
+ if (p->call.timeouts.hard > INT_MAX / HZ)
+ return -ERANGE;
+ if (p->call.nr_timeouts >= 2 && p->call.timeouts.idle > 60 * 60 * 1000)
+ return -ERANGE;
+ if (p->call.nr_timeouts >= 3 && p->call.timeouts.normal > 60 * 60 * 1000)
+ return -ERANGE;
break;
default:
if (!got_user_ID)
return -EINVAL;
- if (p->tx_total_len != -1 && p->command != RXRPC_CMD_SEND_DATA)
+ if (p->call.tx_total_len != -1 && p->command != RXRPC_CMD_SEND_DATA)
return -EINVAL;
_leave(" = 0");
return 0;
cp.exclusive = rx->exclusive | p->exclusive;
cp.upgrade = p->upgrade;
cp.service_id = srx->srx_service;
- call = rxrpc_new_client_call(rx, &cp, srx, p->user_call_ID,
- p->tx_total_len, GFP_KERNEL);
+ call = rxrpc_new_client_call(rx, &cp, srx, &p->call, GFP_KERNEL);
/* The socket is now unlocked */
_leave(" = %p\n", call);
{
enum rxrpc_call_state state;
struct rxrpc_call *call;
+ unsigned long now, j;
int ret;
struct rxrpc_send_params p = {
- .tx_total_len = -1,
- .user_call_ID = 0,
- .abort_code = 0,
- .command = RXRPC_CMD_SEND_DATA,
- .exclusive = false,
- .upgrade = true,
+ .call.tx_total_len = -1,
+ .call.user_call_ID = 0,
+ .call.nr_timeouts = 0,
+ .abort_code = 0,
+ .command = RXRPC_CMD_SEND_DATA,
+ .exclusive = false,
+ .upgrade = false,
};
_enter("");
ret = -EINVAL;
if (rx->sk.sk_state != RXRPC_SERVER_LISTENING)
goto error_release_sock;
- call = rxrpc_accept_call(rx, p.user_call_ID, NULL);
+ call = rxrpc_accept_call(rx, p.call.user_call_ID, NULL);
/* The socket is now unlocked. */
if (IS_ERR(call))
return PTR_ERR(call);
- rxrpc_put_call(call, rxrpc_call_put);
- return 0;
+ ret = 0;
+ goto out_put_unlock;
}
- call = rxrpc_find_call_by_user_ID(rx, p.user_call_ID);
+ call = rxrpc_find_call_by_user_ID(rx, p.call.user_call_ID);
if (!call) {
ret = -EBADSLT;
if (p.command != RXRPC_CMD_SEND_DATA)
goto error_put;
}
- if (p.tx_total_len != -1) {
+ if (p.call.tx_total_len != -1) {
ret = -EINVAL;
if (call->tx_total_len != -1 ||
call->tx_pending ||
call->tx_top != 0)
goto error_put;
- call->tx_total_len = p.tx_total_len;
+ call->tx_total_len = p.call.tx_total_len;
+ }
+ }
+
+ switch (p.call.nr_timeouts) {
+ case 3:
+ j = msecs_to_jiffies(p.call.timeouts.normal);
+ if (p.call.timeouts.normal > 0 && j == 0)
+ j = 1;
+ WRITE_ONCE(call->next_rx_timo, j);
+ /* Fall through */
+ case 2:
+ j = msecs_to_jiffies(p.call.timeouts.idle);
+ if (p.call.timeouts.idle > 0 && j == 0)
+ j = 1;
+ WRITE_ONCE(call->next_req_timo, j);
+ /* Fall through */
+ case 1:
+ if (p.call.timeouts.hard > 0) {
+ j = msecs_to_jiffies(p.call.timeouts.hard);
+ now = jiffies;
+ j += now;
+ WRITE_ONCE(call->expect_term_by, j);
+ rxrpc_reduce_call_timer(call, j, now,
+ rxrpc_timer_set_for_hard);
}
+ break;
}
state = READ_ONCE(call->state);
ret = rxrpc_send_data(rx, call, msg, len, NULL);
}
+out_put_unlock:
mutex_unlock(&call->user_mutex);
error_put:
rxrpc_put_call(call, rxrpc_call_put);
static const unsigned int thirtytwo = 32;
static const unsigned int n_65535 = 65535;
static const unsigned int n_max_acks = RXRPC_RXTX_BUFF_SIZE - 1;
+static const unsigned long one_jiffy = 1;
+static const unsigned long max_jiffies = MAX_JIFFY_OFFSET;
/*
* RxRPC operating parameters.
* information on the individual parameters.
*/
static struct ctl_table rxrpc_sysctl_table[] = {
- /* Values measured in milliseconds */
+ /* Values measured in milliseconds but used in jiffies */
{
.procname = "req_ack_delay",
.data = &rxrpc_requested_ack_delay,
- .maxlen = sizeof(unsigned int),
+ .maxlen = sizeof(unsigned long),
.mode = 0644,
- .proc_handler = proc_dointvec,
- .extra1 = (void *)&zero,
+ .proc_handler = proc_doulongvec_ms_jiffies_minmax,
+ .extra1 = (void *)&one_jiffy,
+ .extra2 = (void *)&max_jiffies,
},
{
.procname = "soft_ack_delay",
.data = &rxrpc_soft_ack_delay,
- .maxlen = sizeof(unsigned int),
+ .maxlen = sizeof(unsigned long),
.mode = 0644,
- .proc_handler = proc_dointvec,
- .extra1 = (void *)&one,
+ .proc_handler = proc_doulongvec_ms_jiffies_minmax,
+ .extra1 = (void *)&one_jiffy,
+ .extra2 = (void *)&max_jiffies,
},
{
.procname = "idle_ack_delay",
.data = &rxrpc_idle_ack_delay,
- .maxlen = sizeof(unsigned int),
+ .maxlen = sizeof(unsigned long),
.mode = 0644,
- .proc_handler = proc_dointvec,
- .extra1 = (void *)&one,
- },
- {
- .procname = "resend_timeout",
- .data = &rxrpc_resend_timeout,
- .maxlen = sizeof(unsigned int),
- .mode = 0644,
- .proc_handler = proc_dointvec,
- .extra1 = (void *)&one,
+ .proc_handler = proc_doulongvec_ms_jiffies_minmax,
+ .extra1 = (void *)&one_jiffy,
+ .extra2 = (void *)&max_jiffies,
},
{
.procname = "idle_conn_expiry",
.data = &rxrpc_conn_idle_client_expiry,
- .maxlen = sizeof(unsigned int),
+ .maxlen = sizeof(unsigned long),
.mode = 0644,
- .proc_handler = proc_dointvec_ms_jiffies,
- .extra1 = (void *)&one,
+ .proc_handler = proc_doulongvec_ms_jiffies_minmax,
+ .extra1 = (void *)&one_jiffy,
+ .extra2 = (void *)&max_jiffies,
},
{
.procname = "idle_conn_fast_expiry",
.data = &rxrpc_conn_idle_client_fast_expiry,
- .maxlen = sizeof(unsigned int),
+ .maxlen = sizeof(unsigned long),
.mode = 0644,
- .proc_handler = proc_dointvec_ms_jiffies,
- .extra1 = (void *)&one,
+ .proc_handler = proc_doulongvec_ms_jiffies_minmax,
+ .extra1 = (void *)&one_jiffy,
+ .extra2 = (void *)&max_jiffies,
},
-
- /* Values measured in seconds but used in jiffies */
{
- .procname = "max_call_lifetime",
- .data = &rxrpc_max_call_lifetime,
- .maxlen = sizeof(unsigned int),
+ .procname = "resend_timeout",
+ .data = &rxrpc_resend_timeout,
+ .maxlen = sizeof(unsigned long),
.mode = 0644,
- .proc_handler = proc_dointvec,
- .extra1 = (void *)&one,
+ .proc_handler = proc_doulongvec_ms_jiffies_minmax,
+ .extra1 = (void *)&one_jiffy,
+ .extra2 = (void *)&max_jiffies,
},
/* Non-time values */
struct tcf_chain *chain, *tmp;
rtnl_lock();
- /* Only chain 0 should be still here. */
+
+ /* At this point, all the chains should have refcnt == 1. */
list_for_each_entry_safe(chain, tmp, &block->chain_list, list)
tcf_chain_put(chain);
rtnl_unlock();
}
/* XXX: Standalone actions are not allowed to jump to any chain, and bound
- * actions should be all removed after flushing. However, filters are now
- * destroyed in tc filter workqueue with RTNL lock, they can not race here.
+ * actions should be all removed after flushing.
*/
void tcf_block_put_ext(struct tcf_block *block, struct Qdisc *q,
struct tcf_block_ext_info *ei)
{
- struct tcf_chain *chain, *tmp;
+ struct tcf_chain *chain;
- list_for_each_entry_safe(chain, tmp, &block->chain_list, list)
+ /* Hold a refcnt for all chains, except 0, so that they don't disappear
+ * while we are iterating.
+ */
+ list_for_each_entry(chain, &block->chain_list, list)
+ if (chain->index)
+ tcf_chain_hold(chain);
+
+ list_for_each_entry(chain, &block->chain_list, list)
tcf_chain_flush(chain);
tcf_block_offload_unbind(block, q, ei);
return 0;
}
-static void __cls_bpf_delete_prog(struct cls_bpf_prog *prog)
+static void cls_bpf_free_parms(struct cls_bpf_prog *prog)
{
- tcf_exts_destroy(&prog->exts);
- tcf_exts_put_net(&prog->exts);
-
if (cls_bpf_is_ebpf(prog))
bpf_prog_put(prog->filter);
else
kfree(prog->bpf_name);
kfree(prog->bpf_ops);
+}
+
+static void __cls_bpf_delete_prog(struct cls_bpf_prog *prog)
+{
+ tcf_exts_destroy(&prog->exts);
+ tcf_exts_put_net(&prog->exts);
+
+ cls_bpf_free_parms(prog);
kfree(prog);
}
goto errout_idr;
ret = cls_bpf_offload(tp, prog, oldprog);
- if (ret) {
- if (!oldprog)
- idr_remove_ext(&head->handle_idr, prog->handle);
- __cls_bpf_delete_prog(prog);
- return ret;
- }
+ if (ret)
+ goto errout_parms;
if (!tc_in_hw(prog->gen_flags))
prog->gen_flags |= TCA_CLS_FLAGS_NOT_IN_HW;
*arg = prog;
return 0;
+errout_parms:
+ cls_bpf_free_parms(prog);
errout_idr:
if (!oldprog)
idr_remove_ext(&head->handle_idr, prog->handle);
if ((q->link.R_tab = qdisc_get_rtab(r, tb[TCA_CBQ_RTAB])) == NULL)
return -EINVAL;
+ err = tcf_block_get(&q->link.block, &q->link.filter_list, sch);
+ if (err)
+ goto put_rtab;
+
err = qdisc_class_hash_init(&q->clhash);
if (err < 0)
- goto put_rtab;
+ goto put_block;
q->link.sibling = &q->link;
q->link.common.classid = sch->handle;
cbq_addprio(q, &q->link);
return 0;
+put_block:
+ tcf_block_put(q->link.block);
+
put_rtab:
qdisc_put_rtab(q->link.R_tab);
return err;
int i;
int err;
+ q->sch = sch;
timer_setup(&q->perturb_timer, sfq_perturbation, TIMER_DEFERRABLE);
err = tcf_block_get(&q->block, &q->filter_list, sch);
INIT_LIST_HEAD(&sctp_address_families);
sctp_v4_pf_init();
sctp_v6_pf_init();
+ sctp_sched_ops_init();
status = register_pernet_subsys(&sctp_defaults_ops);
if (status)
list_for_each_entry(chunk, &t->transmitted, transmitted_list)
cb(chunk);
- list_for_each_entry(chunk, &q->retransmit, list)
+ list_for_each_entry(chunk, &q->retransmit, transmitted_list)
cb(chunk);
- list_for_each_entry(chunk, &q->sacked, list)
+ list_for_each_entry(chunk, &q->sacked, transmitted_list)
cb(chunk);
- list_for_each_entry(chunk, &q->abandoned, list)
+ list_for_each_entry(chunk, &q->abandoned, transmitted_list)
cb(chunk);
list_for_each_entry(chunk, &q->out_chunk_list, list)
*/
/* Mark as failed send. */
- sctp_chunk_fail(ch, SCTP_ERROR_INV_STRM);
+ sctp_chunk_fail(ch, (__force __u32)SCTP_ERROR_INV_STRM);
if (asoc->peer.prsctp_capable &&
SCTP_PR_PRIO_ENABLED(ch->sinfo.sinfo_flags))
asoc->sent_cnt_removable--;
return retval;
}
+static bool sctp_stream_outq_is_empty(struct sctp_stream *stream,
+ __u16 str_nums, __be16 *str_list)
+{
+ struct sctp_association *asoc;
+ __u16 i;
+
+ asoc = container_of(stream, struct sctp_association, stream);
+ if (!asoc->outqueue.out_qlen)
+ return true;
+
+ if (!str_nums)
+ return false;
+
+ for (i = 0; i < str_nums; i++) {
+ __u16 sid = ntohs(str_list[i]);
+
+ if (stream->out[sid].ext &&
+ !list_empty(&stream->out[sid].ext->outq))
+ return false;
+ }
+
+ return true;
+}
+
int sctp_send_reset_streams(struct sctp_association *asoc,
struct sctp_reset_streams *params)
{
for (i = 0; i < str_nums; i++)
nstr_list[i] = htons(str_list[i]);
+ if (out && !sctp_stream_outq_is_empty(stream, str_nums, nstr_list)) {
+ retval = -EAGAIN;
+ goto out;
+ }
+
chunk = sctp_make_strreset_req(asoc, str_nums, nstr_list, out, in);
kfree(nstr_list);
if (asoc->strreset_outstanding)
return -EINPROGRESS;
+ if (!sctp_outq_is_empty(&asoc->outqueue))
+ return -EAGAIN;
+
chunk = sctp_make_strreset_tsnreq(asoc);
if (!chunk)
return -ENOMEM;
flags = SCTP_STREAM_RESET_INCOMING_SSN;
}
- nums = (ntohs(param.p->length) - sizeof(*outreq)) / 2;
+ nums = (ntohs(param.p->length) - sizeof(*outreq)) / sizeof(__u16);
if (nums) {
str_p = outreq->list_of_streams;
for (i = 0; i < nums; i++) {
goto out;
}
- nums = (ntohs(param.p->length) - sizeof(*inreq)) / 2;
+ nums = (ntohs(param.p->length) - sizeof(*inreq)) / sizeof(__u16);
str_p = inreq->list_of_streams;
for (i = 0; i < nums; i++) {
if (ntohs(str_p[i]) >= stream->outcnt) {
}
}
+ if (!sctp_stream_outq_is_empty(stream, nums, str_p)) {
+ result = SCTP_STRRESET_IN_PROGRESS;
+ asoc->strreset_inseq--;
+ goto err;
+ }
+
chunk = sctp_make_strreset_req(asoc, nums, str_p, 1, 0);
if (!chunk)
goto out;
i = asoc->strreset_inseq - request_seq - 1;
result = asoc->strreset_result[i];
if (result == SCTP_STRRESET_PERFORMED) {
- next_tsn = asoc->next_tsn;
+ next_tsn = asoc->ctsn_ack_point + 1;
init_tsn =
sctp_tsnmap_get_ctsn(&asoc->peer.tsn_map) + 1;
}
goto err;
}
+
+ if (!sctp_outq_is_empty(&asoc->outqueue)) {
+ result = SCTP_STRRESET_IN_PROGRESS;
+ goto err;
+ }
+
asoc->strreset_inseq++;
if (!(asoc->strreset_enable & SCTP_ENABLE_RESET_ASSOC_REQ))
goto out;
}
- /* G3: The same processing as though a SACK chunk with no gap report
- * and a cumulative TSN ACK of the Sender's Next TSN minus 1 were
- * received MUST be performed.
+ /* G4: The same processing as though a FWD-TSN chunk (as defined in
+ * [RFC3758]) with all streams affected and a new cumulative TSN
+ * ACK of the Receiver's Next TSN minus 1 were received MUST be
+ * performed.
*/
max_tsn_seen = sctp_tsnmap_get_max_tsn_seen(&asoc->peer.tsn_map);
sctp_ulpq_reasm_flushtsn(&asoc->ulpq, max_tsn_seen);
sctp_tsnmap_init(&asoc->peer.tsn_map, SCTP_TSN_MAP_INITIAL,
init_tsn, GFP_ATOMIC);
- /* G4: The same processing as though a FWD-TSN chunk (as defined in
- * [RFC3758]) with all streams affected and a new cumulative TSN
- * ACK of the Receiver's Next TSN minus 1 were received MUST be
- * performed.
+ /* G3: The same processing as though a SACK chunk with no gap report
+ * and a cumulative TSN ACK of the Sender's Next TSN minus 1 were
+ * received MUST be performed.
*/
sctp_outq_free(&asoc->outqueue);
outreq = (struct sctp_strreset_outreq *)req;
str_p = outreq->list_of_streams;
- nums = (ntohs(outreq->param_hdr.length) - sizeof(*outreq)) / 2;
+ nums = (ntohs(outreq->param_hdr.length) - sizeof(*outreq)) /
+ sizeof(__u16);
if (result == SCTP_STRRESET_PERFORMED) {
if (nums) {
inreq = (struct sctp_strreset_inreq *)req;
str_p = inreq->list_of_streams;
- nums = (ntohs(inreq->param_hdr.length) - sizeof(*inreq)) / 2;
+ nums = (ntohs(inreq->param_hdr.length) - sizeof(*inreq)) /
+ sizeof(__u16);
*evp = sctp_ulpevent_make_stream_reset_event(asoc, flags,
nums, str_p, GFP_ATOMIC);
if (result == SCTP_STRRESET_PERFORMED) {
__u32 mtsn = sctp_tsnmap_get_max_tsn_seen(
&asoc->peer.tsn_map);
+ LIST_HEAD(temp);
sctp_ulpq_reasm_flushtsn(&asoc->ulpq, mtsn);
sctp_ulpq_abort_pd(&asoc->ulpq, GFP_ATOMIC);
SCTP_TSN_MAP_INITIAL,
stsn, GFP_ATOMIC);
+ /* Clean up sacked and abandoned queues only. As the
+ * out_chunk_list may not be empty, splice it to temp,
+ * then get it back after sctp_outq_free is done.
+ */
+ list_splice_init(&asoc->outqueue.out_chunk_list, &temp);
sctp_outq_free(&asoc->outqueue);
+ list_splice_init(&temp, &asoc->outqueue.out_chunk_list);
asoc->next_tsn = rtsn;
asoc->ctsn_ack_point = asoc->next_tsn - 1;
.unsched_all = sctp_sched_fcfs_unsched_all,
};
+static void sctp_sched_ops_fcfs_init(void)
+{
+ sctp_sched_ops_register(SCTP_SS_FCFS, &sctp_sched_fcfs);
+}
+
/* API to other parts of the stack */
-extern struct sctp_sched_ops sctp_sched_prio;
-extern struct sctp_sched_ops sctp_sched_rr;
+static struct sctp_sched_ops *sctp_sched_ops[SCTP_SS_MAX + 1];
-static struct sctp_sched_ops *sctp_sched_ops[] = {
- &sctp_sched_fcfs,
- &sctp_sched_prio,
- &sctp_sched_rr,
-};
+void sctp_sched_ops_register(enum sctp_sched_type sched,
+ struct sctp_sched_ops *sched_ops)
+{
+ sctp_sched_ops[sched] = sched_ops;
+}
+
+void sctp_sched_ops_init(void)
+{
+ sctp_sched_ops_fcfs_init();
+ sctp_sched_ops_prio_init();
+ sctp_sched_ops_rr_init();
+}
int sctp_sched_set_sched(struct sctp_association *asoc,
enum sctp_sched_type sched)
sctp_sched_prio_unsched(soute);
}
-struct sctp_sched_ops sctp_sched_prio = {
+static struct sctp_sched_ops sctp_sched_prio = {
.set = sctp_sched_prio_set,
.get = sctp_sched_prio_get,
.init = sctp_sched_prio_init,
.sched_all = sctp_sched_prio_sched_all,
.unsched_all = sctp_sched_prio_unsched_all,
};
+
+void sctp_sched_ops_prio_init(void)
+{
+ sctp_sched_ops_register(SCTP_SS_PRIO, &sctp_sched_prio);
+}
sctp_sched_rr_unsched(stream, soute);
}
-struct sctp_sched_ops sctp_sched_rr = {
+static struct sctp_sched_ops sctp_sched_rr = {
.set = sctp_sched_rr_set,
.get = sctp_sched_rr_get,
.init = sctp_sched_rr_init,
.sched_all = sctp_sched_rr_sched_all,
.unsched_all = sctp_sched_rr_unsched_all,
};
+
+void sctp_sched_ops_rr_init(void)
+{
+ sctp_sched_ops_register(SCTP_SS_RR, &sctp_sched_rr);
+}
return status;
}
-static struct cache_detail rsi_cache_template = {
+static const struct cache_detail rsi_cache_template = {
.owner = THIS_MODULE,
.hash_size = RSI_HASHMAX,
.name = "auth.rpcsec.init",
return status;
}
-static struct cache_detail rsc_cache_template = {
+static const struct cache_detail rsc_cache_template = {
.owner = THIS_MODULE,
.hash_size = RSC_HASHMAX,
.name = "auth.rpcsec.context",
}
EXPORT_SYMBOL_GPL(cache_unregister_net);
-struct cache_detail *cache_create_net(struct cache_detail *tmpl, struct net *net)
+struct cache_detail *cache_create_net(const struct cache_detail *tmpl, struct net *net)
{
struct cache_detail *cd;
int i;
return 0;
}
-static struct cache_detail unix_gid_cache_template = {
+static const struct cache_detail unix_gid_cache_template = {
.owner = THIS_MODULE,
.hash_size = GID_HASHMAX,
.name = "auth.unix.gid",
.set_client = svcauth_unix_set_client,
};
-static struct cache_detail ip_map_cache_template = {
+static const struct cache_detail ip_map_cache_template = {
.owner = THIS_MODULE,
.hash_size = IP_HASHMAX,
.name = "auth.unix.ip",
while ((skb = skb_peek(defq))) {
hdr = buf_msg(skb);
mtyp = msg_type(hdr);
+ blks = msg_blocks(hdr);
deliver = true;
ack = false;
update = false;
if (!update)
continue;
- blks = msg_blocks(hdr);
tipc_group_update_rcv_win(grp, blks, node, port, xmitq);
}
return;
/* We should not be sending anymore since the peer won't be
* there to receive, but we can still receive if there is data
- * left in our consume queue.
+ * left in our consume queue. If the local endpoint is a host,
+ * we can't call vsock_stream_has_data, since that may block,
+ * but a host endpoint can't read data once the VM has
+ * detached, so there is no available data in that case.
*/
- if (vsock_stream_has_data(vsk) <= 0) {
- sk->sk_state = TCP_CLOSE;
-
+ if (vsk->local_addr.svm_cid == VMADDR_CID_HOST ||
+ vsock_stream_has_data(vsk) <= 0) {
if (sk->sk_state == TCP_SYN_SENT) {
/* The peer may detach from a queue pair while
* we are still in the connecting state, i.e.,
* event like a reset.
*/
+ sk->sk_state = TCP_CLOSE;
sk->sk_err = ECONNRESET;
sk->sk_error_report(sk);
return;
}
+ sk->sk_state = TCP_CLOSE;
}
sk->sk_state_change(sk);
}
MODULE_AUTHOR("VMware, Inc.");
MODULE_DESCRIPTION("VMCI transport for Virtual Sockets");
-MODULE_VERSION("1.0.4.0-k");
+MODULE_VERSION("1.0.5.0-k");
MODULE_LICENSE("GPL v2");
MODULE_ALIAS("vmware_vsock");
MODULE_ALIAS_NETPROTO(PF_VSOCK);
tristate "cfg80211 - wireless configuration API"
depends on RFKILL || !RFKILL
select FW_LOADER
+ # may need to update this when certificates are changed and are
+ # using a different algorithm, though right now they shouldn't
+ # (this is here rather than below to allow it to be a module)
+ select CRYPTO_SHA256 if CFG80211_USE_KERNEL_REGDB_KEYS
---help---
cfg80211 is the Linux wireless LAN (802.11) configuration API.
Enable this if you have a wireless device.
certificates like in the kernel sources (net/wireless/certs/)
that shall be accepted for a signed regulatory database.
+ Note that you need to also select the correct CRYPTO_<hash> modules
+ for your certificates, and if cfg80211 is built-in they also must be.
+
config CFG80211_REG_CELLULAR_HINTS
bool "cfg80211 regulatory support for cellular base station hints"
depends on CFG80211_CERTIFICATION_ONUS
for d, n in delta:
if d: print("%-40s %7s %7s %+7d" % (n, old.get(n,"-"), new.get(n,"-"), d))
- print("Total: Before=%d, After=%d, chg %+.2f%%" % \
- (otot, ntot, (ntot - otot)*100.0/otot))
+ if otot:
+ percent = (ntot - otot) * 100.0 / otot
+ else:
+ percent = 0
+ print("Total: Before=%d, After=%d, chg %+.2f%%" % (otot, ntot, percent))
if sys.argv[1] == "-c":
print_result("Function", "tT", 3)
for (my $count = $linenr; $count <= $lc; $count++) {
my $fmt = get_quoted_string($lines[$count - 1], raw_line($count, 0));
$fmt =~ s/%%//g;
- if ($fmt =~ /(\%[\*\d\.]*p(?![\WFfSsBKRraEhMmIiUDdgVCbGNO]).)/) {
+ if ($fmt =~ /(\%[\*\d\.]*p(?![\WFfSsBKRraEhMmIiUDdgVCbGNOx]).)/) {
$bad_extension = $1;
last;
}
set -o errexit
set -o nounset
+READELF="${CROSS_COMPILE}readelf"
+ADDR2LINE="${CROSS_COMPILE}addr2line"
+SIZE="${CROSS_COMPILE}size"
+NM="${CROSS_COMPILE}nm"
+
command -v awk >/dev/null 2>&1 || die "awk isn't installed"
-command -v readelf >/dev/null 2>&1 || die "readelf isn't installed"
-command -v addr2line >/dev/null 2>&1 || die "addr2line isn't installed"
+command -v ${READELF} >/dev/null 2>&1 || die "readelf isn't installed"
+command -v ${ADDR2LINE} >/dev/null 2>&1 || die "addr2line isn't installed"
+command -v ${SIZE} >/dev/null 2>&1 || die "size isn't installed"
+command -v ${NM} >/dev/null 2>&1 || die "nm isn't installed"
usage() {
echo "usage: faddr2line <object file> <func+offset> <func+offset>..." >&2
find_dir_prefix() {
local objfile=$1
- local start_kernel_addr=$(readelf -sW $objfile | awk '$8 == "start_kernel" {printf "0x%s", $2}')
+ local start_kernel_addr=$(${READELF} -sW $objfile | awk '$8 == "start_kernel" {printf "0x%s", $2}')
[[ -z $start_kernel_addr ]] && return
- local file_line=$(addr2line -e $objfile $start_kernel_addr)
+ local file_line=$(${ADDR2LINE} -e $objfile $start_kernel_addr)
[[ -z $file_line ]] && return
local prefix=${file_line%init/main.c:*}
# Go through each of the object's symbols which match the func name.
# In rare cases there might be duplicates.
- file_end=$(size -Ax $objfile | awk '$1 == ".text" {print $2}')
+ file_end=$(${SIZE} -Ax $objfile | awk '$1 == ".text" {print $2}')
while read symbol; do
local fields=($symbol)
local sym_base=0x${fields[0]}
# pass real address to addr2line
echo "$func+$offset/$sym_size:"
- addr2line -fpie $objfile $addr | sed "s; $dir_prefix\(\./\)*; ;"
+ ${ADDR2LINE} -fpie $objfile $addr | sed "s; $dir_prefix\(\./\)*; ;"
DONE=1
- done < <(nm -n $objfile | awk -v fn=$func -v end=$file_end '$3 == fn { found=1; line=$0; start=$1; next } found == 1 { found=0; print line, "0x"$1 } END {if (found == 1) print line, end; }')
+ done < <(${NM} -n $objfile | awk -v fn=$func -v end=$file_end '$3 == fn { found=1; line=$0; start=$1; next } found == 1 { found=0; print line, "0x"$1 } END {if (found == 1) print line, end; }')
}
[[ $# -lt 2 ]] && usage
aafs_mnt = kern_mount(&aafs_ops);
if (IS_ERR(aafs_mnt))
panic("can't set apparmorfs up\n");
- aafs_mnt->mnt_sb->s_flags &= ~MS_NOUSER;
+ aafs_mnt->mnt_sb->s_flags &= ~SB_NOUSER;
/* Populate fs tree. */
error = entry_create_dir(&aa_sfs_entry, NULL);
/* these entries require a custom callback fn */
struct {
struct aa_label *peer;
- struct {
- const char *target;
- kuid_t ouid;
- } fs;
+ union {
+ struct {
+ const char *target;
+ kuid_t ouid;
+ } fs;
+ int signal;
+ };
};
struct {
struct aa_profile *profile;
const char *ns;
long pos;
} iface;
- int signal;
struct {
int rlim;
unsigned long max;
static inline bool path_mediated_fs(struct dentry *dentry)
{
- return !(dentry->d_sb->s_flags & MS_NOUSER);
+ return !(dentry->d_sb->s_flags & SB_NOUSER);
}
return -EINVAL;
}
csize = hdr->bControlSize;
- if (csize <= 1) {
+ if (!csize) {
usb_audio_dbg(state->chip,
- "unit %u: invalid bControlSize <= 1\n",
+ "unit %u: invalid bControlSize == 0\n",
unitid);
return -EINVAL;
}
dprintf("set %s as cpufreq governor\n", governor);
- if (cpupower_is_cpu_online(cpu) != 0) {
+ if (cpupower_is_cpu_online(cpu) != 1) {
perror("cpufreq_cpu_exists");
fprintf(stderr, "error: cpu %u does not exist\n", cpu);
return -1;
{
int num;
char *tmp;
+ int this_cpu;
+
+ this_cpu = sched_getcpu();
/* Assume idle state count is the same for all CPUs */
- cpuidle_sysfs_monitor.hw_states_num = cpuidle_state_count(0);
+ cpuidle_sysfs_monitor.hw_states_num = cpuidle_state_count(this_cpu);
if (cpuidle_sysfs_monitor.hw_states_num <= 0)
return NULL;
for (num = 0; num < cpuidle_sysfs_monitor.hw_states_num; num++) {
- tmp = cpuidle_state_name(0, num);
+ tmp = cpuidle_state_name(this_cpu, num);
if (tmp == NULL)
continue;
strncpy(cpuidle_cstates[num].name, tmp, CSTATE_NAME_LEN - 1);
free(tmp);
- tmp = cpuidle_state_desc(0, num);
+ tmp = cpuidle_state_desc(this_cpu, num);
if (tmp == NULL)
continue;
strncpy(cpuidle_cstates[num].desc, tmp, CSTATE_DESC_LEN - 1);
int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
{
int ret;
- sigset_t sigsaved;
if (unlikely(!kvm_vcpu_initialized(vcpu)))
return -ENOEXEC;
if (run->immediate_exit)
return -EINTR;
- if (vcpu->sigset_active)
- sigprocmask(SIG_SETMASK, &vcpu->sigset, &sigsaved);
+ kvm_sigset_activate(vcpu);
ret = 1;
run->exit_reason = KVM_EXIT_UNKNOWN;
kvm_pmu_update_run(vcpu);
}
- if (vcpu->sigset_active)
- sigprocmask(SIG_SETMASK, &sigsaved, NULL);
+ kvm_sigset_deactivate(vcpu);
+
return ret;
}
}
EXPORT_SYMBOL_GPL(kvm_vcpu_mark_page_dirty);
+void kvm_sigset_activate(struct kvm_vcpu *vcpu)
+{
+ if (!vcpu->sigset_active)
+ return;
+
+ /*
+ * This does a lockless modification of ->real_blocked, which is fine
+ * because, only current can change ->real_blocked and all readers of
+ * ->real_blocked don't care as long ->real_blocked is always a subset
+ * of ->blocked.
+ */
+ sigprocmask(SIG_SETMASK, &vcpu->sigset, ¤t->real_blocked);
+}
+
+void kvm_sigset_deactivate(struct kvm_vcpu *vcpu)
+{
+ if (!vcpu->sigset_active)
+ return;
+
+ sigprocmask(SIG_SETMASK, ¤t->real_blocked, NULL);
+ sigemptyset(¤t->real_blocked);
+}
+
static void grow_halt_poll_ns(struct kvm_vcpu *vcpu)
{
unsigned int old, val, grow;
projects / platform / kernel / linux-starfive.git / commitdiff