259 common osf_swapctl sys_ni_syscall
260 common osf_memcntl sys_ni_syscall
261 common osf_fdatasync sys_ni_syscall
-300 common bdflush sys_bdflush
+300 common bdflush sys_ni_syscall
301 common sethae sys_sethae
302 common mount sys_mount
303 common old_adjtimex sys_old_adjtimex
554 common landlock_create_ruleset sys_landlock_create_ruleset
555 common landlock_add_rule sys_landlock_add_rule
556 common landlock_restrict_self sys_landlock_restrict_self
+ # 557 reserved for memfd_secret
+ 558 common process_mrelease sys_process_mrelease
131 common quotactl sys_quotactl
132 common getpgid sys_getpgid
133 common fchdir sys_fchdir
-134 common bdflush sys_bdflush
+134 common bdflush sys_ni_syscall
135 common sysfs sys_sysfs
136 common personality sys_personality
# 137 was sys_afs_syscall
444 common landlock_create_ruleset sys_landlock_create_ruleset
445 common landlock_add_rule sys_landlock_add_rule
446 common landlock_restrict_self sys_landlock_restrict_self
+ # 447 reserved for memfd_secret
+ 448 common process_mrelease sys_process_mrelease
#define __NR_fchdir 133
__SYSCALL(__NR_fchdir, sys_fchdir)
#define __NR_bdflush 134
-__SYSCALL(__NR_bdflush, sys_bdflush)
+__SYSCALL(__NR_bdflush, sys_ni_syscall)
#define __NR_sysfs 135
__SYSCALL(__NR_sysfs, sys_sysfs)
#define __NR_personality 136
__SYSCALL(__NR_landlock_add_rule, sys_landlock_add_rule)
#define __NR_landlock_restrict_self 446
__SYSCALL(__NR_landlock_restrict_self, sys_landlock_restrict_self)
+ #define __NR_process_mrelease 448
+ __SYSCALL(__NR_process_mrelease, sys_process_mrelease)
/*
* Please add new compat syscalls above this comment and update
static void __init reserve_crashkernel(void)
{
unsigned long long crash_base, crash_size;
+ unsigned long long crash_max = arm64_dma_phys_limit;
int ret;
ret = parse_crashkernel(boot_command_line, memblock_phys_mem_size(),
crash_size = PAGE_ALIGN(crash_size);
- if (crash_base == 0) {
- /* Current arm64 boot protocol requires 2MB alignment */
- crash_base = memblock_find_in_range(0, arm64_dma_phys_limit,
- crash_size, SZ_2M);
- if (crash_base == 0) {
- pr_warn("cannot allocate crashkernel (size:0x%llx)\n",
- crash_size);
- return;
- }
- } else {
- /* User specifies base address explicitly. */
- if (!memblock_is_region_memory(crash_base, crash_size)) {
- pr_warn("cannot reserve crashkernel: region is not memory\n");
- return;
- }
+ /* User specifies base address explicitly. */
+ if (crash_base)
+ crash_max = crash_base + crash_size;
- if (memblock_is_region_reserved(crash_base, crash_size)) {
- pr_warn("cannot reserve crashkernel: region overlaps reserved memory\n");
- return;
- }
-
- if (!IS_ALIGNED(crash_base, SZ_2M)) {
- pr_warn("cannot reserve crashkernel: base address is not 2MB aligned\n");
- return;
- }
+ /* Current arm64 boot protocol requires 2MB alignment */
+ crash_base = memblock_phys_alloc_range(crash_size, SZ_2M,
+ crash_base, crash_max);
+ if (!crash_base) {
+ pr_warn("cannot allocate crashkernel (size:0x%llx)\n",
+ crash_size);
+ return;
}
- memblock_reserve(crash_base, crash_size);
pr_info("crashkernel reserved: 0x%016llx - 0x%016llx (%lld MB)\n",
crash_base, crash_base + crash_size, crash_size >> 20);
}
#endif /* CONFIG_KEXEC_CORE */
-#ifdef CONFIG_CRASH_DUMP
-static int __init early_init_dt_scan_elfcorehdr(unsigned long node,
- const char *uname, int depth, void *data)
-{
- const __be32 *reg;
- int len;
-
- if (depth != 1 || strcmp(uname, "chosen") != 0)
- return 0;
-
- reg = of_get_flat_dt_prop(node, "linux,elfcorehdr", &len);
- if (!reg || (len < (dt_root_addr_cells + dt_root_size_cells)))
- return 1;
-
- elfcorehdr_addr = dt_mem_next_cell(dt_root_addr_cells, ®);
- elfcorehdr_size = dt_mem_next_cell(dt_root_size_cells, ®);
-
- return 1;
-}
-
-/*
- * reserve_elfcorehdr() - reserves memory for elf core header
- *
- * This function reserves the memory occupied by an elf core header
- * described in the device tree. This region contains all the
- * information about primary kernel's core image and is used by a dump
- * capture kernel to access the system memory on primary kernel.
- */
-static void __init reserve_elfcorehdr(void)
-{
- of_scan_flat_dt(early_init_dt_scan_elfcorehdr, NULL);
-
- if (!elfcorehdr_size)
- return;
-
- if (memblock_is_region_reserved(elfcorehdr_addr, elfcorehdr_size)) {
- pr_warn("elfcorehdr is overlapped\n");
- return;
- }
-
- memblock_reserve(elfcorehdr_addr, elfcorehdr_size);
-
- pr_info("Reserving %lldKB of memory at 0x%llx for elfcorehdr\n",
- elfcorehdr_size >> 10, elfcorehdr_addr);
-}
-#else
-static void __init reserve_elfcorehdr(void)
-{
-}
-#endif /* CONFIG_CRASH_DUMP */
-
/*
* Return the maximum physical address for a zone accessible by the given bits
* limit. If DRAM starts above 32-bit, expand the zone to the maximum
}
early_param("mem", early_mem);
-static int __init early_init_dt_scan_usablemem(unsigned long node,
- const char *uname, int depth, void *data)
-{
- struct memblock_region *usablemem = data;
- const __be32 *reg;
- int len;
-
- if (depth != 1 || strcmp(uname, "chosen") != 0)
- return 0;
-
- reg = of_get_flat_dt_prop(node, "linux,usable-memory-range", &len);
- if (!reg || (len < (dt_root_addr_cells + dt_root_size_cells)))
- return 1;
-
- usablemem->base = dt_mem_next_cell(dt_root_addr_cells, ®);
- usablemem->size = dt_mem_next_cell(dt_root_size_cells, ®);
-
- return 1;
-}
-
-static void __init fdt_enforce_memory_region(void)
-{
- struct memblock_region reg = {
- .size = 0,
- };
-
- of_scan_flat_dt(early_init_dt_scan_usablemem, ®);
-
- if (reg.size)
- memblock_cap_memory_range(reg.base, reg.size);
-}
-
void __init arm64_memblock_init(void)
{
const s64 linear_region_size = PAGE_END - _PAGE_OFFSET(vabits_actual);
- /* Handle linux,usable-memory-range property */
- fdt_enforce_memory_region();
-
/* Remove memory above our supported physical address size */
memblock_remove(1ULL << PHYS_MASK_SHIFT, ULLONG_MAX);
early_init_fdt_scan_reserved_mem();
- reserve_elfcorehdr();
-
high_memory = __va(memblock_end_of_DRAM() - 1) + 1;
}
# 1135 was get_kernel_syms
# 1136 was query_module
113 common quotactl sys_quotactl
-114 common bdflush sys_bdflush
+114 common bdflush sys_ni_syscall
115 common sysfs sys_sysfs
116 common personality sys_personality
117 common afs_syscall sys_ni_syscall
444 common landlock_create_ruleset sys_landlock_create_ruleset
445 common landlock_add_rule sys_landlock_add_rule
446 common landlock_restrict_self sys_landlock_restrict_self
+ # 447 reserved for memfd_secret
+ 448 common process_mrelease sys_process_mrelease
131 common quotactl sys_quotactl
132 common getpgid sys_getpgid
133 common fchdir sys_fchdir
-134 common bdflush sys_bdflush
+134 common bdflush sys_ni_syscall
135 common sysfs sys_sysfs
136 common personality sys_personality
# 137 was afs_syscall
444 common landlock_create_ruleset sys_landlock_create_ruleset
445 common landlock_add_rule sys_landlock_add_rule
446 common landlock_restrict_self sys_landlock_restrict_self
+ # 447 reserved for memfd_secret
+ 448 common process_mrelease sys_process_mrelease
131 common quotactl sys_quotactl
132 common getpgid sys_getpgid
133 common fchdir sys_fchdir
-134 common bdflush sys_bdflush
+134 common bdflush sys_ni_syscall
135 common sysfs sys_sysfs
136 common personality sys_personality
137 common afs_syscall sys_ni_syscall
444 common landlock_create_ruleset sys_landlock_create_ruleset
445 common landlock_add_rule sys_landlock_add_rule
446 common landlock_restrict_self sys_landlock_restrict_self
+ # 447 reserved for memfd_secret
+ 448 common process_mrelease sys_process_mrelease
131 o32 quotactl sys_quotactl
132 o32 getpgid sys_getpgid
133 o32 fchdir sys_fchdir
-134 o32 bdflush sys_bdflush
+134 o32 bdflush sys_ni_syscall
135 o32 sysfs sys_sysfs
136 o32 personality sys_personality sys_32_personality
137 o32 afs_syscall sys_ni_syscall
444 o32 landlock_create_ruleset sys_landlock_create_ruleset
445 o32 landlock_add_rule sys_landlock_add_rule
446 o32 landlock_restrict_self sys_landlock_restrict_self
+ # 447 reserved for memfd_secret
+ 448 o32 process_mrelease sys_process_mrelease
131 common quotactl sys_quotactl
132 common getpgid sys_getpgid
133 common fchdir sys_fchdir
-134 common bdflush sys_bdflush
+134 common bdflush sys_ni_syscall
135 common sysfs sys_sysfs
136 32 personality parisc_personality
136 64 personality sys_personality
444 common landlock_create_ruleset sys_landlock_create_ruleset
445 common landlock_add_rule sys_landlock_add_rule
446 common landlock_restrict_self sys_landlock_restrict_self
+ # 447 reserved for memfd_secret
+ 448 common process_mrelease sys_process_mrelease
131 nospu quotactl sys_quotactl
132 common getpgid sys_getpgid
133 common fchdir sys_fchdir
-134 common bdflush sys_bdflush
+134 common bdflush sys_ni_syscall
135 common sysfs sys_sysfs
136 32 personality sys_personality ppc64_personality
136 64 personality ppc64_personality
444 common landlock_create_ruleset sys_landlock_create_ruleset
445 common landlock_add_rule sys_landlock_add_rule
446 common landlock_restrict_self sys_landlock_restrict_self
+ # 447 reserved for memfd_secret
+ 448 common process_mrelease sys_process_mrelease
crash_size = PAGE_ALIGN(crash_size);
- if (crash_base == 0) {
- /*
- * Current riscv boot protocol requires 2MB alignment for
- * RV64 and 4MB alignment for RV32 (hugepage size)
- */
- crash_base = memblock_find_in_range(search_start, search_end,
- crash_size, PMD_SIZE);
-
- if (crash_base == 0) {
- pr_warn("crashkernel: couldn't allocate %lldKB\n",
- crash_size >> 10);
- return;
- }
- } else {
- /* User specifies base address explicitly. */
- if (!memblock_is_region_memory(crash_base, crash_size)) {
- pr_warn("crashkernel: requested region is not memory\n");
- return;
- }
-
- if (memblock_is_region_reserved(crash_base, crash_size)) {
- pr_warn("crashkernel: requested region is reserved\n");
- return;
- }
-
+ if (crash_base) {
+ search_start = crash_base;
+ search_end = crash_base + crash_size;
+ }
- if (!IS_ALIGNED(crash_base, PMD_SIZE)) {
- pr_warn("crashkernel: requested region is misaligned\n");
- return;
- }
+ /*
+ * Current riscv boot protocol requires 2MB alignment for
+ * RV64 and 4MB alignment for RV32 (hugepage size)
+ */
+ crash_base = memblock_phys_alloc_range(crash_size, PMD_SIZE,
+ search_start, search_end);
+ if (crash_base == 0) {
+ pr_warn("crashkernel: couldn't allocate %lldKB\n",
+ crash_size >> 10);
+ return;
}
- memblock_reserve(crash_base, crash_size);
pr_info("crashkernel: reserved 0x%016llx - 0x%016llx (%lld MB)\n",
crash_base, crash_base + crash_size, crash_size >> 20);
}
#endif /* CONFIG_KEXEC_CORE */
-#ifdef CONFIG_CRASH_DUMP
-/*
- * We keep track of the ELF core header of the crashed
- * kernel with a reserved-memory region with compatible
- * string "linux,elfcorehdr". Here we register a callback
- * to populate elfcorehdr_addr/size when this region is
- * present. Note that this region will be marked as
- * reserved once we call early_init_fdt_scan_reserved_mem()
- * later on.
- */
-static int __init elfcore_hdr_setup(struct reserved_mem *rmem)
-{
- elfcorehdr_addr = rmem->base;
- elfcorehdr_size = rmem->size;
- return 0;
-}
-
-RESERVEDMEM_OF_DECLARE(elfcorehdr, "linux,elfcorehdr", elfcore_hdr_setup);
-#endif
-
void __init paging_init(void)
{
setup_bootmem();
unsigned int console_irq = -1;
EXPORT_SYMBOL(console_irq);
-unsigned long elf_hwcap __read_mostly = 0;
-char elf_platform[ELF_PLATFORM_SIZE];
+/*
+ * Some code and data needs to stay below 2 GB, even when the kernel would be
+ * relocated above 2 GB, because it has to use 31 bit addresses.
+ * Such code and data is part of the .amode31 section.
+ */
+unsigned long __amode31_ref __samode31 = __pa(&_samode31);
+unsigned long __amode31_ref __eamode31 = __pa(&_eamode31);
+unsigned long __amode31_ref __stext_amode31 = __pa(&_stext_amode31);
+unsigned long __amode31_ref __etext_amode31 = __pa(&_etext_amode31);
+struct exception_table_entry __amode31_ref *__start_amode31_ex_table = _start_amode31_ex_table;
+struct exception_table_entry __amode31_ref *__stop_amode31_ex_table = _stop_amode31_ex_table;
+
+/*
+ * Control registers CR2, CR5 and CR15 are initialized with addresses
+ * of tables that must be placed below 2G which is handled by the AMODE31
+ * sections.
+ * Because the AMODE31 sections are relocated below 2G at startup,
+ * the content of control registers CR2, CR5 and CR15 must be updated
+ * with new addresses after the relocation. The initial initialization of
+ * control registers occurs in head64.S and then gets updated again after AMODE31
+ * relocation. We must access the relevant AMODE31 tables indirectly via
+ * pointers placed in the .amode31.refs linker section. Those pointers get
+ * updated automatically during AMODE31 relocation and always contain a valid
+ * address within AMODE31 sections.
+ */
+
+static __amode31_data u32 __ctl_duct_amode31[16] __aligned(64);
+
+static __amode31_data u64 __ctl_aste_amode31[8] __aligned(64) = {
+ [1] = 0xffffffffffffffff
+};
+
+static __amode31_data u32 __ctl_duald_amode31[32] __aligned(128) = {
+ 0x80000000, 0, 0, 0,
+ 0x80000000, 0, 0, 0,
+ 0x80000000, 0, 0, 0,
+ 0x80000000, 0, 0, 0,
+ 0x80000000, 0, 0, 0,
+ 0x80000000, 0, 0, 0,
+ 0x80000000, 0, 0, 0,
+ 0x80000000, 0, 0, 0
+};
+
+static __amode31_data u32 __ctl_linkage_stack_amode31[8] __aligned(64) = {
+ 0, 0, 0x89000000, 0,
+ 0, 0, 0x8a000000, 0
+};
-unsigned long int_hwcap = 0;
+static u64 __amode31_ref *__ctl_aste = __ctl_aste_amode31;
+static u32 __amode31_ref *__ctl_duald = __ctl_duald_amode31;
+static u32 __amode31_ref *__ctl_linkage_stack = __ctl_linkage_stack_amode31;
+static u32 __amode31_ref *__ctl_duct = __ctl_duct_amode31;
int __bootdata(noexec_disabled);
unsigned long __bootdata(ident_map_size);
struct mem_detect_info __bootdata(mem_detect);
+struct initrd_data __bootdata(initrd_data);
-struct exception_table_entry *__bootdata_preserved(__start_dma_ex_table);
-struct exception_table_entry *__bootdata_preserved(__stop_dma_ex_table);
-unsigned long __bootdata_preserved(__stext_dma);
-unsigned long __bootdata_preserved(__etext_dma);
-unsigned long __bootdata_preserved(__sdma);
-unsigned long __bootdata_preserved(__edma);
unsigned long __bootdata_preserved(__kaslr_offset);
unsigned int __bootdata_preserved(zlib_dfltcc_support);
EXPORT_SYMBOL(zlib_dfltcc_support);
u64 __bootdata_preserved(stfle_fac_list[16]);
EXPORT_SYMBOL(stfle_fac_list);
u64 __bootdata_preserved(alt_stfle_fac_list[16]);
+struct oldmem_data __bootdata_preserved(oldmem_data);
unsigned long VMALLOC_START;
EXPORT_SYMBOL(VMALLOC_START);
{
if (!is_ipl_type_dump())
return;
- if (OLDMEM_BASE)
+ if (oldmem_data.start)
return;
strcat(boot_command_line, " cio_ignore=all,!ipldev,!condev");
console_loglevel = 2;
lc->restart_stack = (unsigned long) restart_stack;
lc->restart_fn = (unsigned long) do_restart;
lc->restart_data = 0;
- lc->restart_source = -1UL;
+ lc->restart_source = -1U;
mcck_stack = (unsigned long)memblock_alloc(THREAD_SIZE, THREAD_SIZE);
if (!mcck_stack)
static void __init setup_lowcore_dat_on(void)
{
+ struct lowcore *lc = lowcore_ptr[0];
+
__ctl_clear_bit(0, 28);
S390_lowcore.external_new_psw.mask |= PSW_MASK_DAT;
S390_lowcore.svc_new_psw.mask |= PSW_MASK_DAT;
S390_lowcore.program_new_psw.mask |= PSW_MASK_DAT;
S390_lowcore.io_new_psw.mask |= PSW_MASK_DAT;
+ __ctl_store(S390_lowcore.cregs_save_area, 0, 15);
__ctl_set_bit(0, 28);
+ mem_assign_absolute(S390_lowcore.restart_flags, RESTART_FLAG_CTLREGS);
+ mem_assign_absolute(S390_lowcore.program_new_psw, lc->program_new_psw);
+ memcpy_absolute(&S390_lowcore.cregs_save_area, lc->cregs_save_area,
+ sizeof(S390_lowcore.cregs_save_area));
}
static struct resource code_resource = {
return;
}
- low = crash_base ?: OLDMEM_BASE;
+ low = crash_base ?: oldmem_data.start;
high = low + crash_size;
- if (low >= OLDMEM_BASE && high <= OLDMEM_BASE + OLDMEM_SIZE) {
+ if (low >= oldmem_data.start && high <= oldmem_data.start + oldmem_data.size) {
/* The crashkernel fits into OLDMEM, reuse OLDMEM */
crash_base = low;
} else {
return;
}
low = crash_base ?: low;
- crash_base = memblock_find_in_range(low, high, crash_size,
- KEXEC_CRASH_MEM_ALIGN);
+ crash_base = memblock_phys_alloc_range(crash_size,
+ KEXEC_CRASH_MEM_ALIGN,
+ low, high);
}
if (!crash_base) {
return;
}
- if (register_memory_notifier(&kdump_mem_nb))
+ if (register_memory_notifier(&kdump_mem_nb)) {
+ memblock_free(crash_base, crash_size);
return;
+ }
- if (!OLDMEM_BASE && MACHINE_IS_VM)
+ if (!oldmem_data.start && MACHINE_IS_VM)
diag10_range(PFN_DOWN(crash_base), PFN_DOWN(crash_size));
crashk_res.start = crash_base;
crashk_res.end = crash_base + crash_size - 1;
static void __init reserve_initrd(void)
{
#ifdef CONFIG_BLK_DEV_INITRD
- if (!INITRD_START || !INITRD_SIZE)
+ if (!initrd_data.start || !initrd_data.size)
return;
- initrd_start = INITRD_START;
- initrd_end = initrd_start + INITRD_SIZE;
- memblock_reserve(INITRD_START, INITRD_SIZE);
+ initrd_start = initrd_data.start;
+ initrd_end = initrd_start + initrd_data.size;
+ memblock_reserve(initrd_data.start, initrd_data.size);
#endif
}
static void __init check_initrd(void)
{
#ifdef CONFIG_BLK_DEV_INITRD
- if (INITRD_START && INITRD_SIZE &&
- !memblock_is_region_memory(INITRD_START, INITRD_SIZE)) {
+ if (initrd_data.start && initrd_data.size &&
+ !memblock_is_region_memory(initrd_data.start, initrd_data.size)) {
pr_err("The initial RAM disk does not fit into the memory\n");
- memblock_free(INITRD_START, INITRD_SIZE);
+ memblock_free(initrd_data.start, initrd_data.size);
initrd_start = initrd_end = 0;
}
#endif
{
unsigned long start_pfn = PFN_UP(__pa(_end));
- memblock_reserve(0, HEAD_END);
+ memblock_reserve(0, STARTUP_NORMAL_OFFSET);
+ memblock_reserve((unsigned long)sclp_early_sccb, EXT_SCCB_READ_SCP);
memblock_reserve((unsigned long)_stext, PFN_PHYS(start_pfn)
- (unsigned long)_stext);
- memblock_reserve(__sdma, __edma - __sdma);
}
static void __init setup_memory(void)
memblock_enforce_memory_limit(memblock_end_of_DRAM());
}
-/*
- * Setup hardware capabilities.
- */
-static int __init setup_hwcaps(void)
+static void __init relocate_amode31_section(void)
{
- static const int stfl_bits[6] = { 0, 2, 7, 17, 19, 21 };
- struct cpuid cpu_id;
- int i;
-
- /*
- * The store facility list bits numbers as found in the principles
- * of operation are numbered with bit 1UL<<31 as number 0 to
- * bit 1UL<<0 as number 31.
- * Bit 0: instructions named N3, "backported" to esa-mode
- * Bit 2: z/Architecture mode is active
- * Bit 7: the store-facility-list-extended facility is installed
- * Bit 17: the message-security assist is installed
- * Bit 19: the long-displacement facility is installed
- * Bit 21: the extended-immediate facility is installed
- * Bit 22: extended-translation facility 3 is installed
- * Bit 30: extended-translation facility 3 enhancement facility
- * These get translated to:
- * HWCAP_S390_ESAN3 bit 0, HWCAP_S390_ZARCH bit 1,
- * HWCAP_S390_STFLE bit 2, HWCAP_S390_MSA bit 3,
- * HWCAP_S390_LDISP bit 4, HWCAP_S390_EIMM bit 5 and
- * HWCAP_S390_ETF3EH bit 8 (22 && 30).
- */
- for (i = 0; i < 6; i++)
- if (test_facility(stfl_bits[i]))
- elf_hwcap |= 1UL << i;
-
- if (test_facility(22) && test_facility(30))
- elf_hwcap |= HWCAP_S390_ETF3EH;
-
- /*
- * Check for additional facilities with store-facility-list-extended.
- * stfle stores doublewords (8 byte) with bit 1ULL<<63 as bit 0
- * and 1ULL<<0 as bit 63. Bits 0-31 contain the same information
- * as stored by stfl, bits 32-xxx contain additional facilities.
- * How many facility words are stored depends on the number of
- * doublewords passed to the instruction. The additional facilities
- * are:
- * Bit 42: decimal floating point facility is installed
- * Bit 44: perform floating point operation facility is installed
- * translated to:
- * HWCAP_S390_DFP bit 6 (42 && 44).
- */
- if ((elf_hwcap & (1UL << 2)) && test_facility(42) && test_facility(44))
- elf_hwcap |= HWCAP_S390_DFP;
-
- /*
- * Huge page support HWCAP_S390_HPAGE is bit 7.
- */
- if (MACHINE_HAS_EDAT1)
- elf_hwcap |= HWCAP_S390_HPAGE;
-
- /*
- * 64-bit register support for 31-bit processes
- * HWCAP_S390_HIGH_GPRS is bit 9.
- */
- elf_hwcap |= HWCAP_S390_HIGH_GPRS;
-
- /*
- * Transactional execution support HWCAP_S390_TE is bit 10.
- */
- if (MACHINE_HAS_TE)
- elf_hwcap |= HWCAP_S390_TE;
-
- /*
- * Vector extension HWCAP_S390_VXRS is bit 11. The Vector extension
- * can be disabled with the "novx" parameter. Use MACHINE_HAS_VX
- * instead of facility bit 129.
- */
- if (MACHINE_HAS_VX) {
- elf_hwcap |= HWCAP_S390_VXRS;
- if (test_facility(134))
- elf_hwcap |= HWCAP_S390_VXRS_BCD;
- if (test_facility(135))
- elf_hwcap |= HWCAP_S390_VXRS_EXT;
- if (test_facility(148))
- elf_hwcap |= HWCAP_S390_VXRS_EXT2;
- if (test_facility(152))
- elf_hwcap |= HWCAP_S390_VXRS_PDE;
- }
- if (test_facility(150))
- elf_hwcap |= HWCAP_S390_SORT;
- if (test_facility(151))
- elf_hwcap |= HWCAP_S390_DFLT;
-
- /*
- * Guarded storage support HWCAP_S390_GS is bit 12.
- */
- if (MACHINE_HAS_GS)
- elf_hwcap |= HWCAP_S390_GS;
-
- get_cpu_id(&cpu_id);
- add_device_randomness(&cpu_id, sizeof(cpu_id));
- switch (cpu_id.machine) {
- case 0x2064:
- case 0x2066:
- default: /* Use "z900" as default for 64 bit kernels. */
- strcpy(elf_platform, "z900");
- break;
- case 0x2084:
- case 0x2086:
- strcpy(elf_platform, "z990");
- break;
- case 0x2094:
- case 0x2096:
- strcpy(elf_platform, "z9-109");
- break;
- case 0x2097:
- case 0x2098:
- strcpy(elf_platform, "z10");
- break;
- case 0x2817:
- case 0x2818:
- strcpy(elf_platform, "z196");
- break;
- case 0x2827:
- case 0x2828:
- strcpy(elf_platform, "zEC12");
- break;
- case 0x2964:
- case 0x2965:
- strcpy(elf_platform, "z13");
- break;
- case 0x3906:
- case 0x3907:
- strcpy(elf_platform, "z14");
- break;
- case 0x8561:
- case 0x8562:
- strcpy(elf_platform, "z15");
- break;
- }
-
- /*
- * Virtualization support HWCAP_INT_SIE is bit 0.
- */
- if (sclp.has_sief2)
- int_hwcap |= HWCAP_INT_SIE;
+ unsigned long amode31_addr, amode31_size;
+ long amode31_offset;
+ long *ptr;
+
+ /* Allocate a new AMODE31 capable memory region */
+ amode31_size = __eamode31 - __samode31;
+ pr_info("Relocating AMODE31 section of size 0x%08lx\n", amode31_size);
+ amode31_addr = (unsigned long)memblock_alloc_low(amode31_size, PAGE_SIZE);
+ if (!amode31_addr)
+ panic("Failed to allocate memory for AMODE31 section\n");
+ amode31_offset = amode31_addr - __samode31;
+
+ /* Move original AMODE31 section to the new one */
+ memmove((void *)amode31_addr, (void *)__samode31, amode31_size);
+ /* Zero out the old AMODE31 section to catch invalid accesses within it */
+ memset((void *)__samode31, 0, amode31_size);
+
+ /* Update all AMODE31 region references */
+ for (ptr = _start_amode31_refs; ptr != _end_amode31_refs; ptr++)
+ *ptr += amode31_offset;
+}
- return 0;
+/* This must be called after AMODE31 relocation */
+static void __init setup_cr(void)
+{
+ union ctlreg2 cr2;
+ union ctlreg5 cr5;
+ union ctlreg15 cr15;
+
+ __ctl_duct[1] = (unsigned long)__ctl_aste;
+ __ctl_duct[2] = (unsigned long)__ctl_aste;
+ __ctl_duct[4] = (unsigned long)__ctl_duald;
+
+ /* Update control registers CR2, CR5 and CR15 */
+ __ctl_store(cr2.val, 2, 2);
+ __ctl_store(cr5.val, 5, 5);
+ __ctl_store(cr15.val, 15, 15);
+ cr2.ducto = (unsigned long)__ctl_duct >> 6;
+ cr5.pasteo = (unsigned long)__ctl_duct >> 6;
+ cr15.lsea = (unsigned long)__ctl_linkage_stack >> 3;
+ __ctl_load(cr2.val, 2, 2);
+ __ctl_load(cr5.val, 5, 5);
+ __ctl_load(cr15.val, 15, 15);
}
-arch_initcall(setup_hwcaps);
/*
* Add system information as device randomness
free_mem_detect_info();
+ relocate_amode31_section();
+ setup_cr();
+
setup_uv();
setup_memory_end();
setup_memory();
131 common quotactl sys_quotactl sys_quotactl
132 common getpgid sys_getpgid sys_getpgid
133 common fchdir sys_fchdir sys_fchdir
-134 common bdflush sys_bdflush sys_bdflush
+134 common bdflush sys_ni_syscall sys_ni_syscall
135 common sysfs sys_sysfs sys_sysfs
136 common personality sys_s390_personality sys_s390_personality
137 common afs_syscall - -
444 common landlock_create_ruleset sys_landlock_create_ruleset sys_landlock_create_ruleset
445 common landlock_add_rule sys_landlock_add_rule sys_landlock_add_rule
446 common landlock_restrict_self sys_landlock_restrict_self sys_landlock_restrict_self
+ # 447 reserved for memfd_secret
+ 448 common process_mrelease sys_process_mrelease sys_process_mrelease
#include <linux/kprobes.h>
#include <linux/uaccess.h>
#include <linux/hugetlb.h>
+#include <linux/kfence.h>
#include <asm/asm-offsets.h>
#include <asm/diag.h>
#include <asm/gmap.h>
{
const struct exception_table_entry *fixup;
- fixup = search_extable(__start_dma_ex_table,
- __stop_dma_ex_table - __start_dma_ex_table,
+ fixup = search_extable(__start_amode31_ex_table,
+ __stop_amode31_ex_table - __start_amode31_ex_table,
addr);
if (!fixup)
fixup = search_exception_tables(addr);
unsigned long address;
unsigned int flags;
vm_fault_t fault;
+ bool is_write;
tsk = current;
/*
mm = tsk->mm;
trans_exc_code = regs->int_parm_long;
+ address = trans_exc_code & __FAIL_ADDR_MASK;
+ is_write = (trans_exc_code & store_indication) == 0x400;
/*
* Verify that the fault happened in user space, that
type = get_fault_type(regs);
switch (type) {
case KERNEL_FAULT:
+ if (kfence_handle_page_fault(address, is_write, regs))
+ return 0;
goto out;
case USER_FAULT:
case GMAP_FAULT:
break;
}
- address = trans_exc_code & __FAIL_ADDR_MASK;
perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
flags = FAULT_FLAG_DEFAULT;
if (user_mode(regs))
flags |= FAULT_FLAG_USER;
- if (access == VM_WRITE || (trans_exc_code & store_indication) == 0x400)
+ if (access == VM_WRITE || is_write)
flags |= FAULT_FLAG_WRITE;
mmap_read_lock(mm);
break;
case KERNEL_FAULT:
page = phys_to_page(addr);
- if (unlikely(!try_get_page(page)))
+ if (unlikely(!try_get_compound_head(page, 1)))
break;
rc = arch_make_page_accessible(page);
put_page(page);
131 common quotactl sys_quotactl
132 common getpgid sys_getpgid
133 common fchdir sys_fchdir
-134 common bdflush sys_bdflush
+134 common bdflush sys_ni_syscall
135 common sysfs sys_sysfs
136 common personality sys_personality
# 137 was afs_syscall
444 common landlock_create_ruleset sys_landlock_create_ruleset
445 common landlock_add_rule sys_landlock_add_rule
446 common landlock_restrict_self sys_landlock_restrict_self
+ # 447 reserved for memfd_secret
+ 448 common process_mrelease sys_process_mrelease
222 common delete_module sys_delete_module
223 common get_kernel_syms sys_ni_syscall
224 common getpgid sys_getpgid
-225 common bdflush sys_bdflush
+225 common bdflush sys_ni_syscall
226 common sysfs sys_sysfs
227 common afs_syscall sys_nis_syscall
228 common setfsuid sys_setfsuid16
444 common landlock_create_ruleset sys_landlock_create_ruleset
445 common landlock_add_rule sys_landlock_add_rule
446 common landlock_restrict_self sys_landlock_restrict_self
+ # 447 reserved for memfd_secret
+ 448 common process_mrelease sys_process_mrelease
131 i386 quotactl sys_quotactl
132 i386 getpgid sys_getpgid
133 i386 fchdir sys_fchdir
-134 i386 bdflush sys_bdflush
+134 i386 bdflush sys_ni_syscall
135 i386 sysfs sys_sysfs
136 i386 personality sys_personality
137 i386 afs_syscall
445 i386 landlock_add_rule sys_landlock_add_rule
446 i386 landlock_restrict_self sys_landlock_restrict_self
447 i386 memfd_secret sys_memfd_secret
+ 448 i386 process_mrelease sys_process_mrelease
# 205 was old nfsservctl
205 common nfsservctl sys_ni_syscall
206 common _sysctl sys_ni_syscall
-207 common bdflush sys_bdflush
+207 common bdflush sys_ni_syscall
208 common uname sys_newuname
209 common sysinfo sys_sysinfo
210 common init_module sys_init_module
444 common landlock_create_ruleset sys_landlock_create_ruleset
445 common landlock_add_rule sys_landlock_add_rule
446 common landlock_restrict_self sys_landlock_restrict_self
+ # 447 reserved for memfd_secret
+ 448 common process_mrelease sys_process_mrelease
static void bio_invalidate_vmalloc_pages(struct bio *bio)
{
- #ifdef ARCH_HAS_FLUSH_KERNEL_DCACHE_PAGE
+ #ifdef ARCH_IMPLEMENTS_FLUSH_KERNEL_VMAP_RANGE
if (bio->bi_private && !op_is_write(bio_op(bio))) {
unsigned long i, len = 0;
struct bvec_iter_all iter_all;
bio_for_each_segment_all(bvec, bio, iter_all) {
- memcpy(p, page_address(bvec->bv_page), bvec->bv_len);
+ memcpy_from_bvec(p, bvec);
p += bvec->bv_len;
}
u8 *cp = host->data->status;
unsigned long start = jiffies;
- while (1) {
+ do {
int status;
unsigned i;
return cp[i];
}
- if (time_is_before_jiffies(start + timeout))
- break;
-
- /* If we need long timeouts, we may release the CPU.
- * We use jiffies here because we want to have a relation
- * between elapsed time and the blocking of the scheduler.
- */
- if (time_is_before_jiffies(start + 1))
- schedule();
- }
+ /* If we need long timeouts, we may release the CPU */
+ cond_resched();
+ } while (time_is_after_jiffies(start + timeout));
return -ETIMEDOUT;
}
/* discard mappings */
if (direction == DMA_FROM_DEVICE)
- flush_kernel_dcache_page(sg_page(sg));
+ flush_dcache_page(sg_page(sg));
kunmap(sg_page(sg));
if (dma_dev)
dma_unmap_page(dma_dev, dma_addr, PAGE_SIZE, dir);
* We are doing an exec(). 'current' is the process
* doing the exec and bprm->mm is the new process's mm.
*/
+ mmap_read_lock(bprm->mm);
ret = get_user_pages_remote(bprm->mm, pos, 1, gup_flags,
&page, NULL, NULL);
+ mmap_read_unlock(bprm->mm);
if (ret <= 0)
return NULL;
}
if (kmapped_page) {
- flush_kernel_dcache_page(kmapped_page);
+ flush_dcache_page(kmapped_page);
kunmap(kmapped_page);
put_arg_page(kmapped_page);
}
ret = 0;
out:
if (kmapped_page) {
- flush_kernel_dcache_page(kmapped_page);
+ flush_dcache_page(kmapped_page);
kunmap(kmapped_page);
put_arg_page(kmapped_page);
}
kaddr = kmap_atomic(page);
flush_arg_page(bprm, pos & PAGE_MASK, page);
memcpy(kaddr + offset_in_page(pos), arg, bytes_to_copy);
- flush_kernel_dcache_page(page);
+ flush_dcache_page(page);
kunmap_atomic(kaddr);
put_arg_page(page);
}
const char __user *const __user *, envp,
int, flags)
{
- int lookup_flags = (flags & AT_EMPTY_PATH) ? LOOKUP_EMPTY : 0;
-
return do_execveat(fd,
- getname_flags(filename, lookup_flags, NULL),
+ getname_uflags(filename, flags),
argv, envp, flags);
}
const compat_uptr_t __user *, envp,
int, flags)
{
- int lookup_flags = (flags & AT_EMPTY_PATH) ? LOOKUP_EMPTY : 0;
-
return compat_do_execveat(fd,
- getname_flags(filename, lookup_flags, NULL),
+ getname_uflags(filename, flags),
argv, envp, flags);
}
#endif
pid_t f_getown(struct file *filp)
{
pid_t pid = 0;
- read_lock(&filp->f_owner.lock);
+
+ read_lock_irq(&filp->f_owner.lock);
rcu_read_lock();
if (pid_task(filp->f_owner.pid, filp->f_owner.pid_type)) {
pid = pid_vnr(filp->f_owner.pid);
pid = -pid;
}
rcu_read_unlock();
- read_unlock(&filp->f_owner.lock);
+ read_unlock_irq(&filp->f_owner.lock);
return pid;
}
struct f_owner_ex owner = {};
int ret = 0;
- read_lock(&filp->f_owner.lock);
+ read_lock_irq(&filp->f_owner.lock);
rcu_read_lock();
if (pid_task(filp->f_owner.pid, filp->f_owner.pid_type))
owner.pid = pid_vnr(filp->f_owner.pid);
ret = -EINVAL;
break;
}
- read_unlock(&filp->f_owner.lock);
+ read_unlock_irq(&filp->f_owner.lock);
if (!ret) {
ret = copy_to_user(owner_p, &owner, sizeof(owner));
uid_t src[2];
int err;
- read_lock(&filp->f_owner.lock);
+ read_lock_irq(&filp->f_owner.lock);
src[0] = from_kuid(user_ns, filp->f_owner.uid);
src[1] = from_kuid(user_ns, filp->f_owner.euid);
- read_unlock(&filp->f_owner.lock);
+ read_unlock_irq(&filp->f_owner.lock);
err = put_user(src[0], &dst[0]);
err |= put_user(src[1], &dst[1]);
{
while (fa) {
struct fown_struct *fown;
+ unsigned long flags;
if (fa->magic != FASYNC_MAGIC) {
printk(KERN_ERR "kill_fasync: bad magic number in "
"fasync_struct!\n");
return;
}
- read_lock(&fa->fa_lock);
+ read_lock_irqsave(&fa->fa_lock, flags);
if (fa->fa_file) {
fown = &fa->fa_file->f_owner;
/* Don't send SIGURG to processes which have not set a
if (!(sig == SIGURG && fown->signum == 0))
send_sigio(fown, fa->fa_fd, band);
}
- read_unlock(&fa->fa_lock);
+ read_unlock_irqrestore(&fa->fa_lock, flags);
fa = rcu_dereference(fa->fa_next);
}
}
__FMODE_EXEC | __FMODE_NONOTIFY));
fasync_cache = kmem_cache_create("fasync_cache",
- sizeof(struct fasync_struct), 0, SLAB_PANIC, NULL);
+ sizeof(struct fasync_struct), 0,
+ SLAB_PANIC | SLAB_ACCOUNT, NULL);
return 0;
}
inc_wb_stat(new_wb, WB_WRITEBACK);
}
+ if (mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK)) {
+ atomic_dec(&old_wb->writeback_inodes);
+ atomic_inc(&new_wb->writeback_inodes);
+ }
+
wb_get(new_wb);
/*
* cgroup_writeback_by_id - initiate cgroup writeback from bdi and memcg IDs
* @bdi_id: target bdi id
* @memcg_id: target memcg css id
- * @nr: number of pages to write, 0 for best-effort dirty flushing
* @reason: reason why some writeback work initiated
* @done: target wb_completion
*
* Initiate flush of the bdi_writeback identified by @bdi_id and @memcg_id
* with the specified parameters.
*/
- int cgroup_writeback_by_id(u64 bdi_id, int memcg_id, unsigned long nr,
+ int cgroup_writeback_by_id(u64 bdi_id, int memcg_id,
enum wb_reason reason, struct wb_completion *done)
{
struct backing_dev_info *bdi;
struct cgroup_subsys_state *memcg_css;
struct bdi_writeback *wb;
struct wb_writeback_work *work;
+ unsigned long dirty;
int ret;
/* lookup bdi and memcg */
}
/*
- * If @nr is zero, the caller is attempting to write out most of
+ * The caller is attempting to write out most of
* the currently dirty pages. Let's take the current dirty page
* count and inflate it by 25% which should be large enough to
* flush out most dirty pages while avoiding getting livelocked by
* concurrent dirtiers.
+ *
+ * BTW the memcg stats are flushed periodically and this is best-effort
+ * estimation, so some potential error is ok.
*/
- if (!nr) {
- unsigned long filepages, headroom, dirty, writeback;
-
- mem_cgroup_wb_stats(wb, &filepages, &headroom, &dirty,
- &writeback);
- nr = dirty * 10 / 8;
- }
+ dirty = memcg_page_state(mem_cgroup_from_css(memcg_css), NR_FILE_DIRTY);
+ dirty = dirty * 10 / 8;
/* issue the writeback work */
work = kzalloc(sizeof(*work), GFP_NOWAIT | __GFP_NOWARN);
if (work) {
- work->nr_pages = nr;
+ work->nr_pages = dirty;
work->sync_mode = WB_SYNC_NONE;
work->range_cyclic = 1;
work->reason = reason;
static long wb_writeback(struct bdi_writeback *wb,
struct wb_writeback_work *work)
{
- unsigned long wb_start = jiffies;
long nr_pages = work->nr_pages;
unsigned long dirtied_before = jiffies;
struct inode *inode;
progress = __writeback_inodes_wb(wb, work);
trace_writeback_written(wb, work);
- wb_update_bandwidth(wb, wb_start);
-
/*
* Did we write something? Try for more
*
}
EXPORT_SYMBOL(write_inode_now);
-/**
- * sync_inode - write an inode and its pages to disk.
- * @inode: the inode to sync
- * @wbc: controls the writeback mode
- *
- * sync_inode() will write an inode and its pages to disk. It will also
- * correctly update the inode on its superblock's dirty inode lists and will
- * update inode->i_state.
- *
- * The caller must have a ref on the inode.
- */
-int sync_inode(struct inode *inode, struct writeback_control *wbc)
-{
- return writeback_single_inode(inode, wbc);
-}
-EXPORT_SYMBOL(sync_inode);
-
/**
* sync_inode_metadata - write an inode to disk
* @inode: the inode to sync
.nr_to_write = 0, /* metadata-only */
};
- return sync_inode(inode, &wbc);
+ return writeback_single_inode(inode, &wbc);
}
EXPORT_SYMBOL(sync_inode_metadata);
mapping_set_gfp_mask(mapping, GFP_HIGHUSER_MOVABLE);
mapping->private_data = NULL;
mapping->writeback_index = 0;
+ __init_rwsem(&mapping->invalidate_lock, "mapping.invalidate_lock",
+ &sb->s_type->invalidate_lock_key);
inode->i_private = NULL;
inode->i_mapping = mapping;
INIT_HLIST_HEAD(&inode->i_dentry); /* buggered by rcu freeing */
return LRU_ROTATE;
}
- if (inode_has_buffers(inode) || inode->i_data.nrpages) {
+ if (inode_has_buffers(inode) || !mapping_empty(&inode->i_data)) {
__iget(inode);
spin_unlock(&inode->i_lock);
spin_unlock(lru_lock);
return error;
}
-#ifdef CONFIG_MANDATORY_FILE_LOCKING
-/**
- * locks_mandatory_locked - Check for an active lock
- * @file: the file to check
- *
- * Searches the inode's list of locks to find any POSIX locks which conflict.
- * This function is called from locks_verify_locked() only.
- */
-int locks_mandatory_locked(struct file *file)
-{
- int ret;
- struct inode *inode = locks_inode(file);
- struct file_lock_context *ctx;
- struct file_lock *fl;
-
- ctx = smp_load_acquire(&inode->i_flctx);
- if (!ctx || list_empty_careful(&ctx->flc_posix))
- return 0;
-
- /*
- * Search the lock list for this inode for any POSIX locks.
- */
- spin_lock(&ctx->flc_lock);
- ret = 0;
- list_for_each_entry(fl, &ctx->flc_posix, fl_list) {
- if (fl->fl_owner != current->files &&
- fl->fl_owner != file) {
- ret = -EAGAIN;
- break;
- }
- }
- spin_unlock(&ctx->flc_lock);
- return ret;
-}
-
-/**
- * locks_mandatory_area - Check for a conflicting lock
- * @inode: the file to check
- * @filp: how the file was opened (if it was)
- * @start: first byte in the file to check
- * @end: lastbyte in the file to check
- * @type: %F_WRLCK for a write lock, else %F_RDLCK
- *
- * Searches the inode's list of locks to find any POSIX locks which conflict.
- */
-int locks_mandatory_area(struct inode *inode, struct file *filp, loff_t start,
- loff_t end, unsigned char type)
-{
- struct file_lock fl;
- int error;
- bool sleep = false;
-
- locks_init_lock(&fl);
- fl.fl_pid = current->tgid;
- fl.fl_file = filp;
- fl.fl_flags = FL_POSIX | FL_ACCESS;
- if (filp && !(filp->f_flags & O_NONBLOCK))
- sleep = true;
- fl.fl_type = type;
- fl.fl_start = start;
- fl.fl_end = end;
-
- for (;;) {
- if (filp) {
- fl.fl_owner = filp;
- fl.fl_flags &= ~FL_SLEEP;
- error = posix_lock_inode(inode, &fl, NULL);
- if (!error)
- break;
- }
-
- if (sleep)
- fl.fl_flags |= FL_SLEEP;
- fl.fl_owner = current->files;
- error = posix_lock_inode(inode, &fl, NULL);
- if (error != FILE_LOCK_DEFERRED)
- break;
- error = wait_event_interruptible(fl.fl_wait,
- list_empty(&fl.fl_blocked_member));
- if (!error) {
- /*
- * If we've been sleeping someone might have
- * changed the permissions behind our back.
- */
- if (__mandatory_lock(inode))
- continue;
- }
-
- break;
- }
- locks_delete_block(&fl);
-
- return error;
-}
-EXPORT_SYMBOL(locks_mandatory_area);
-#endif /* CONFIG_MANDATORY_FILE_LOCKING */
-
static void lease_clear_pending(struct file_lock *fl, int arg)
{
switch (arg) {
if (file_lock == NULL)
return -ENOLCK;
- /* Don't allow mandatory locks on files that may be memory mapped
- * and shared.
- */
- if (mandatory_lock(inode) && mapping_writably_mapped(filp->f_mapping)) {
- error = -EAGAIN;
- goto out;
- }
-
error = flock_to_posix_lock(filp, file_lock, flock);
if (error)
goto out;
struct flock64 *flock)
{
struct file_lock *file_lock = locks_alloc_lock();
- struct inode *inode = locks_inode(filp);
struct file *f;
int error;
if (file_lock == NULL)
return -ENOLCK;
- /* Don't allow mandatory locks on files that may be memory mapped
- * and shared.
- */
- if (mandatory_lock(inode) && mapping_writably_mapped(filp->f_mapping)) {
- error = -EAGAIN;
- goto out;
- }
-
error = flock64_to_posix_lock(filp, file_lock, flock);
if (error)
goto out;
seq_puts(f, "POSIX ");
seq_printf(f, " %s ",
- (inode == NULL) ? "*NOINODE*" :
- mandatory_lock(inode) ? "MANDATORY" : "ADVISORY ");
+ (inode == NULL) ? "*NOINODE*" : "ADVISORY ");
} else if (IS_FLOCK(fl)) {
if (fl->fl_type & LOCK_MAND) {
seq_puts(f, "FLOCK MSNFS ");
int i;
flctx_cache = kmem_cache_create("file_lock_ctx",
- sizeof(struct file_lock_context), 0, SLAB_PANIC, NULL);
+ sizeof(struct file_lock_context), 0,
+ SLAB_PANIC | SLAB_ACCOUNT, NULL);
filelock_cache = kmem_cache_create("file_lock_cache",
- sizeof(struct file_lock), 0, SLAB_PANIC, NULL);
+ sizeof(struct file_lock), 0,
+ SLAB_PANIC | SLAB_ACCOUNT, NULL);
for_each_possible_cpu(i) {
struct file_lock_list_struct *fll = per_cpu_ptr(&file_lock_list, i);
return result;
}
+struct filename *
+getname_uflags(const char __user *filename, int uflags)
+{
+ int flags = (uflags & AT_EMPTY_PATH) ? LOOKUP_EMPTY : 0;
+
+ return getname_flags(filename, flags, NULL);
+}
+
struct filename *
getname(const char __user * filename)
{
void putname(struct filename *name)
{
+ if (IS_ERR_OR_NULL(name))
+ return;
+
BUG_ON(name->refcnt <= 0);
if (--name->refcnt > 0)
return err;
}
-int filename_lookup(int dfd, struct filename *name, unsigned flags,
+static int __filename_lookup(int dfd, struct filename *name, unsigned flags,
struct path *path, struct path *root)
{
int retval;
audit_inode(name, path->dentry,
flags & LOOKUP_MOUNTPOINT ? AUDIT_INODE_NOEVAL : 0);
restore_nameidata();
+ return retval;
+}
+
+int filename_lookup(int dfd, struct filename *name, unsigned flags,
+ struct path *path, struct path *root)
+{
+ int retval = __filename_lookup(dfd, name, flags, path, root);
+
putname(name);
return retval;
}
return err;
}
-static struct filename *filename_parentat(int dfd, struct filename *name,
+static int __filename_parentat(int dfd, struct filename *name,
unsigned int flags, struct path *parent,
struct qstr *last, int *type)
{
struct nameidata nd;
if (IS_ERR(name))
- return name;
+ return PTR_ERR(name);
set_nameidata(&nd, dfd, name, NULL);
retval = path_parentat(&nd, flags | LOOKUP_RCU, parent);
if (unlikely(retval == -ECHILD))
*last = nd.last;
*type = nd.last_type;
audit_inode(name, parent->dentry, AUDIT_INODE_PARENT);
- } else {
- putname(name);
- name = ERR_PTR(retval);
}
restore_nameidata();
- return name;
+ return retval;
+}
+
+static int filename_parentat(int dfd, struct filename *name,
+ unsigned int flags, struct path *parent,
+ struct qstr *last, int *type)
+{
+ int retval = __filename_parentat(dfd, name, flags, parent, last, type);
+
+ putname(name);
+ return retval;
}
/* does lookup, returns the object with parent locked */
struct dentry *kern_path_locked(const char *name, struct path *path)
{
- struct filename *filename;
struct dentry *d;
struct qstr last;
- int type;
+ int type, error;
- filename = filename_parentat(AT_FDCWD, getname_kernel(name), 0, path,
+ error = filename_parentat(AT_FDCWD, getname_kernel(name), 0, path,
&last, &type);
- if (IS_ERR(filename))
- return ERR_CAST(filename);
+ if (error)
+ return ERR_PTR(error);
if (unlikely(type != LAST_NORM)) {
path_put(path);
- putname(filename);
return ERR_PTR(-EINVAL);
}
inode_lock_nested(path->dentry->d_inode, I_MUTEX_PARENT);
inode_unlock(path->dentry->d_inode);
path_put(path);
}
- putname(filename);
return d;
}
}
EXPORT_SYMBOL(vfs_path_lookup);
-static int lookup_one_len_common(const char *name, struct dentry *base,
- int len, struct qstr *this)
+static int lookup_one_common(struct user_namespace *mnt_userns,
+ const char *name, struct dentry *base, int len,
+ struct qstr *this)
{
this->name = name;
this->len = len;
return err;
}
- return inode_permission(&init_user_ns, base->d_inode, MAY_EXEC);
+ return inode_permission(mnt_userns, base->d_inode, MAY_EXEC);
}
/**
WARN_ON_ONCE(!inode_is_locked(base->d_inode));
- err = lookup_one_len_common(name, base, len, &this);
+ err = lookup_one_common(&init_user_ns, name, base, len, &this);
if (err)
return ERR_PTR(err);
WARN_ON_ONCE(!inode_is_locked(base->d_inode));
- err = lookup_one_len_common(name, base, len, &this);
+ err = lookup_one_common(&init_user_ns, name, base, len, &this);
if (err)
return ERR_PTR(err);
}
EXPORT_SYMBOL(lookup_one_len);
+/**
+ * lookup_one - filesystem helper to lookup single pathname component
+ * @mnt_userns: user namespace of the mount the lookup is performed from
+ * @name: pathname component to lookup
+ * @base: base directory to lookup from
+ * @len: maximum length @len should be interpreted to
+ *
+ * Note that this routine is purely a helper for filesystem usage and should
+ * not be called by generic code.
+ *
+ * The caller must hold base->i_mutex.
+ */
+struct dentry *lookup_one(struct user_namespace *mnt_userns, const char *name,
+ struct dentry *base, int len)
+{
+ struct dentry *dentry;
+ struct qstr this;
+ int err;
+
+ WARN_ON_ONCE(!inode_is_locked(base->d_inode));
+
+ err = lookup_one_common(mnt_userns, name, base, len, &this);
+ if (err)
+ return ERR_PTR(err);
+
+ dentry = lookup_dcache(&this, base, 0);
+ return dentry ? dentry : __lookup_slow(&this, base, 0);
+}
+EXPORT_SYMBOL(lookup_one);
+
/**
* lookup_one_len_unlocked - filesystem helper to lookup single pathname component
* @name: pathname component to lookup
int err;
struct dentry *ret;
- err = lookup_one_len_common(name, base, len, &this);
+ err = lookup_one_common(&init_user_ns, name, base, len, &this);
if (err)
return ERR_PTR(err);
/*
* Refuse to truncate files with mandatory locks held on them.
*/
- error = locks_verify_locked(filp);
- if (!error)
- error = security_path_truncate(path);
+ error = security_path_truncate(path);
if (!error) {
error = do_truncate(mnt_userns, path->dentry, 0,
ATTR_MTIME|ATTR_CTIME|ATTR_OPEN,
return file;
}
-static struct dentry *filename_create(int dfd, struct filename *name,
+static struct dentry *__filename_create(int dfd, struct filename *name,
struct path *path, unsigned int lookup_flags)
{
struct dentry *dentry = ERR_PTR(-EEXIST);
*/
lookup_flags &= LOOKUP_REVAL;
- name = filename_parentat(dfd, name, lookup_flags, path, &last, &type);
- if (IS_ERR(name))
- return ERR_CAST(name);
+ error = __filename_parentat(dfd, name, lookup_flags, path, &last, &type);
+ if (error)
+ return ERR_PTR(error);
/*
* Yucky last component or no last component at all?
error = err2;
goto fail;
}
- putname(name);
return dentry;
fail:
dput(dentry);
mnt_drop_write(path->mnt);
out:
path_put(path);
- putname(name);
return dentry;
}
+static inline struct dentry *filename_create(int dfd, struct filename *name,
+ struct path *path, unsigned int lookup_flags)
+{
+ struct dentry *res = __filename_create(dfd, name, path, lookup_flags);
+
+ putname(name);
+ return res;
+}
+
struct dentry *kern_path_create(int dfd, const char *pathname,
struct path *path, unsigned int lookup_flags)
{
}
}
-static long do_mknodat(int dfd, const char __user *filename, umode_t mode,
+static int do_mknodat(int dfd, struct filename *name, umode_t mode,
unsigned int dev)
{
struct user_namespace *mnt_userns;
error = may_mknod(mode);
if (error)
- return error;
+ goto out1;
retry:
- dentry = user_path_create(dfd, filename, &path, lookup_flags);
+ dentry = __filename_create(dfd, name, &path, lookup_flags);
+ error = PTR_ERR(dentry);
if (IS_ERR(dentry))
- return PTR_ERR(dentry);
+ goto out1;
if (!IS_POSIXACL(path.dentry->d_inode))
mode &= ~current_umask();
error = security_path_mknod(&path, dentry, mode, dev);
if (error)
- goto out;
+ goto out2;
mnt_userns = mnt_user_ns(path.mnt);
switch (mode & S_IFMT) {
dentry, mode, 0);
break;
}
-out:
+out2:
done_path_create(&path, dentry);
if (retry_estale(error, lookup_flags)) {
lookup_flags |= LOOKUP_REVAL;
goto retry;
}
+out1:
+ putname(name);
return error;
}
SYSCALL_DEFINE4(mknodat, int, dfd, const char __user *, filename, umode_t, mode,
unsigned int, dev)
{
- return do_mknodat(dfd, filename, mode, dev);
+ return do_mknodat(dfd, getname(filename), mode, dev);
}
SYSCALL_DEFINE3(mknod, const char __user *, filename, umode_t, mode, unsigned, dev)
{
- return do_mknodat(AT_FDCWD, filename, mode, dev);
+ return do_mknodat(AT_FDCWD, getname(filename), mode, dev);
}
/**
}
EXPORT_SYMBOL(vfs_mkdir);
-static long do_mkdirat(int dfd, const char __user *pathname, umode_t mode)
+int do_mkdirat(int dfd, struct filename *name, umode_t mode)
{
struct dentry *dentry;
struct path path;
unsigned int lookup_flags = LOOKUP_DIRECTORY;
retry:
- dentry = user_path_create(dfd, pathname, &path, lookup_flags);
+ dentry = __filename_create(dfd, name, &path, lookup_flags);
+ error = PTR_ERR(dentry);
if (IS_ERR(dentry))
- return PTR_ERR(dentry);
+ goto out_putname;
if (!IS_POSIXACL(path.dentry->d_inode))
mode &= ~current_umask();
lookup_flags |= LOOKUP_REVAL;
goto retry;
}
+out_putname:
+ putname(name);
return error;
}
SYSCALL_DEFINE3(mkdirat, int, dfd, const char __user *, pathname, umode_t, mode)
{
- return do_mkdirat(dfd, pathname, mode);
+ return do_mkdirat(dfd, getname(pathname), mode);
}
SYSCALL_DEFINE2(mkdir, const char __user *, pathname, umode_t, mode)
{
- return do_mkdirat(AT_FDCWD, pathname, mode);
+ return do_mkdirat(AT_FDCWD, getname(pathname), mode);
}
/**
}
EXPORT_SYMBOL(vfs_rmdir);
-long do_rmdir(int dfd, struct filename *name)
+int do_rmdir(int dfd, struct filename *name)
{
struct user_namespace *mnt_userns;
- int error = 0;
+ int error;
struct dentry *dentry;
struct path path;
struct qstr last;
int type;
unsigned int lookup_flags = 0;
retry:
- name = filename_parentat(dfd, name, lookup_flags,
- &path, &last, &type);
- if (IS_ERR(name))
- return PTR_ERR(name);
+ error = __filename_parentat(dfd, name, lookup_flags, &path, &last, &type);
+ if (error)
+ goto exit1;
switch (type) {
case LAST_DOTDOT:
error = -ENOTEMPTY;
- goto exit1;
+ goto exit2;
case LAST_DOT:
error = -EINVAL;
- goto exit1;
+ goto exit2;
case LAST_ROOT:
error = -EBUSY;
- goto exit1;
+ goto exit2;
}
error = mnt_want_write(path.mnt);
if (error)
- goto exit1;
+ goto exit2;
inode_lock_nested(path.dentry->d_inode, I_MUTEX_PARENT);
dentry = __lookup_hash(&last, path.dentry, lookup_flags);
error = PTR_ERR(dentry);
if (IS_ERR(dentry))
- goto exit2;
+ goto exit3;
if (!dentry->d_inode) {
error = -ENOENT;
- goto exit3;
+ goto exit4;
}
error = security_path_rmdir(&path, dentry);
if (error)
- goto exit3;
+ goto exit4;
mnt_userns = mnt_user_ns(path.mnt);
error = vfs_rmdir(mnt_userns, path.dentry->d_inode, dentry);
-exit3:
+exit4:
dput(dentry);
-exit2:
+exit3:
inode_unlock(path.dentry->d_inode);
mnt_drop_write(path.mnt);
-exit1:
+exit2:
path_put(&path);
if (retry_estale(error, lookup_flags)) {
lookup_flags |= LOOKUP_REVAL;
goto retry;
}
+exit1:
putname(name);
return error;
}
return -EPERM;
inode_lock(target);
- if (is_local_mountpoint(dentry))
+ if (IS_SWAPFILE(target))
+ error = -EPERM;
+ else if (is_local_mountpoint(dentry))
error = -EBUSY;
else {
error = security_inode_unlink(dir, dentry);
* writeout happening, and we don't want to prevent access to the directory
* while waiting on the I/O.
*/
-long do_unlinkat(int dfd, struct filename *name)
+int do_unlinkat(int dfd, struct filename *name)
{
int error;
struct dentry *dentry;
struct inode *delegated_inode = NULL;
unsigned int lookup_flags = 0;
retry:
- name = filename_parentat(dfd, name, lookup_flags, &path, &last, &type);
- if (IS_ERR(name))
- return PTR_ERR(name);
+ error = __filename_parentat(dfd, name, lookup_flags, &path, &last, &type);
+ if (error)
+ goto exit1;
error = -EISDIR;
if (type != LAST_NORM)
- goto exit1;
+ goto exit2;
error = mnt_want_write(path.mnt);
if (error)
- goto exit1;
+ goto exit2;
retry_deleg:
inode_lock_nested(path.dentry->d_inode, I_MUTEX_PARENT);
dentry = __lookup_hash(&last, path.dentry, lookup_flags);
ihold(inode);
error = security_path_unlink(&path, dentry);
if (error)
- goto exit2;
+ goto exit3;
mnt_userns = mnt_user_ns(path.mnt);
error = vfs_unlink(mnt_userns, path.dentry->d_inode, dentry,
&delegated_inode);
-exit2:
+exit3:
dput(dentry);
}
inode_unlock(path.dentry->d_inode);
goto retry_deleg;
}
mnt_drop_write(path.mnt);
-exit1:
+exit2:
path_put(&path);
if (retry_estale(error, lookup_flags)) {
lookup_flags |= LOOKUP_REVAL;
inode = NULL;
goto retry;
}
+exit1:
putname(name);
return error;
error = -EISDIR;
else
error = -ENOTDIR;
- goto exit2;
+ goto exit3;
}
SYSCALL_DEFINE3(unlinkat, int, dfd, const char __user *, pathname, int, flag)
}
EXPORT_SYMBOL(vfs_symlink);
-static long do_symlinkat(const char __user *oldname, int newdfd,
- const char __user *newname)
+int do_symlinkat(struct filename *from, int newdfd, struct filename *to)
{
int error;
- struct filename *from;
struct dentry *dentry;
struct path path;
unsigned int lookup_flags = 0;
- from = getname(oldname);
- if (IS_ERR(from))
- return PTR_ERR(from);
+ if (IS_ERR(from)) {
+ error = PTR_ERR(from);
+ goto out_putnames;
+ }
retry:
- dentry = user_path_create(newdfd, newname, &path, lookup_flags);
+ dentry = __filename_create(newdfd, to, &path, lookup_flags);
error = PTR_ERR(dentry);
if (IS_ERR(dentry))
- goto out_putname;
+ goto out_putnames;
error = security_path_symlink(&path, dentry, from->name);
if (!error) {
lookup_flags |= LOOKUP_REVAL;
goto retry;
}
-out_putname:
+out_putnames:
+ putname(to);
putname(from);
return error;
}
SYSCALL_DEFINE3(symlinkat, const char __user *, oldname,
int, newdfd, const char __user *, newname)
{
- return do_symlinkat(oldname, newdfd, newname);
+ return do_symlinkat(getname(oldname), newdfd, getname(newname));
}
SYSCALL_DEFINE2(symlink, const char __user *, oldname, const char __user *, newname)
{
- return do_symlinkat(oldname, AT_FDCWD, newname);
+ return do_symlinkat(getname(oldname), AT_FDCWD, getname(newname));
}
/**
* with linux 2.0, and to avoid hard-linking to directories
* and other special files. --ADM
*/
-static int do_linkat(int olddfd, const char __user *oldname, int newdfd,
- const char __user *newname, int flags)
+int do_linkat(int olddfd, struct filename *old, int newdfd,
+ struct filename *new, int flags)
{
struct user_namespace *mnt_userns;
struct dentry *new_dentry;
int how = 0;
int error;
- if ((flags & ~(AT_SYMLINK_FOLLOW | AT_EMPTY_PATH)) != 0)
- return -EINVAL;
+ if ((flags & ~(AT_SYMLINK_FOLLOW | AT_EMPTY_PATH)) != 0) {
+ error = -EINVAL;
+ goto out_putnames;
+ }
/*
* To use null names we require CAP_DAC_READ_SEARCH
* This ensures that not everyone will be able to create
* handlink using the passed filedescriptor.
*/
- if (flags & AT_EMPTY_PATH) {
- if (!capable(CAP_DAC_READ_SEARCH))
- return -ENOENT;
- how = LOOKUP_EMPTY;
+ if (flags & AT_EMPTY_PATH && !capable(CAP_DAC_READ_SEARCH)) {
+ error = -ENOENT;
+ goto out_putnames;
}
if (flags & AT_SYMLINK_FOLLOW)
how |= LOOKUP_FOLLOW;
retry:
- error = user_path_at(olddfd, oldname, how, &old_path);
+ error = __filename_lookup(olddfd, old, how, &old_path, NULL);
if (error)
- return error;
+ goto out_putnames;
- new_dentry = user_path_create(newdfd, newname, &new_path,
+ new_dentry = __filename_create(newdfd, new, &new_path,
(how & LOOKUP_REVAL));
error = PTR_ERR(new_dentry);
if (IS_ERR(new_dentry))
- goto out;
+ goto out_putpath;
error = -EXDEV;
if (old_path.mnt != new_path.mnt)
how |= LOOKUP_REVAL;
goto retry;
}
-out:
+out_putpath:
path_put(&old_path);
+out_putnames:
+ putname(old);
+ putname(new);
return error;
}
SYSCALL_DEFINE5(linkat, int, olddfd, const char __user *, oldname,
int, newdfd, const char __user *, newname, int, flags)
{
- return do_linkat(olddfd, oldname, newdfd, newname, flags);
+ return do_linkat(olddfd, getname_uflags(oldname, flags),
+ newdfd, getname(newname), flags);
}
SYSCALL_DEFINE2(link, const char __user *, oldname, const char __user *, newname)
{
- return do_linkat(AT_FDCWD, oldname, AT_FDCWD, newname, 0);
+ return do_linkat(AT_FDCWD, getname(oldname), AT_FDCWD, getname(newname), 0);
}
/**
else if (target)
inode_lock(target);
+ error = -EPERM;
+ if (IS_SWAPFILE(source) || (target && IS_SWAPFILE(target)))
+ goto out;
+
error = -EBUSY;
if (is_local_mountpoint(old_dentry) || is_local_mountpoint(new_dentry))
goto out;
int error = -EINVAL;
if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE | RENAME_WHITEOUT))
- goto put_both;
+ goto put_names;
if ((flags & (RENAME_NOREPLACE | RENAME_WHITEOUT)) &&
(flags & RENAME_EXCHANGE))
- goto put_both;
+ goto put_names;
if (flags & RENAME_EXCHANGE)
target_flags = 0;
retry:
- from = filename_parentat(olddfd, from, lookup_flags, &old_path,
+ error = __filename_parentat(olddfd, from, lookup_flags, &old_path,
&old_last, &old_type);
- if (IS_ERR(from)) {
- error = PTR_ERR(from);
- goto put_new;
- }
+ if (error)
+ goto put_names;
- to = filename_parentat(newdfd, to, lookup_flags, &new_path, &new_last,
+ error = __filename_parentat(newdfd, to, lookup_flags, &new_path, &new_last,
&new_type);
- if (IS_ERR(to)) {
- error = PTR_ERR(to);
+ if (error)
goto exit1;
- }
error = -EXDEV;
if (old_path.mnt != new_path.mnt)
lookup_flags |= LOOKUP_REVAL;
goto retry;
}
-put_both:
- if (!IS_ERR(from))
- putname(from);
-put_new:
- if (!IS_ERR(to))
- putname(to);
+put_names:
+ putname(from);
+ putname(to);
return error;
}
goto out_free_cache;
if (name) {
- mnt->mnt_devname = kstrdup_const(name, GFP_KERNEL);
+ mnt->mnt_devname = kstrdup_const(name,
+ GFP_KERNEL_ACCOUNT);
if (!mnt->mnt_devname)
goto out_free_id;
}
return ns_capable(current->nsproxy->mnt_ns->user_ns, CAP_SYS_ADMIN);
}
-#ifdef CONFIG_MANDATORY_FILE_LOCKING
-static bool may_mandlock(void)
+static void warn_mandlock(void)
{
- pr_warn_once("======================================================\n"
- "WARNING: the mand mount option is being deprecated and\n"
- " will be removed in v5.15!\n"
- "======================================================\n");
- return capable(CAP_SYS_ADMIN);
+ pr_warn_once("=======================================================\n"
+ "WARNING: The mand mount option has been deprecated and\n"
+ " and is ignored by this kernel. Remove the mand\n"
+ " option from the mount to silence this warning.\n"
+ "=======================================================\n");
}
-#else
-static inline bool may_mandlock(void)
-{
- pr_warn("VFS: \"mand\" mount option not supported");
- return false;
-}
-#endif
static int can_umount(const struct path *path, int flags)
{
return ret;
}
+static int do_set_group(struct path *from_path, struct path *to_path)
+{
+ struct mount *from, *to;
+ int err;
+
+ from = real_mount(from_path->mnt);
+ to = real_mount(to_path->mnt);
+
+ namespace_lock();
+
+ err = -EINVAL;
+ /* To and From must be mounted */
+ if (!is_mounted(&from->mnt))
+ goto out;
+ if (!is_mounted(&to->mnt))
+ goto out;
+
+ err = -EPERM;
+ /* We should be allowed to modify mount namespaces of both mounts */
+ if (!ns_capable(from->mnt_ns->user_ns, CAP_SYS_ADMIN))
+ goto out;
+ if (!ns_capable(to->mnt_ns->user_ns, CAP_SYS_ADMIN))
+ goto out;
+
+ err = -EINVAL;
+ /* To and From paths should be mount roots */
+ if (from_path->dentry != from_path->mnt->mnt_root)
+ goto out;
+ if (to_path->dentry != to_path->mnt->mnt_root)
+ goto out;
+
+ /* Setting sharing groups is only allowed across same superblock */
+ if (from->mnt.mnt_sb != to->mnt.mnt_sb)
+ goto out;
+
+ /* From mount root should be wider than To mount root */
+ if (!is_subdir(to->mnt.mnt_root, from->mnt.mnt_root))
+ goto out;
+
+ /* From mount should not have locked children in place of To's root */
+ if (has_locked_children(from, to->mnt.mnt_root))
+ goto out;
+
+ /* Setting sharing groups is only allowed on private mounts */
+ if (IS_MNT_SHARED(to) || IS_MNT_SLAVE(to))
+ goto out;
+
+ /* From should not be private */
+ if (!IS_MNT_SHARED(from) && !IS_MNT_SLAVE(from))
+ goto out;
+
+ if (IS_MNT_SLAVE(from)) {
+ struct mount *m = from->mnt_master;
+
+ list_add(&to->mnt_slave, &m->mnt_slave_list);
+ to->mnt_master = m;
+ }
+
+ if (IS_MNT_SHARED(from)) {
+ to->mnt_group_id = from->mnt_group_id;
+ list_add(&to->mnt_share, &from->mnt_share);
+ lock_mount_hash();
+ set_mnt_shared(to);
+ unlock_mount_hash();
+ }
+
+ err = 0;
+out:
+ namespace_unlock();
+ return err;
+}
+
static int do_move_mount(struct path *old_path, struct path *new_path)
{
struct mnt_namespace *ns;
return ret;
if (!may_mount())
return -EPERM;
- if ((flags & SB_MANDLOCK) && !may_mandlock())
- return -EPERM;
+ if (flags & SB_MANDLOCK)
+ warn_mandlock();
/* Default to relatime unless overriden */
if (!(flags & MS_NOATIME))
if (!ucounts)
return ERR_PTR(-ENOSPC);
- new_ns = kzalloc(sizeof(struct mnt_namespace), GFP_KERNEL);
+ new_ns = kzalloc(sizeof(struct mnt_namespace), GFP_KERNEL_ACCOUNT);
if (!new_ns) {
dec_mnt_namespaces(ucounts);
return ERR_PTR(-ENOMEM);
if (fc->phase != FS_CONTEXT_AWAITING_MOUNT)
goto err_unlock;
- ret = -EPERM;
- if ((fc->sb_flags & SB_MANDLOCK) && !may_mandlock())
- goto err_unlock;
+ if (fc->sb_flags & SB_MANDLOCK)
+ warn_mandlock();
newmount.mnt = vfs_create_mount(fc);
if (IS_ERR(newmount.mnt)) {
if (ret < 0)
goto out_to;
- ret = do_move_mount(&from_path, &to_path);
+ if (flags & MOVE_MOUNT_SET_GROUP)
+ ret = do_set_group(&from_path, &to_path);
+ else
+ ret = do_move_mount(&from_path, &to_path);
out_to:
path_put(&to_path);
int err;
mnt_cache = kmem_cache_create("mnt_cache", sizeof(struct mount),
- 0, SLAB_HWCACHE_ALIGN | SLAB_PANIC, NULL);
+ 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT, NULL);
mount_hashtable = alloc_large_system_hash("Mount-cache",
sizeof(struct hlist_head),
sb = inode->i_sb;
#ifdef CONFIG_BLOCK
if (sb_is_blkdev_sb(sb))
- return I_BDEV(inode)->bd_bdi;
+ return I_BDEV(inode)->bd_disk->bdi;
#endif
return sb->s_bdi;
}
return inode->i_wb;
}
+ static inline struct bdi_writeback *inode_to_wb_wbc(
+ struct inode *inode,
+ struct writeback_control *wbc)
+ {
+ /*
+ * If wbc does not have inode attached, it means cgroup writeback was
+ * disabled when wbc started. Just use the default wb in that case.
+ */
+ return wbc->wb ? wbc->wb : &inode_to_bdi(inode)->wb;
+ }
+
/**
* unlocked_inode_to_wb_begin - begin unlocked inode wb access transaction
* @inode: target inode
return &inode_to_bdi(inode)->wb;
}
+ static inline struct bdi_writeback *inode_to_wb_wbc(
+ struct inode *inode,
+ struct writeback_control *wbc)
+ {
+ return inode_to_wb(inode);
+ }
+
+
static inline struct bdi_writeback *
unlocked_inode_to_wb_begin(struct inode *inode, struct wb_lock_cookie *cookie)
{
unsigned int generation;
};
- struct lruvec_stat {
- long count[NR_VM_NODE_STAT_ITEMS];
- };
-
- struct batched_lruvec_stat {
- s32 count[NR_VM_NODE_STAT_ITEMS];
- };
-
/*
* Bitmap and deferred work of shrinker::id corresponding to memcg-aware
* shrinkers, which have elements charged to this memcg.
unsigned long *map;
};
+ struct lruvec_stats_percpu {
+ /* Local (CPU and cgroup) state */
+ long state[NR_VM_NODE_STAT_ITEMS];
+
+ /* Delta calculation for lockless upward propagation */
+ long state_prev[NR_VM_NODE_STAT_ITEMS];
+ };
+
+ struct lruvec_stats {
+ /* Aggregated (CPU and subtree) state */
+ long state[NR_VM_NODE_STAT_ITEMS];
+
+ /* Pending child counts during tree propagation */
+ long state_pending[NR_VM_NODE_STAT_ITEMS];
+ };
+
/*
* per-node information in memory controller.
*/
struct mem_cgroup_per_node {
struct lruvec lruvec;
- /*
- * Legacy local VM stats. This should be struct lruvec_stat and
- * cannot be optimized to struct batched_lruvec_stat. Because
- * the threshold of the lruvec_stat_cpu can be as big as
- * MEMCG_CHARGE_BATCH * PAGE_SIZE. It can fit into s32. But this
- * filed has no upper limit.
- */
- struct lruvec_stat __percpu *lruvec_stat_local;
-
- /* Subtree VM stats (batched updates) */
- struct batched_lruvec_stat __percpu *lruvec_stat_cpu;
- atomic_long_t lruvec_stat[NR_VM_NODE_STAT_ITEMS];
+ struct lruvec_stats_percpu __percpu *lruvec_stats_percpu;
+ struct lruvec_stats lruvec_stats;
unsigned long lru_zone_size[MAX_NR_ZONES][NR_LRU_LISTS];
}
#endif
- static __always_inline bool memcg_stat_item_in_bytes(int idx)
- {
- if (idx == MEMCG_PERCPU_B)
- return true;
- return vmstat_item_in_bytes(idx);
- }
-
static inline bool mem_cgroup_is_root(struct mem_cgroup *memcg)
{
return (memcg == root_mem_cgroup);
page_counter_read(&memcg->memory);
}
- int mem_cgroup_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask);
+ int __mem_cgroup_charge(struct page *page, struct mm_struct *mm,
+ gfp_t gfp_mask);
+ static inline int mem_cgroup_charge(struct page *page, struct mm_struct *mm,
+ gfp_t gfp_mask)
+ {
+ if (mem_cgroup_disabled())
+ return 0;
+ return __mem_cgroup_charge(page, mm, gfp_mask);
+ }
+
int mem_cgroup_swapin_charge_page(struct page *page, struct mm_struct *mm,
gfp_t gfp, swp_entry_t entry);
void mem_cgroup_swapin_uncharge_swap(swp_entry_t entry);
- void mem_cgroup_uncharge(struct page *page);
- void mem_cgroup_uncharge_list(struct list_head *page_list);
+ void __mem_cgroup_uncharge(struct page *page);
+ static inline void mem_cgroup_uncharge(struct page *page)
+ {
+ if (mem_cgroup_disabled())
+ return;
+ __mem_cgroup_uncharge(page);
+ }
+
+ void __mem_cgroup_uncharge_list(struct list_head *page_list);
+ static inline void mem_cgroup_uncharge_list(struct list_head *page_list)
+ {
+ if (mem_cgroup_disabled())
+ return;
+ __mem_cgroup_uncharge_list(page_list);
+ }
void mem_cgroup_migrate(struct page *oldpage, struct page *newpage);
return !!(memcg->css.flags & CSS_ONLINE);
}
- /*
- * For memory reclaim.
- */
- int mem_cgroup_select_victim_node(struct mem_cgroup *memcg);
-
void mem_cgroup_update_lru_size(struct lruvec *lruvec, enum lru_list lru,
int zid, int nr_pages);
local_irq_restore(flags);
}
+ static inline unsigned long memcg_page_state(struct mem_cgroup *memcg, int idx)
+ {
+ return READ_ONCE(memcg->vmstats.state[idx]);
+ }
+
static inline unsigned long lruvec_page_state(struct lruvec *lruvec,
enum node_stat_item idx)
{
struct mem_cgroup_per_node *pn;
- long x;
if (mem_cgroup_disabled())
return node_page_state(lruvec_pgdat(lruvec), idx);
pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
- x = atomic_long_read(&pn->lruvec_stat[idx]);
- #ifdef CONFIG_SMP
- if (x < 0)
- x = 0;
- #endif
- return x;
+ return READ_ONCE(pn->lruvec_stats.state[idx]);
}
static inline unsigned long lruvec_page_state_local(struct lruvec *lruvec,
pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
for_each_possible_cpu(cpu)
- x += per_cpu(pn->lruvec_stat_local->count[idx], cpu);
+ x += per_cpu(pn->lruvec_stats_percpu->state[idx], cpu);
#ifdef CONFIG_SMP
if (x < 0)
x = 0;
return x;
}
+ void mem_cgroup_flush_stats(void);
+
void __mod_memcg_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx,
int val);
void __mod_lruvec_kmem_state(void *p, enum node_stat_item idx, int val);
{
}
+ static inline unsigned long memcg_page_state(struct mem_cgroup *memcg, int idx)
+ {
+ return 0;
+ }
+
static inline unsigned long lruvec_page_state(struct lruvec *lruvec,
enum node_stat_item idx)
{
return node_page_state(lruvec_pgdat(lruvec), idx);
}
+ static inline void mem_cgroup_flush_stats(void)
+ {
+ }
+
static inline void __mod_memcg_lruvec_state(struct lruvec *lruvec,
enum node_stat_item idx, int val)
{
#endif /* CONFIG_CGROUP_WRITEBACK */
struct sock;
-bool mem_cgroup_charge_skmem(struct mem_cgroup *memcg, unsigned int nr_pages);
+bool mem_cgroup_charge_skmem(struct mem_cgroup *memcg, unsigned int nr_pages,
+ gfp_t gfp_mask);
void mem_cgroup_uncharge_skmem(struct mem_cgroup *memcg, unsigned int nr_pages);
#ifdef CONFIG_MEMCG
extern struct static_key_false memcg_sockets_enabled_key;
return kvmalloc_array(n, size, flags | __GFP_ZERO);
}
+extern void *kvrealloc(const void *p, size_t oldsize, size_t newsize,
+ gfp_t flags);
extern void kvfree(const void *addr);
extern void kvfree_sensitive(const void *addr, size_t len);
}
bool __must_check try_grab_page(struct page *page, unsigned int flags);
- __maybe_unused struct page *try_grab_compound_head(struct page *page, int refs,
- unsigned int flags);
+ struct page *try_grab_compound_head(struct page *page, int refs,
+ unsigned int flags);
-
- static inline __must_check bool try_get_page(struct page *page)
- {
- page = compound_head(page);
- if (WARN_ON_ONCE(page_ref_count(page) <= 0))
- return false;
- page_ref_inc(page);
- return true;
- }
+ struct page *try_get_compound_head(struct page *page, int refs);
static inline void put_page(struct page *page)
{
struct kvec;
int get_kernel_pages(const struct kvec *iov, int nr_pages, int write,
struct page **pages);
- int get_kernel_page(unsigned long start, int write, struct page **pages);
struct page *get_dump_page(unsigned long addr);
extern int try_to_release_page(struct page * page, gfp_t gfp_mask);
extern int unpoison_memory(unsigned long pfn);
extern int sysctl_memory_failure_early_kill;
extern int sysctl_memory_failure_recovery;
- extern void shake_page(struct page *p, int access);
+ extern void shake_page(struct page *p);
extern atomic_long_t num_poisoned_pages __read_mostly;
extern int soft_offline_page(unsigned long pfn, int flags);
asmlinkage long sys_madvise(unsigned long start, size_t len, int behavior);
asmlinkage long sys_process_madvise(int pidfd, const struct iovec __user *vec,
size_t vlen, int behavior, unsigned int flags);
+ asmlinkage long sys_process_mrelease(int pidfd, unsigned int flags);
asmlinkage long sys_remap_file_pages(unsigned long start, unsigned long size,
unsigned long prot, unsigned long pgoff,
unsigned long flags);
asmlinkage long sys_vfork(void);
asmlinkage long sys_recv(int, void __user *, size_t, unsigned);
asmlinkage long sys_send(int, void __user *, size_t, unsigned);
-asmlinkage long sys_bdflush(int func, long data);
asmlinkage long sys_oldumount(char __user *name);
asmlinkage long sys_uselib(const char __user *library);
asmlinkage long sys_sysfs(int option,
void wbc_detach_inode(struct writeback_control *wbc);
void wbc_account_cgroup_owner(struct writeback_control *wbc, struct page *page,
size_t bytes);
- int cgroup_writeback_by_id(u64 bdi_id, int memcg_id, unsigned long nr_pages,
+ int cgroup_writeback_by_id(u64 bdi_id, int memcg_id,
enum wb_reason reason, struct wb_completion *done);
void cgroup_writeback_umount(void);
bool cleanup_offline_cgwb(struct bdi_writeback *wb);
/*
* mm/page-writeback.c
*/
-#ifdef CONFIG_BLOCK
void laptop_io_completion(struct backing_dev_info *info);
void laptop_sync_completion(void);
-void laptop_mode_sync(struct work_struct *work);
void laptop_mode_timer_fn(struct timer_list *t);
-#else
-static inline void laptop_sync_completion(void) { }
-#endif
bool node_dirty_ok(struct pglist_data *pgdat);
int wb_domain_init(struct wb_domain *dom, gfp_t gfp);
#ifdef CONFIG_CGROUP_WRITEBACK
void global_dirty_limits(unsigned long *pbackground, unsigned long *pdirty);
unsigned long wb_calc_thresh(struct bdi_writeback *wb, unsigned long thresh);
- void wb_update_bandwidth(struct bdi_writeback *wb, unsigned long start_time);
+ void wb_update_bandwidth(struct bdi_writeback *wb);
void balance_dirty_pages_ratelimited(struct address_space *mapping);
bool wb_over_bg_thresh(struct bdi_writeback *wb);
#include <asm/unistd.h>
#include <asm/siginfo.h>
#include <asm/cacheflush.h>
+#include <asm/syscall.h> /* for syscall_get_* */
/*
* SLAB caches for signal bits.
case SIL_FAULT_MCEERR:
case SIL_FAULT_BNDERR:
case SIL_FAULT_PKUERR:
- case SIL_PERF_EVENT:
+ case SIL_FAULT_PERF_EVENT:
case SIL_SYS:
ret = false;
break;
* that is why we also clear SIGNAL_UNKILLABLE.
*/
static int
-force_sig_info_to_task(struct kernel_siginfo *info, struct task_struct *t)
+force_sig_info_to_task(struct kernel_siginfo *info, struct task_struct *t, bool sigdfl)
{
unsigned long int flags;
int ret, blocked, ignored;
action = &t->sighand->action[sig-1];
ignored = action->sa.sa_handler == SIG_IGN;
blocked = sigismember(&t->blocked, sig);
- if (blocked || ignored) {
+ if (blocked || ignored || sigdfl) {
action->sa.sa_handler = SIG_DFL;
if (blocked) {
sigdelset(&t->blocked, sig);
int force_sig_info(struct kernel_siginfo *info)
{
- return force_sig_info_to_task(info, current);
+ return force_sig_info_to_task(info, current, false);
}
/*
return sighand;
}
+#ifdef CONFIG_LOCKDEP
+void lockdep_assert_task_sighand_held(struct task_struct *task)
+{
+ struct sighand_struct *sighand;
+
+ rcu_read_lock();
+ sighand = rcu_dereference(task->sighand);
+ if (sighand)
+ lockdep_assert_held(&sighand->siglock);
+ else
+ WARN_ON_ONCE(1);
+ rcu_read_unlock();
+}
+#endif
+
/*
* send signal info to all the members of a group
*/
}
int force_sig_fault_to_task(int sig, int code, void __user *addr
- ___ARCH_SI_TRAPNO(int trapno)
___ARCH_SI_IA64(int imm, unsigned int flags, unsigned long isr)
, struct task_struct *t)
{
info.si_errno = 0;
info.si_code = code;
info.si_addr = addr;
-#ifdef __ARCH_SI_TRAPNO
- info.si_trapno = trapno;
-#endif
#ifdef __ia64__
info.si_imm = imm;
info.si_flags = flags;
info.si_isr = isr;
#endif
- return force_sig_info_to_task(&info, t);
+ return force_sig_info_to_task(&info, t, false);
}
int force_sig_fault(int sig, int code, void __user *addr
- ___ARCH_SI_TRAPNO(int trapno)
___ARCH_SI_IA64(int imm, unsigned int flags, unsigned long isr))
{
return force_sig_fault_to_task(sig, code, addr
- ___ARCH_SI_TRAPNO(trapno)
___ARCH_SI_IA64(imm, flags, isr), current);
}
int send_sig_fault(int sig, int code, void __user *addr
- ___ARCH_SI_TRAPNO(int trapno)
___ARCH_SI_IA64(int imm, unsigned int flags, unsigned long isr)
, struct task_struct *t)
{
info.si_errno = 0;
info.si_code = code;
info.si_addr = addr;
-#ifdef __ARCH_SI_TRAPNO
- info.si_trapno = trapno;
-#endif
#ifdef __ia64__
info.si_imm = imm;
info.si_flags = flags;
return force_sig_info(&info);
}
+/**
+ * force_sig_seccomp - signals the task to allow in-process syscall emulation
+ * @syscall: syscall number to send to userland
+ * @reason: filter-supplied reason code to send to userland (via si_errno)
+ *
+ * Forces a SIGSYS with a code of SYS_SECCOMP and related sigsys info.
+ */
+int force_sig_seccomp(int syscall, int reason, bool force_coredump)
+{
+ struct kernel_siginfo info;
+
+ clear_siginfo(&info);
+ info.si_signo = SIGSYS;
+ info.si_code = SYS_SECCOMP;
+ info.si_call_addr = (void __user *)KSTK_EIP(current);
+ info.si_errno = reason;
+ info.si_arch = syscall_get_arch(current);
+ info.si_syscall = syscall;
+ return force_sig_info_to_task(&info, current, force_coredump);
+}
+
/* For the crazy architectures that include trap information in
* the errno field, instead of an actual errno value.
*/
return force_sig_info(&info);
}
+/* For the rare architectures that include trap information using
+ * si_trapno.
+ */
+int force_sig_fault_trapno(int sig, int code, void __user *addr, int trapno)
+{
+ struct kernel_siginfo info;
+
+ clear_siginfo(&info);
+ info.si_signo = sig;
+ info.si_errno = 0;
+ info.si_code = code;
+ info.si_addr = addr;
+ info.si_trapno = trapno;
+ return force_sig_info(&info);
+}
+
+/* For the rare architectures that include trap information using
+ * si_trapno.
+ */
+int send_sig_fault_trapno(int sig, int code, void __user *addr, int trapno,
+ struct task_struct *t)
+{
+ struct kernel_siginfo info;
+
+ clear_siginfo(&info);
+ info.si_signo = sig;
+ info.si_errno = 0;
+ info.si_code = code;
+ info.si_addr = addr;
+ info.si_trapno = trapno;
+ return send_sig_info(info.si_signo, &info, t);
+}
+
int kill_pgrp(struct pid *pid, int sig, int priv)
{
int ret;
case SIL_FAULT_MCEERR:
case SIL_FAULT_BNDERR:
case SIL_FAULT_PKUERR:
- case SIL_PERF_EVENT:
+ case SIL_FAULT_PERF_EVENT:
ksig->info.si_addr = arch_untagged_si_addr(
ksig->info.si_addr, ksig->sig, ksig->info.si_code);
break;
layout = SIL_FAULT_PKUERR;
#endif
else if ((sig == SIGTRAP) && (si_code == TRAP_PERF))
- layout = SIL_PERF_EVENT;
-#ifdef __ARCH_SI_TRAPNO
- else if (layout == SIL_FAULT)
+ layout = SIL_FAULT_PERF_EVENT;
+ else if (IS_ENABLED(CONFIG_SPARC) &&
+ (sig == SIGILL) && (si_code == ILL_ILLTRP))
+ layout = SIL_FAULT_TRAPNO;
+ else if (IS_ENABLED(CONFIG_ALPHA) &&
+ ((sig == SIGFPE) ||
+ ((sig == SIGTRAP) && (si_code == TRAP_UNK))))
layout = SIL_FAULT_TRAPNO;
-#endif
}
else if (si_code <= NSIGPOLL)
layout = SIL_POLL;
to->si_addr = ptr_to_compat(from->si_addr);
to->si_pkey = from->si_pkey;
break;
- case SIL_PERF_EVENT:
+ case SIL_FAULT_PERF_EVENT:
to->si_addr = ptr_to_compat(from->si_addr);
to->si_perf_data = from->si_perf_data;
to->si_perf_type = from->si_perf_type;
to->si_addr = compat_ptr(from->si_addr);
to->si_pkey = from->si_pkey;
break;
- case SIL_PERF_EVENT:
+ case SIL_FAULT_PERF_EVENT:
to->si_addr = compat_ptr(from->si_addr);
to->si_perf_data = from->si_perf_data;
to->si_perf_type = from->si_perf_type;
{
siginfo_buildtime_checks();
- sigqueue_cachep = KMEM_CACHE(sigqueue, SLAB_PANIC);
+ sigqueue_cachep = KMEM_CACHE(sigqueue, SLAB_PANIC | SLAB_ACCOUNT);
}
#ifdef CONFIG_KGDB_KDB
COND_SYSCALL(mincore);
COND_SYSCALL(madvise);
COND_SYSCALL(process_madvise);
+ COND_SYSCALL(process_mrelease);
COND_SYSCALL(remap_file_pages);
COND_SYSCALL(mbind);
COND_SYSCALL_COMPAT(mbind);
COND_SYSCALL(recv);
COND_SYSCALL_COMPAT(recv);
COND_SYSCALL(send);
-COND_SYSCALL(bdflush);
COND_SYSCALL(uselib);
/* optional: time32 */
}
}
+static int do_proc_dobool_conv(bool *negp, unsigned long *lvalp,
+ int *valp,
+ int write, void *data)
+{
+ if (write) {
+ *(bool *)valp = *lvalp;
+ } else {
+ int val = *(bool *)valp;
+
+ *lvalp = (unsigned long)val;
+ *negp = false;
+ }
+ return 0;
+}
+
static int do_proc_dointvec_conv(bool *negp, unsigned long *lvalp,
int *valp,
int write, void *data)
buffer, lenp, ppos, conv, data);
}
+/**
+ * proc_dobool - read/write a bool
+ * @table: the sysctl table
+ * @write: %TRUE if this is a write to the sysctl file
+ * @buffer: the user buffer
+ * @lenp: the size of the user buffer
+ * @ppos: file position
+ *
+ * Reads/writes up to table->maxlen/sizeof(unsigned int) integer
+ * values from/to the user buffer, treated as an ASCII string.
+ *
+ * Returns 0 on success.
+ */
+int proc_dobool(struct ctl_table *table, int write, void *buffer,
+ size_t *lenp, loff_t *ppos)
+{
+ return do_proc_dointvec(table, write, buffer, lenp, ppos,
+ do_proc_dobool_conv, NULL);
+}
+
/**
* proc_dointvec - read a vector of integers
* @table: the sysctl table
return -ENOSYS;
}
+int proc_dobool(struct ctl_table *table, int write,
+ void *buffer, size_t *lenp, loff_t *ppos)
+{
+ return -ENOSYS;
+}
+
int proc_dointvec(struct ctl_table *table, int write,
void *buffer, size_t *lenp, loff_t *ppos)
{
.data = &sysctl_compaction_proactiveness,
.maxlen = sizeof(sysctl_compaction_proactiveness),
.mode = 0644,
- .proc_handler = proc_dointvec_minmax,
+ .proc_handler = compaction_proactiveness_sysctl_handler,
.extra1 = SYSCTL_ZERO,
.extra2 = &one_hundred,
},
* No sense putting this after each symbol definition, twice,
* exception granted :-)
*/
+EXPORT_SYMBOL(proc_dobool);
EXPORT_SYMBOL(proc_dointvec);
EXPORT_SYMBOL(proc_douintvec);
EXPORT_SYMBOL(proc_dointvec_jiffies);
static __init int init_posix_timers(void)
{
posix_timers_cache = kmem_cache_create("posix_timers_cache",
- sizeof (struct k_itimer), 0, SLAB_PANIC,
- NULL);
+ sizeof(struct k_itimer), 0,
+ SLAB_PANIC | SLAB_ACCOUNT, NULL);
return 0;
}
__initcall(init_posix_timers);
int posix_timer_event(struct k_itimer *timr, int si_private)
{
enum pid_type type;
- int ret = -1;
+ int ret;
/*
* FIXME: if ->sigq is queued we can race with
* dequeue_signal()->posixtimer_rearm().
* @nents_first_chunk: Number of entries int the (preallocated) first
* scatterlist chunk, 0 means no such preallocated first chunk
* @free_fn: Free function
+ * @num_ents: Number of entries in the table
*
* Description:
* Free an sg table previously allocated and setup with
*
**/
void __sg_free_table(struct sg_table *table, unsigned int max_ents,
- unsigned int nents_first_chunk, sg_free_fn *free_fn)
+ unsigned int nents_first_chunk, sg_free_fn *free_fn,
+ unsigned int num_ents)
{
struct scatterlist *sgl, *next;
unsigned curr_max_ents = nents_first_chunk ?: max_ents;
return;
sgl = table->sgl;
- while (table->orig_nents) {
- unsigned int alloc_size = table->orig_nents;
+ while (num_ents) {
+ unsigned int alloc_size = num_ents;
unsigned int sg_size;
/*
next = NULL;
}
- table->orig_nents -= sg_size;
+ num_ents -= sg_size;
if (nents_first_chunk)
nents_first_chunk = 0;
else
}
EXPORT_SYMBOL(__sg_free_table);
+/**
+ * sg_free_append_table - Free a previously allocated append sg table.
+ * @table: The mapped sg append table header
+ *
+ **/
+void sg_free_append_table(struct sg_append_table *table)
+{
+ __sg_free_table(&table->sgt, SG_MAX_SINGLE_ALLOC, false, sg_kfree,
+ table->total_nents);
+}
+EXPORT_SYMBOL(sg_free_append_table);
+
+
/**
* sg_free_table - Free a previously allocated sg table
* @table: The mapped sg table header
**/
void sg_free_table(struct sg_table *table)
{
- __sg_free_table(table, SG_MAX_SINGLE_ALLOC, false, sg_kfree);
+ __sg_free_table(table, SG_MAX_SINGLE_ALLOC, false, sg_kfree,
+ table->orig_nents);
}
EXPORT_SYMBOL(sg_free_table);
ret = __sg_alloc_table(table, nents, SG_MAX_SINGLE_ALLOC,
NULL, 0, gfp_mask, sg_kmalloc);
if (unlikely(ret))
- __sg_free_table(table, SG_MAX_SINGLE_ALLOC, 0, sg_kfree);
-
+ sg_free_table(table);
return ret;
}
EXPORT_SYMBOL(sg_alloc_table);
-static struct scatterlist *get_next_sg(struct sg_table *table,
+static struct scatterlist *get_next_sg(struct sg_append_table *table,
struct scatterlist *cur,
unsigned long needed_sges,
gfp_t gfp_mask)
return ERR_PTR(-ENOMEM);
sg_init_table(new_sg, alloc_size);
if (cur) {
+ table->total_nents += alloc_size - 1;
__sg_chain(next_sg, new_sg);
- table->orig_nents += alloc_size - 1;
} else {
- table->sgl = new_sg;
- table->orig_nents = alloc_size;
- table->nents = 0;
+ table->sgt.sgl = new_sg;
+ table->total_nents = alloc_size;
}
return new_sg;
}
/**
- * __sg_alloc_table_from_pages - Allocate and initialize an sg table from
- * an array of pages
- * @sgt: The sg table header to use
- * @pages: Pointer to an array of page pointers
- * @n_pages: Number of pages in the pages array
+ * sg_alloc_append_table_from_pages - Allocate and initialize an append sg
+ * table from an array of pages
+ * @sgt_append: The sg append table to use
+ * @pages: Pointer to an array of page pointers
+ * @n_pages: Number of pages in the pages array
* @offset: Offset from start of the first page to the start of a buffer
* @size: Number of valid bytes in the buffer (after offset)
* @max_segment: Maximum size of a scatterlist element in bytes
- * @prv: Last populated sge in sgt
* @left_pages: Left pages caller have to set after this call
* @gfp_mask: GFP allocation mask
*
* Description:
- * If @prv is NULL, allocate and initialize an sg table from a list of pages,
- * else reuse the scatterlist passed in at @prv.
- * Contiguous ranges of the pages are squashed into a single scatterlist
- * entry up to the maximum size specified in @max_segment. A user may
- * provide an offset at a start and a size of valid data in a buffer
- * specified by the page array.
+ * In the first call it allocate and initialize an sg table from a list of
+ * pages, else reuse the scatterlist from sgt_append. Contiguous ranges of
+ * the pages are squashed into a single scatterlist entry up to the maximum
+ * size specified in @max_segment. A user may provide an offset at a start
+ * and a size of valid data in a buffer specified by the page array. The
+ * returned sg table is released by sg_free_append_table
*
* Returns:
- * Last SGE in sgt on success, PTR_ERR on otherwise.
- * The allocation in @sgt must be released by sg_free_table.
+ * 0 on success, negative error on failure
*
* Notes:
* If this function returns non-0 (eg failure), the caller must call
- * sg_free_table() to cleanup any leftover allocations.
+ * sg_free_append_table() to cleanup any leftover allocations.
+ *
+ * In the fist call, sgt_append must by initialized.
*/
-struct scatterlist *__sg_alloc_table_from_pages(struct sg_table *sgt,
+int sg_alloc_append_table_from_pages(struct sg_append_table *sgt_append,
struct page **pages, unsigned int n_pages, unsigned int offset,
unsigned long size, unsigned int max_segment,
- struct scatterlist *prv, unsigned int left_pages,
- gfp_t gfp_mask)
+ unsigned int left_pages, gfp_t gfp_mask)
{
unsigned int chunks, cur_page, seg_len, i, prv_len = 0;
unsigned int added_nents = 0;
- struct scatterlist *s = prv;
+ struct scatterlist *s = sgt_append->prv;
/*
* The algorithm below requires max_segment to be aligned to PAGE_SIZE
*/
max_segment = ALIGN_DOWN(max_segment, PAGE_SIZE);
if (WARN_ON(max_segment < PAGE_SIZE))
- return ERR_PTR(-EINVAL);
+ return -EINVAL;
- if (IS_ENABLED(CONFIG_ARCH_NO_SG_CHAIN) && prv)
- return ERR_PTR(-EOPNOTSUPP);
+ if (IS_ENABLED(CONFIG_ARCH_NO_SG_CHAIN) && sgt_append->prv)
+ return -EOPNOTSUPP;
- if (prv) {
- unsigned long paddr = (page_to_pfn(sg_page(prv)) * PAGE_SIZE +
- prv->offset + prv->length) /
- PAGE_SIZE;
+ if (sgt_append->prv) {
+ unsigned long paddr =
+ (page_to_pfn(sg_page(sgt_append->prv)) * PAGE_SIZE +
+ sgt_append->prv->offset + sgt_append->prv->length) /
+ PAGE_SIZE;
if (WARN_ON(offset))
- return ERR_PTR(-EINVAL);
+ return -EINVAL;
/* Merge contiguous pages into the last SG */
- prv_len = prv->length;
+ prv_len = sgt_append->prv->length;
while (n_pages && page_to_pfn(pages[0]) == paddr) {
- if (prv->length + PAGE_SIZE > max_segment)
+ if (sgt_append->prv->length + PAGE_SIZE > max_segment)
break;
- prv->length += PAGE_SIZE;
+ sgt_append->prv->length += PAGE_SIZE;
paddr++;
pages++;
n_pages--;
}
/* Pass how many chunks might be left */
- s = get_next_sg(sgt, s, chunks - i + left_pages, gfp_mask);
+ s = get_next_sg(sgt_append, s, chunks - i + left_pages,
+ gfp_mask);
if (IS_ERR(s)) {
/*
* Adjust entry length to be as before function was
* called.
*/
- if (prv)
- prv->length = prv_len;
- return s;
+ if (sgt_append->prv)
+ sgt_append->prv->length = prv_len;
+ return PTR_ERR(s);
}
chunk_size = ((j - cur_page) << PAGE_SHIFT) - offset;
sg_set_page(s, pages[cur_page],
offset = 0;
cur_page = j;
}
- sgt->nents += added_nents;
+ sgt_append->sgt.nents += added_nents;
+ sgt_append->sgt.orig_nents = sgt_append->sgt.nents;
+ sgt_append->prv = s;
out:
if (!left_pages)
sg_mark_end(s);
- return s;
+ return 0;
}
-EXPORT_SYMBOL(__sg_alloc_table_from_pages);
+EXPORT_SYMBOL(sg_alloc_append_table_from_pages);
/**
- * sg_alloc_table_from_pages - Allocate and initialize an sg table from
- * an array of pages
+ * sg_alloc_table_from_pages_segment - Allocate and initialize an sg table from
+ * an array of pages and given maximum
+ * segment.
* @sgt: The sg table header to use
* @pages: Pointer to an array of page pointers
* @n_pages: Number of pages in the pages array
* @offset: Offset from start of the first page to the start of a buffer
* @size: Number of valid bytes in the buffer (after offset)
+ * @max_segment: Maximum size of a scatterlist element in bytes
* @gfp_mask: GFP allocation mask
*
* Description:
* Allocate and initialize an sg table from a list of pages. Contiguous
- * ranges of the pages are squashed into a single scatterlist node. A user
- * may provide an offset at a start and a size of valid data in a buffer
- * specified by the page array. The returned sg table is released by
- * sg_free_table.
+ * ranges of the pages are squashed into a single scatterlist node up to the
+ * maximum size specified in @max_segment. A user may provide an offset at a
+ * start and a size of valid data in a buffer specified by the page array.
*
- * Returns:
+ * The returned sg table is released by sg_free_table.
+ *
+ * Returns:
* 0 on success, negative error on failure
*/
-int sg_alloc_table_from_pages(struct sg_table *sgt, struct page **pages,
- unsigned int n_pages, unsigned int offset,
- unsigned long size, gfp_t gfp_mask)
+int sg_alloc_table_from_pages_segment(struct sg_table *sgt, struct page **pages,
+ unsigned int n_pages, unsigned int offset,
+ unsigned long size, unsigned int max_segment,
+ gfp_t gfp_mask)
{
- return PTR_ERR_OR_ZERO(__sg_alloc_table_from_pages(sgt, pages, n_pages,
- offset, size, UINT_MAX, NULL, 0, gfp_mask));
+ struct sg_append_table append = {};
+ int err;
+
+ err = sg_alloc_append_table_from_pages(&append, pages, n_pages, offset,
+ size, max_segment, 0, gfp_mask);
+ if (err) {
+ sg_free_append_table(&append);
+ return err;
+ }
+ memcpy(sgt, &append.sgt, sizeof(*sgt));
+ WARN_ON(append.total_nents != sgt->orig_nents);
+ return 0;
}
-EXPORT_SYMBOL(sg_alloc_table_from_pages);
+EXPORT_SYMBOL(sg_alloc_table_from_pages_segment);
#ifdef CONFIG_SGL_ALLOC
miter->__offset += miter->consumed;
miter->__remaining -= miter->consumed;
- if ((miter->__flags & SG_MITER_TO_SG) &&
- !PageSlab(miter->page))
- flush_kernel_dcache_page(miter->page);
+ if (miter->__flags & SG_MITER_TO_SG)
+ flush_dcache_page(miter->page);
if (miter->__flags & SG_MITER_ATOMIC) {
WARN_ON_ONCE(preemptible());
}
multishot = kasan_save_enable_multi_shot();
- kasan_set_tagging_report_once(false);
fail_data.report_found = false;
kunit_add_named_resource(test, NULL, NULL, &resource,
"kasan_data", &fail_data);
static void kasan_test_exit(struct kunit *test)
{
- kasan_set_tagging_report_once(true);
kasan_restore_multi_shot(multishot);
KUNIT_EXPECT_FALSE(test, fail_data.report_found);
}
static void kmalloc_oob_right(struct kunit *test)
{
char *ptr;
- size_t size = 123;
+ size_t size = 128 - KASAN_GRANULE_SIZE - 5;
ptr = kmalloc(size, GFP_KERNEL);
KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr);
- KUNIT_EXPECT_KASAN_FAIL(test, ptr[size + OOB_TAG_OFF] = 'x');
+ /*
+ * An unaligned access past the requested kmalloc size.
+ * Only generic KASAN can precisely detect these.
+ */
+ if (IS_ENABLED(CONFIG_KASAN_GENERIC))
+ KUNIT_EXPECT_KASAN_FAIL(test, ptr[size] = 'x');
+
+ /*
+ * An aligned access into the first out-of-bounds granule that falls
+ * within the aligned kmalloc object.
+ */
+ KUNIT_EXPECT_KASAN_FAIL(test, ptr[size + 5] = 'y');
+
+ /* Out-of-bounds access past the aligned kmalloc object. */
+ KUNIT_EXPECT_KASAN_FAIL(test, ptr[0] =
+ ptr[size + KASAN_GRANULE_SIZE + 5]);
+
kfree(ptr);
}
ptr = kmalloc_node(size, GFP_KERNEL, 0);
KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr);
- KUNIT_EXPECT_KASAN_FAIL(test, ptr[size] = 0);
+ KUNIT_EXPECT_KASAN_FAIL(test, ptr[0] = ptr[size]);
kfree(ptr);
}
KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr);
kfree(ptr);
- KUNIT_EXPECT_KASAN_FAIL(test, ptr[0] = 0);
+ KUNIT_EXPECT_KASAN_FAIL(test, ((volatile char *)ptr)[0]);
}
static void kmalloc_pagealloc_invalid_free(struct kunit *test)
ptr = page_address(pages);
KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr);
- KUNIT_EXPECT_KASAN_FAIL(test, ptr[size] = 0);
+ KUNIT_EXPECT_KASAN_FAIL(test, ptr[0] = ptr[size]);
free_pages((unsigned long)ptr, order);
}
KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr);
free_pages((unsigned long)ptr, order);
- KUNIT_EXPECT_KASAN_FAIL(test, ptr[0] = 0);
+ KUNIT_EXPECT_KASAN_FAIL(test, ((volatile char *)ptr)[0]);
}
static void kmalloc_large_oob_right(struct kunit *test)
kfree(ptr1);
}
+ /*
+ * Note: in the memset tests below, the written range touches both valid and
+ * invalid memory. This makes sure that the instrumentation does not only check
+ * the starting address but the whole range.
+ */
+
static void kmalloc_oob_memset_2(struct kunit *test)
{
char *ptr;
- size_t size = 8;
+ size_t size = 128 - KASAN_GRANULE_SIZE;
ptr = kmalloc(size, GFP_KERNEL);
KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr);
- KUNIT_EXPECT_KASAN_FAIL(test, memset(ptr + 7 + OOB_TAG_OFF, 0, 2));
+ KUNIT_EXPECT_KASAN_FAIL(test, memset(ptr + size - 1, 0, 2));
kfree(ptr);
}
static void kmalloc_oob_memset_4(struct kunit *test)
{
char *ptr;
- size_t size = 8;
+ size_t size = 128 - KASAN_GRANULE_SIZE;
ptr = kmalloc(size, GFP_KERNEL);
KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr);
- KUNIT_EXPECT_KASAN_FAIL(test, memset(ptr + 5 + OOB_TAG_OFF, 0, 4));
+ KUNIT_EXPECT_KASAN_FAIL(test, memset(ptr + size - 3, 0, 4));
kfree(ptr);
}
-
static void kmalloc_oob_memset_8(struct kunit *test)
{
char *ptr;
- size_t size = 8;
+ size_t size = 128 - KASAN_GRANULE_SIZE;
ptr = kmalloc(size, GFP_KERNEL);
KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr);
- KUNIT_EXPECT_KASAN_FAIL(test, memset(ptr + 1 + OOB_TAG_OFF, 0, 8));
+ KUNIT_EXPECT_KASAN_FAIL(test, memset(ptr + size - 7, 0, 8));
kfree(ptr);
}
static void kmalloc_oob_memset_16(struct kunit *test)
{
char *ptr;
- size_t size = 16;
+ size_t size = 128 - KASAN_GRANULE_SIZE;
ptr = kmalloc(size, GFP_KERNEL);
KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr);
- KUNIT_EXPECT_KASAN_FAIL(test, memset(ptr + 1 + OOB_TAG_OFF, 0, 16));
+ KUNIT_EXPECT_KASAN_FAIL(test, memset(ptr + size - 15, 0, 16));
kfree(ptr);
}
static void kmalloc_oob_in_memset(struct kunit *test)
{
char *ptr;
- size_t size = 666;
+ size_t size = 128 - KASAN_GRANULE_SIZE;
ptr = kmalloc(size, GFP_KERNEL);
KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr);
- KUNIT_EXPECT_KASAN_FAIL(test, memset(ptr, 0, size + 5 + OOB_TAG_OFF));
+ KUNIT_EXPECT_KASAN_FAIL(test,
+ memset(ptr, 0, size + KASAN_GRANULE_SIZE));
kfree(ptr);
}
size_t size = 64;
volatile size_t invalid_size = -2;
+ /*
+ * Hardware tag-based mode doesn't check memmove for negative size.
+ * As a result, this test introduces a side-effect memory corruption,
+ * which can result in a crash.
+ */
+ KASAN_TEST_NEEDS_CONFIG_OFF(test, CONFIG_KASAN_HW_TAGS);
+
ptr = kmalloc(size, GFP_KERNEL);
KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr);
memset((char *)ptr, 0, 64);
-
KUNIT_EXPECT_KASAN_FAIL(test,
memmove((char *)ptr, (char *)ptr + 4, invalid_size));
kfree(ptr);
KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr);
kfree(ptr);
- KUNIT_EXPECT_KASAN_FAIL(test, *(ptr + 8) = 'x');
+ KUNIT_EXPECT_KASAN_FAIL(test, ((volatile char *)ptr)[8]);
}
static void kmalloc_uaf_memset(struct kunit *test)
char *ptr;
size_t size = 33;
+ /*
+ * Only generic KASAN uses quarantine, which is required to avoid a
+ * kernel memory corruption this test causes.
+ */
+ KASAN_TEST_NEEDS_CONFIG_ON(test, CONFIG_KASAN_GENERIC);
+
ptr = kmalloc(size, GFP_KERNEL);
KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr);
goto again;
}
- KUNIT_EXPECT_KASAN_FAIL(test, ptr1[40] = 'x');
+ KUNIT_EXPECT_KASAN_FAIL(test, ((volatile char *)ptr1)[40]);
KUNIT_EXPECT_PTR_NE(test, ptr1, ptr2);
kfree(ptr2);
ptr[size] = 'x';
/* This one must. */
- KUNIT_EXPECT_KASAN_FAIL(test, ptr[real_size] = 'y');
+ KUNIT_EXPECT_KASAN_FAIL(test, ((volatile char *)ptr)[real_size]);
kfree(ptr);
}
kfree(ptr);
KUNIT_EXPECT_KASAN_FAIL(test, ksize(ptr));
- KUNIT_EXPECT_KASAN_FAIL(test, kasan_int_result = *ptr);
- KUNIT_EXPECT_KASAN_FAIL(test, kasan_int_result = *(ptr + size));
+ KUNIT_EXPECT_KASAN_FAIL(test, ((volatile char *)ptr)[0]);
+ KUNIT_EXPECT_KASAN_FAIL(test, ((volatile char *)ptr)[size]);
}
static void kasan_stack_oob(struct kunit *test)
spin_unlock_bh(&wb->work_lock);
}
+ static void wb_update_bandwidth_workfn(struct work_struct *work)
+ {
+ struct bdi_writeback *wb = container_of(to_delayed_work(work),
+ struct bdi_writeback, bw_dwork);
+
+ wb_update_bandwidth(wb);
+ }
+
/*
* Initial write bandwidth: 100 MB/s
*/
INIT_LIST_HEAD(&wb->b_dirty_time);
spin_lock_init(&wb->list_lock);
+ atomic_set(&wb->writeback_inodes, 0);
wb->bw_time_stamp = jiffies;
wb->balanced_dirty_ratelimit = INIT_BW;
wb->dirty_ratelimit = INIT_BW;
spin_lock_init(&wb->work_lock);
INIT_LIST_HEAD(&wb->work_list);
INIT_DELAYED_WORK(&wb->dwork, wb_workfn);
+ INIT_DELAYED_WORK(&wb->bw_dwork, wb_update_bandwidth_workfn);
wb->dirty_sleep = jiffies;
err = fprop_local_init_percpu(&wb->completions, gfp);
mod_delayed_work(bdi_wq, &wb->dwork, 0);
flush_delayed_work(&wb->dwork);
WARN_ON(!list_empty(&wb->work_list));
+ flush_delayed_work(&wb->bw_dwork);
}
static void wb_exit(struct bdi_writeback *wb)
bdi->capabilities = BDI_CAP_WRITEBACK | BDI_CAP_WRITEBACK_ACCT;
bdi->ra_pages = VM_READAHEAD_PAGES;
bdi->io_pages = VM_READAHEAD_PAGES;
+ timer_setup(&bdi->laptop_mode_wb_timer, laptop_mode_timer_fn, 0);
return bdi;
}
EXPORT_SYMBOL(bdi_alloc);
void bdi_unregister(struct backing_dev_info *bdi)
{
+ del_timer_sync(&bdi->laptop_mode_wb_timer);
+
/* make sure nobody finds us on the bdi_list anymore */
bdi_remove_from_list(bdi);
wb_shutdown(&bdi->wb);
* ->swap_lock (exclusive_swap_page, others)
* ->i_pages lock
*
- * ->i_mutex
- * ->i_mmap_rwsem (truncate->unmap_mapping_range)
+ * ->i_rwsem
+ * ->invalidate_lock (acquired by fs in truncate path)
+ * ->i_mmap_rwsem (truncate->unmap_mapping_range)
*
* ->mmap_lock
* ->i_mmap_rwsem
* ->i_pages lock (arch-dependent flush_dcache_mmap_lock)
*
* ->mmap_lock
- * ->lock_page (access_process_vm)
+ * ->invalidate_lock (filemap_fault)
+ * ->lock_page (filemap_fault, access_process_vm)
*
- * ->i_mutex (generic_perform_write)
+ * ->i_rwsem (generic_perform_write)
* ->mmap_lock (fault_in_pages_readable->do_page_fault)
*
* bdi->wb.list_lock
void delete_from_page_cache(struct page *page)
{
struct address_space *mapping = page_mapping(page);
- unsigned long flags;
BUG_ON(!PageLocked(page));
- xa_lock_irqsave(&mapping->i_pages, flags);
+ xa_lock_irq(&mapping->i_pages);
__delete_from_page_cache(page, NULL);
- xa_unlock_irqrestore(&mapping->i_pages, flags);
+ xa_unlock_irq(&mapping->i_pages);
page_cache_free_page(mapping, page);
}
struct pagevec *pvec)
{
int i;
- unsigned long flags;
if (!pagevec_count(pvec))
return;
- xa_lock_irqsave(&mapping->i_pages, flags);
+ xa_lock_irq(&mapping->i_pages);
for (i = 0; i < pagevec_count(pvec); i++) {
trace_mm_filemap_delete_from_page_cache(pvec->pages[i]);
unaccount_page_cache_page(mapping, pvec->pages[i]);
}
page_cache_delete_batch(mapping, pvec);
- xa_unlock_irqrestore(&mapping->i_pages, flags);
+ xa_unlock_irq(&mapping->i_pages);
for (i = 0; i < pagevec_count(pvec); i++)
page_cache_free_page(mapping, pvec->pages[i]);
return 0;
}
+/**
+ * filemap_fdatawrite_wbc - start writeback on mapping dirty pages in range
+ * @mapping: address space structure to write
+ * @wbc: the writeback_control controlling the writeout
+ *
+ * Call writepages on the mapping using the provided wbc to control the
+ * writeout.
+ *
+ * Return: %0 on success, negative error code otherwise.
+ */
+int filemap_fdatawrite_wbc(struct address_space *mapping,
+ struct writeback_control *wbc)
+{
+ int ret;
+
+ if (!mapping_can_writeback(mapping) ||
+ !mapping_tagged(mapping, PAGECACHE_TAG_DIRTY))
+ return 0;
+
+ wbc_attach_fdatawrite_inode(wbc, mapping->host);
+ ret = do_writepages(mapping, wbc);
+ wbc_detach_inode(wbc);
+ return ret;
+}
+EXPORT_SYMBOL(filemap_fdatawrite_wbc);
+
/**
* __filemap_fdatawrite_range - start writeback on mapping dirty pages in range
* @mapping: address space structure to write
int __filemap_fdatawrite_range(struct address_space *mapping, loff_t start,
loff_t end, int sync_mode)
{
- int ret;
struct writeback_control wbc = {
.sync_mode = sync_mode,
.nr_to_write = LONG_MAX,
.range_end = end,
};
- if (!mapping_can_writeback(mapping) ||
- !mapping_tagged(mapping, PAGECACHE_TAG_DIRTY))
- return 0;
-
- wbc_attach_fdatawrite_inode(&wbc, mapping->host);
- ret = do_writepages(mapping, &wbc);
- wbc_detach_inode(&wbc);
- return ret;
+ return filemap_fdatawrite_wbc(mapping, &wbc);
}
static inline int __filemap_fdatawrite(struct address_space *mapping,
void (*freepage)(struct page *) = mapping->a_ops->freepage;
pgoff_t offset = old->index;
XA_STATE(xas, &mapping->i_pages, offset);
- unsigned long flags;
VM_BUG_ON_PAGE(!PageLocked(old), old);
VM_BUG_ON_PAGE(!PageLocked(new), new);
mem_cgroup_migrate(old, new);
- xas_lock_irqsave(&xas, flags);
+ xas_lock_irq(&xas);
xas_store(&xas, new);
old->mapping = NULL;
__dec_lruvec_page_state(old, NR_SHMEM);
if (PageSwapBacked(new))
__inc_lruvec_page_state(new, NR_SHMEM);
- xas_unlock_irqrestore(&xas, flags);
+ xas_unlock_irq(&xas);
if (freepage)
freepage(old);
put_page(old);
EXPORT_SYMBOL(__page_cache_alloc);
#endif
+/*
+ * filemap_invalidate_lock_two - lock invalidate_lock for two mappings
+ *
+ * Lock exclusively invalidate_lock of any passed mapping that is not NULL.
+ *
+ * @mapping1: the first mapping to lock
+ * @mapping2: the second mapping to lock
+ */
+void filemap_invalidate_lock_two(struct address_space *mapping1,
+ struct address_space *mapping2)
+{
+ if (mapping1 > mapping2)
+ swap(mapping1, mapping2);
+ if (mapping1)
+ down_write(&mapping1->invalidate_lock);
+ if (mapping2 && mapping1 != mapping2)
+ down_write_nested(&mapping2->invalidate_lock, 1);
+}
+EXPORT_SYMBOL(filemap_invalidate_lock_two);
+
+/*
+ * filemap_invalidate_unlock_two - unlock invalidate_lock for two mappings
+ *
+ * Unlock exclusive invalidate_lock of any passed mapping that is not NULL.
+ *
+ * @mapping1: the first mapping to unlock
+ * @mapping2: the second mapping to unlock
+ */
+void filemap_invalidate_unlock_two(struct address_space *mapping1,
+ struct address_space *mapping2)
+{
+ if (mapping1)
+ up_write(&mapping1->invalidate_lock);
+ if (mapping2 && mapping1 != mapping2)
+ up_write(&mapping2->invalidate_lock);
+}
+EXPORT_SYMBOL(filemap_invalidate_unlock_two);
+
/*
* In order to wait for pages to become available there must be
* waitqueues associated with pages. By using a hash table of
{
int error;
+ if (iocb->ki_flags & IOCB_NOWAIT) {
+ if (!filemap_invalidate_trylock_shared(mapping))
+ return -EAGAIN;
+ } else {
+ filemap_invalidate_lock_shared(mapping);
+ }
+
if (!trylock_page(page)) {
+ error = -EAGAIN;
if (iocb->ki_flags & (IOCB_NOWAIT | IOCB_NOIO))
- return -EAGAIN;
+ goto unlock_mapping;
if (!(iocb->ki_flags & IOCB_WAITQ)) {
+ filemap_invalidate_unlock_shared(mapping);
put_and_wait_on_page_locked(page, TASK_KILLABLE);
return AOP_TRUNCATED_PAGE;
}
error = __lock_page_async(page, iocb->ki_waitq);
if (error)
- return error;
+ goto unlock_mapping;
}
+ error = AOP_TRUNCATED_PAGE;
if (!page->mapping)
- goto truncated;
+ goto unlock;
error = 0;
if (filemap_range_uptodate(mapping, iocb->ki_pos, iter, page))
goto unlock;
error = filemap_read_page(iocb->ki_filp, mapping, page);
- if (error == AOP_TRUNCATED_PAGE)
- put_page(page);
- return error;
-truncated:
- unlock_page(page);
- put_page(page);
- return AOP_TRUNCATED_PAGE;
+ goto unlock_mapping;
unlock:
unlock_page(page);
+unlock_mapping:
+ filemap_invalidate_unlock_shared(mapping);
+ if (error == AOP_TRUNCATED_PAGE)
+ put_page(page);
return error;
}
if (!page)
return -ENOMEM;
+ /*
+ * Protect against truncate / hole punch. Grabbing invalidate_lock here
+ * assures we cannot instantiate and bring uptodate new pagecache pages
+ * after evicting page cache during truncate and before actually
+ * freeing blocks. Note that we could release invalidate_lock after
+ * inserting the page into page cache as the locked page would then be
+ * enough to synchronize with hole punching. But there are code paths
+ * such as filemap_update_page() filling in partially uptodate pages or
+ * ->readpages() that need to hold invalidate_lock while mapping blocks
+ * for IO so let's hold the lock here as well to keep locking rules
+ * simple.
+ */
+ filemap_invalidate_lock_shared(mapping);
error = add_to_page_cache_lru(page, mapping, index,
mapping_gfp_constraint(mapping, GFP_KERNEL));
if (error == -EEXIST)
if (error)
goto error;
+ filemap_invalidate_unlock_shared(mapping);
pagevec_add(pvec, page);
return 0;
error:
+ filemap_invalidate_unlock_shared(mapping);
put_page(page);
return error;
}
pgoff_t max_off;
struct page *page;
vm_fault_t ret = 0;
+ bool mapping_locked = false;
max_off = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE);
if (unlikely(offset >= max_off))
* Do we have something in the page cache already?
*/
page = find_get_page(mapping, offset);
- if (likely(page) && !(vmf->flags & FAULT_FLAG_TRIED)) {
+ if (likely(page)) {
/*
- * We found the page, so try async readahead before
- * waiting for the lock.
+ * We found the page, so try async readahead before waiting for
+ * the lock.
*/
- fpin = do_async_mmap_readahead(vmf, page);
- } else if (!page) {
+ if (!(vmf->flags & FAULT_FLAG_TRIED))
+ fpin = do_async_mmap_readahead(vmf, page);
+ if (unlikely(!PageUptodate(page))) {
+ filemap_invalidate_lock_shared(mapping);
+ mapping_locked = true;
+ }
+ } else {
/* No page in the page cache at all */
count_vm_event(PGMAJFAULT);
count_memcg_event_mm(vmf->vma->vm_mm, PGMAJFAULT);
ret = VM_FAULT_MAJOR;
fpin = do_sync_mmap_readahead(vmf);
retry_find:
+ /*
+ * See comment in filemap_create_page() why we need
+ * invalidate_lock
+ */
+ if (!mapping_locked) {
+ filemap_invalidate_lock_shared(mapping);
+ mapping_locked = true;
+ }
page = pagecache_get_page(mapping, offset,
FGP_CREAT|FGP_FOR_MMAP,
vmf->gfp_mask);
if (!page) {
if (fpin)
goto out_retry;
+ filemap_invalidate_unlock_shared(mapping);
return VM_FAULT_OOM;
}
}
* We have a locked page in the page cache, now we need to check
* that it's up-to-date. If not, it is going to be due to an error.
*/
- if (unlikely(!PageUptodate(page)))
+ if (unlikely(!PageUptodate(page))) {
+ /*
+ * The page was in cache and uptodate and now it is not.
+ * Strange but possible since we didn't hold the page lock all
+ * the time. Let's drop everything get the invalidate lock and
+ * try again.
+ */
+ if (!mapping_locked) {
+ unlock_page(page);
+ put_page(page);
+ goto retry_find;
+ }
goto page_not_uptodate;
+ }
/*
* We've made it this far and we had to drop our mmap_lock, now is the
unlock_page(page);
goto out_retry;
}
+ if (mapping_locked)
+ filemap_invalidate_unlock_shared(mapping);
/*
* Found the page and have a reference on it.
if (!error || error == AOP_TRUNCATED_PAGE)
goto retry_find;
+ filemap_invalidate_unlock_shared(mapping);
return VM_FAULT_SIGBUS;
*/
if (page)
put_page(page);
+ if (mapping_locked)
+ filemap_invalidate_unlock_shared(mapping);
if (fpin)
fput(fpin);
return ret | VM_FAULT_RETRY;
*
* If the page does not get brought uptodate, return -EIO.
*
+ * The function expects mapping->invalidate_lock to be already held.
+ *
* Return: up to date page on success, ERR_PTR() on failure.
*/
struct page *read_cache_page(struct address_space *mapping,
*
* If the page does not get brought uptodate, return -EIO.
*
+ * The function expects mapping->invalidate_lock to be already held.
+ *
* Return: up to date page on success, ERR_PTR() on failure.
*/
struct page *read_cache_page_gfp(struct address_space *mapping,
* modification times and calls proper subroutines depending on whether we
* do direct IO or a standard buffered write.
*
- * It expects i_mutex to be grabbed unless we work on a block device or similar
+ * It expects i_rwsem to be grabbed unless we work on a block device or similar
* object which does not need locking at all.
*
* This function does *not* take care of syncing data in case of O_SYNC write.
* A caller has to handle it. This is mainly due to the fact that we want to
- * avoid syncing under i_mutex.
+ * avoid syncing under i_rwsem.
*
* Return:
* * number of bytes written, even for truncated writes
*
* This is a wrapper around __generic_file_write_iter() to be used by most
* filesystems. It takes care of syncing the file in case of O_SYNC file
- * and acquires i_mutex as needed.
+ * and acquires i_rwsem as needed.
* Return:
* * negative error code if no data has been written at all of
* vfs_fsync_range() failed for a synchronous write
KASAN_ARG_STACKTRACE_ON,
};
- enum kasan_arg_fault {
- KASAN_ARG_FAULT_DEFAULT,
- KASAN_ARG_FAULT_REPORT,
- KASAN_ARG_FAULT_PANIC,
- };
-
static enum kasan_arg kasan_arg __ro_after_init;
static enum kasan_arg_mode kasan_arg_mode __ro_after_init;
static enum kasan_arg_stacktrace kasan_arg_stacktrace __ro_after_init;
- static enum kasan_arg_fault kasan_arg_fault __ro_after_init;
/* Whether KASAN is enabled at all. */
DEFINE_STATIC_KEY_FALSE(kasan_flag_enabled);
/* Whether to collect alloc/free stack traces. */
DEFINE_STATIC_KEY_FALSE(kasan_flag_stacktrace);
- /* Whether to panic or print a report and disable tag checking on fault. */
- bool kasan_flag_panic __ro_after_init;
-
/* kasan=off/on */
static int __init early_kasan_flag(char *arg)
{
}
early_param("kasan.stacktrace", early_kasan_flag_stacktrace);
- /* kasan.fault=report/panic */
- static int __init early_kasan_fault(char *arg)
- {
- if (!arg)
- return -EINVAL;
-
- if (!strcmp(arg, "report"))
- kasan_arg_fault = KASAN_ARG_FAULT_REPORT;
- else if (!strcmp(arg, "panic"))
- kasan_arg_fault = KASAN_ARG_FAULT_PANIC;
- else
- return -EINVAL;
-
- return 0;
- }
- early_param("kasan.fault", early_kasan_fault);
-
/* kasan_init_hw_tags_cpu() is called for each CPU. */
void kasan_init_hw_tags_cpu(void)
{
if (kasan_arg == KASAN_ARG_OFF)
return;
- hw_init_tags(KASAN_TAG_MAX);
-
/*
* Enable async mode only when explicitly requested through
* the command line.
break;
}
- switch (kasan_arg_fault) {
- case KASAN_ARG_FAULT_DEFAULT:
- /*
- * Default to no panic on report.
- * Do nothing, kasan_flag_panic keeps its default value.
- */
- break;
- case KASAN_ARG_FAULT_REPORT:
- /* Do nothing, kasan_flag_panic keeps its default value. */
- break;
- case KASAN_ARG_FAULT_PANIC:
- /* Enable panic on report. */
- kasan_flag_panic = true;
- break;
- }
-
pr_info("KernelAddressSanitizer initialized\n");
}
#if IS_ENABLED(CONFIG_KASAN_KUNIT_TEST)
-void kasan_set_tagging_report_once(bool state)
-{
- hw_set_tagging_report_once(state);
-}
-EXPORT_SYMBOL_GPL(kasan_set_tagging_report_once);
-
void kasan_enable_tagging_sync(void)
{
hw_enable_tagging_sync();
#define __MM_KASAN_KASAN_H
#include <linux/kasan.h>
+#include <linux/kasan-tags.h>
#include <linux/kfence.h>
#include <linux/stackdepot.h>
#endif
- extern bool kasan_flag_panic __ro_after_init;
extern bool kasan_flag_async __ro_after_init;
#if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)
#define KASAN_MEMORY_PER_SHADOW_PAGE (KASAN_GRANULE_SIZE << PAGE_SHIFT)
-#define KASAN_TAG_KERNEL 0xFF /* native kernel pointers tag */
-#define KASAN_TAG_INVALID 0xFE /* inaccessible memory tag */
-#define KASAN_TAG_MAX 0xFD /* maximum value for random tags */
-
-#ifdef CONFIG_KASAN_HW_TAGS
-#define KASAN_TAG_MIN 0xF0 /* minimum value for random tags */
-#else
-#define KASAN_TAG_MIN 0x00 /* minimum value for random tags */
-#endif
-
#ifdef CONFIG_KASAN_GENERIC
#define KASAN_FREE_PAGE 0xFF /* page was freed */
#define KASAN_PAGE_REDZONE 0xFE /* redzone for kmalloc_large allocations */
#ifndef arch_enable_tagging_async
#define arch_enable_tagging_async()
#endif
-#ifndef arch_init_tags
-#define arch_init_tags(max_tag)
-#endif
-#ifndef arch_set_tagging_report_once
-#define arch_set_tagging_report_once(state)
-#endif
#ifndef arch_force_async_tag_fault
#define arch_force_async_tag_fault()
#endif
#define hw_enable_tagging_sync() arch_enable_tagging_sync()
#define hw_enable_tagging_async() arch_enable_tagging_async()
-#define hw_init_tags(max_tag) arch_init_tags(max_tag)
-#define hw_set_tagging_report_once(state) arch_set_tagging_report_once(state)
#define hw_force_async_tag_fault() arch_force_async_tag_fault()
#define hw_get_random_tag() arch_get_random_tag()
#define hw_get_mem_tag(addr) arch_get_mem_tag(addr)
#define hw_enable_tagging_sync()
#define hw_enable_tagging_async()
-#define hw_set_tagging_report_once(state)
#endif /* CONFIG_KASAN_HW_TAGS */
#if defined(CONFIG_KASAN_HW_TAGS) && IS_ENABLED(CONFIG_KASAN_KUNIT_TEST)
-void kasan_set_tagging_report_once(bool state);
void kasan_enable_tagging_sync(void);
void kasan_force_async_fault(void);
#else /* CONFIG_KASAN_HW_TAGS || CONFIG_KASAN_KUNIT_TEST */
-static inline void kasan_set_tagging_report_once(bool state) { }
static inline void kasan_enable_tagging_sync(void) { }
static inline void kasan_force_async_fault(void) { }
+ ((loff_t)vma->vm_pgoff << PAGE_SHIFT);
/*
- * Filesystem's fallocate may need to take i_mutex. We need to
+ * Filesystem's fallocate may need to take i_rwsem. We need to
* explicitly grab a reference because the vma (and hence the
* vma's reference to the file) can go away as soon as we drop
* mmap_lock.
switch (behavior) {
case MADV_COLD:
case MADV_PAGEOUT:
+ case MADV_WILLNEED:
return true;
default:
return false;
* Return:
* Found address on success, 0 on failure.
*/
- phys_addr_t __init_memblock memblock_find_in_range(phys_addr_t start,
+ static phys_addr_t __init_memblock memblock_find_in_range(phys_addr_t start,
phys_addr_t end, phys_addr_t size,
phys_addr_t align)
{
int __init_memblock memblock_add_node(phys_addr_t base, phys_addr_t size,
int nid)
{
+ phys_addr_t end = base + size - 1;
+
+ memblock_dbg("%s: [%pa-%pa] nid=%d %pS\n", __func__,
+ &base, &end, nid, (void *)_RET_IP_);
+
return memblock_add_range(&memblock.memory, base, size, nid, 0);
}
phys_addr_t min_addr, phys_addr_t max_addr,
int nid)
{
- void *ptr;
-
memblock_dbg("%s: %llu bytes align=0x%llx nid=%d from=%pa max_addr=%pa %pS\n",
__func__, (u64)size, (u64)align, nid, &min_addr,
&max_addr, (void *)_RET_IP_);
- ptr = memblock_alloc_internal(size, align,
- min_addr, max_addr, nid, true);
- if (ptr && size > 0)
- page_init_poison(ptr, size);
-
- return ptr;
+ return memblock_alloc_internal(size, align, min_addr, max_addr, nid,
+ true);
}
/**
phys_addr_t min_addr, phys_addr_t max_addr,
int nid)
{
- void *ptr;
-
memblock_dbg("%s: %llu bytes align=0x%llx nid=%d from=%pa max_addr=%pa %pS\n",
__func__, (u64)size, (u64)align, nid, &min_addr,
&max_addr, (void *)_RET_IP_);
- ptr = memblock_alloc_internal(size, align,
- min_addr, max_addr, nid, false);
- if (ptr && size > 0)
- page_init_poison(ptr, size);
-
- return ptr;
+ return memblock_alloc_internal(size, align, min_addr, max_addr, nid,
+ false);
}
/**
if (!size)
return;
+ if (memblock.memory.cnt <= 1) {
+ pr_warn("%s: No memory registered yet\n", __func__);
+ return;
+ }
+
ret = memblock_isolate_range(&memblock.memory, base, size,
&start_rgn, &end_rgn);
if (ret)
return !cgroup_subsys_on_dfl(memory_cgrp_subsys) && !cgroup_memory_noswap;
}
+ /* memcg and lruvec stats flushing */
+ static void flush_memcg_stats_dwork(struct work_struct *w);
+ static DECLARE_DEFERRABLE_WORK(stats_flush_dwork, flush_memcg_stats_dwork);
+ static void flush_memcg_stats_work(struct work_struct *w);
+ static DECLARE_WORK(stats_flush_work, flush_memcg_stats_work);
+ static DEFINE_PER_CPU(unsigned int, stats_flush_threshold);
+ static DEFINE_SPINLOCK(stats_flush_lock);
+
#define THRESHOLDS_EVENTS_TARGET 128
#define SOFTLIMIT_EVENTS_TARGET 1024
return &memcg->vmpressure;
}
- struct cgroup_subsys_state *vmpressure_to_css(struct vmpressure *vmpr)
+ struct mem_cgroup *vmpressure_to_memcg(struct vmpressure *vmpr)
{
- return &container_of(vmpr, struct mem_cgroup, vmpressure)->css;
+ return container_of(vmpr, struct mem_cgroup, vmpressure);
}
#ifdef CONFIG_MEMCG_KMEM
cgroup_rstat_updated(memcg->css.cgroup, smp_processor_id());
}
- /* idx can be of type enum memcg_stat_item or node_stat_item. */
- static unsigned long memcg_page_state(struct mem_cgroup *memcg, int idx)
- {
- long x = READ_ONCE(memcg->vmstats.state[idx]);
- #ifdef CONFIG_SMP
- if (x < 0)
- x = 0;
- #endif
- return x;
- }
-
/* idx can be of type enum memcg_stat_item or node_stat_item. */
static unsigned long memcg_page_state_local(struct mem_cgroup *memcg, int idx)
{
return x;
}
- static struct mem_cgroup_per_node *
- parent_nodeinfo(struct mem_cgroup_per_node *pn, int nid)
- {
- struct mem_cgroup *parent;
-
- parent = parent_mem_cgroup(pn->memcg);
- if (!parent)
- return NULL;
- return parent->nodeinfo[nid];
- }
-
void __mod_memcg_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx,
int val)
{
struct mem_cgroup_per_node *pn;
struct mem_cgroup *memcg;
- long x, threshold = MEMCG_CHARGE_BATCH;
pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
memcg = pn->memcg;
__mod_memcg_state(memcg, idx, val);
/* Update lruvec */
- __this_cpu_add(pn->lruvec_stat_local->count[idx], val);
-
- if (vmstat_item_in_bytes(idx))
- threshold <<= PAGE_SHIFT;
-
- x = val + __this_cpu_read(pn->lruvec_stat_cpu->count[idx]);
- if (unlikely(abs(x) > threshold)) {
- pg_data_t *pgdat = lruvec_pgdat(lruvec);
- struct mem_cgroup_per_node *pi;
-
- for (pi = pn; pi; pi = parent_nodeinfo(pi, pgdat->node_id))
- atomic_long_add(x, &pi->lruvec_stat[idx]);
- x = 0;
- }
- __this_cpu_write(pn->lruvec_stat_cpu->count[idx], x);
+ __this_cpu_add(pn->lruvec_stats_percpu->state[idx], val);
+ if (!(__this_cpu_inc_return(stats_flush_threshold) % MEMCG_CHARGE_BATCH))
+ queue_work(system_unbound_wq, &stats_flush_work);
}
/**
static __always_inline struct mem_cgroup *active_memcg(void)
{
- if (in_interrupt())
+ if (!in_task())
return this_cpu_read(int_active_memcg);
else
return current->active_memcg;
return false;
/* Memcg to charge can't be determined. */
- if (in_interrupt() || !current->mm || (current->flags & PF_KTHREAD))
+ if (!in_task() || !current->mm || (current->flags & PF_KTHREAD))
return true;
return false;
unsigned long flags;
/*
- * The only protection from memory hotplug vs. drain_stock races is
- * that we always operate on local CPU stock here with IRQ disabled
+ * The only protection from cpu hotplug (memcg_hotplug_cpu_dead) vs.
+ * drain_stock races is that we always operate on local CPU stock
+ * here with IRQ disabled
*/
local_irq_save(flags);
if (memcg && stock->nr_pages &&
mem_cgroup_is_descendant(memcg, root_memcg))
flush = true;
- if (obj_stock_flush_required(stock, root_memcg))
+ else if (obj_stock_flush_required(stock, root_memcg))
flush = true;
rcu_read_unlock();
mutex_unlock(&percpu_charge_mutex);
}
- static void memcg_flush_lruvec_page_state(struct mem_cgroup *memcg, int cpu)
- {
- int nid;
-
- for_each_node(nid) {
- struct mem_cgroup_per_node *pn = memcg->nodeinfo[nid];
- unsigned long stat[NR_VM_NODE_STAT_ITEMS];
- struct batched_lruvec_stat *lstatc;
- int i;
-
- lstatc = per_cpu_ptr(pn->lruvec_stat_cpu, cpu);
- for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++) {
- stat[i] = lstatc->count[i];
- lstatc->count[i] = 0;
- }
-
- do {
- for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++)
- atomic_long_add(stat[i], &pn->lruvec_stat[i]);
- } while ((pn = parent_nodeinfo(pn, nid)));
- }
- }
-
static int memcg_hotplug_cpu_dead(unsigned int cpu)
{
struct memcg_stock_pcp *stock;
- struct mem_cgroup *memcg;
stock = &per_cpu(memcg_stock, cpu);
drain_stock(stock);
- for_each_mem_cgroup(memcg)
- memcg_flush_lruvec_page_state(memcg, cpu);
-
return 0;
}
{
struct mem_cgroup *memcg = mem_cgroup_from_css(css);
- if (val > 100)
+ if (val > 200)
return -EINVAL;
if (!mem_cgroup_is_root(memcg))
atomic_read(&frn->done.cnt) == 1) {
frn->at = 0;
trace_flush_foreign(wb, frn->bdi_id, frn->memcg_id);
- cgroup_writeback_by_id(frn->bdi_id, frn->memcg_id, 0,
+ cgroup_writeback_by_id(frn->bdi_id, frn->memcg_id,
WB_REASON_FOREIGN_FLUSH,
&frn->done);
}
vfs_poll(efile.file, &event->pt);
- spin_lock(&memcg->event_list_lock);
+ spin_lock_irq(&memcg->event_list_lock);
list_add(&event->list, &memcg->event_list);
- spin_unlock(&memcg->event_list_lock);
+ spin_unlock_irq(&memcg->event_list_lock);
fdput(cfile);
fdput(efile);
if (!pn)
return 1;
- pn->lruvec_stat_local = alloc_percpu_gfp(struct lruvec_stat,
- GFP_KERNEL_ACCOUNT);
- if (!pn->lruvec_stat_local) {
- kfree(pn);
- return 1;
- }
-
- pn->lruvec_stat_cpu = alloc_percpu_gfp(struct batched_lruvec_stat,
- GFP_KERNEL_ACCOUNT);
- if (!pn->lruvec_stat_cpu) {
- free_percpu(pn->lruvec_stat_local);
+ pn->lruvec_stats_percpu = alloc_percpu_gfp(struct lruvec_stats_percpu,
+ GFP_KERNEL_ACCOUNT);
+ if (!pn->lruvec_stats_percpu) {
kfree(pn);
return 1;
}
if (!pn)
return;
- free_percpu(pn->lruvec_stat_cpu);
- free_percpu(pn->lruvec_stat_local);
+ free_percpu(pn->lruvec_stats_percpu);
kfree(pn);
}
static void mem_cgroup_free(struct mem_cgroup *memcg)
{
- int cpu;
-
memcg_wb_domain_exit(memcg);
- /*
- * Flush percpu lruvec stats to guarantee the value
- * correctness on parent's and all ancestor levels.
- */
- for_each_online_cpu(cpu)
- memcg_flush_lruvec_page_state(memcg, cpu);
__mem_cgroup_free(memcg);
}
/* Online state pins memcg ID, memcg ID pins CSS */
refcount_set(&memcg->id.ref, 1);
css_get(css);
+
+ if (unlikely(mem_cgroup_is_root(memcg)))
+ queue_delayed_work(system_unbound_wq, &stats_flush_dwork,
+ 2UL*HZ);
return 0;
}
* Notify userspace about cgroup removing only after rmdir of cgroup
* directory to avoid race between userspace and kernelspace.
*/
- spin_lock(&memcg->event_list_lock);
+ spin_lock_irq(&memcg->event_list_lock);
list_for_each_entry_safe(event, tmp, &memcg->event_list, list) {
list_del_init(&event->list);
schedule_work(&event->remove);
}
- spin_unlock(&memcg->event_list_lock);
+ spin_unlock_irq(&memcg->event_list_lock);
page_counter_set_min(&memcg->memory, 0);
page_counter_set_low(&memcg->memory, 0);
memcg_wb_domain_size_changed(memcg);
}
+ void mem_cgroup_flush_stats(void)
+ {
+ if (!spin_trylock(&stats_flush_lock))
+ return;
+
+ cgroup_rstat_flush_irqsafe(root_mem_cgroup->css.cgroup);
+ spin_unlock(&stats_flush_lock);
+ }
+
+ static void flush_memcg_stats_dwork(struct work_struct *w)
+ {
+ mem_cgroup_flush_stats();
+ queue_delayed_work(system_unbound_wq, &stats_flush_dwork, 2UL*HZ);
+ }
+
+ static void flush_memcg_stats_work(struct work_struct *w)
+ {
+ mem_cgroup_flush_stats();
+ }
+
static void mem_cgroup_css_rstat_flush(struct cgroup_subsys_state *css, int cpu)
{
struct mem_cgroup *memcg = mem_cgroup_from_css(css);
struct mem_cgroup *parent = parent_mem_cgroup(memcg);
struct memcg_vmstats_percpu *statc;
long delta, v;
- int i;
+ int i, nid;
statc = per_cpu_ptr(memcg->vmstats_percpu, cpu);
if (parent)
parent->vmstats.events_pending[i] += delta;
}
+
+ for_each_node_state(nid, N_MEMORY) {
+ struct mem_cgroup_per_node *pn = memcg->nodeinfo[nid];
+ struct mem_cgroup_per_node *ppn = NULL;
+ struct lruvec_stats_percpu *lstatc;
+
+ if (parent)
+ ppn = parent->nodeinfo[nid];
+
+ lstatc = per_cpu_ptr(pn->lruvec_stats_percpu, cpu);
+
+ for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++) {
+ delta = pn->lruvec_stats.state_pending[i];
+ if (delta)
+ pn->lruvec_stats.state_pending[i] = 0;
+
+ v = READ_ONCE(lstatc->state[i]);
+ if (v != lstatc->state_prev[i]) {
+ delta += v - lstatc->state_prev[i];
+ lstatc->state_prev[i] = v;
+ }
+
+ if (!delta)
+ continue;
+
+ pn->lruvec_stats.state[i] += delta;
+ if (ppn)
+ ppn->lruvec_stats.state_pending[i] += delta;
+ }
+ }
}
#ifdef CONFIG_MMU
int i;
struct mem_cgroup *memcg = mem_cgroup_from_seq(m);
+ cgroup_rstat_flush(memcg->css.cgroup);
+
for (i = 0; i < ARRAY_SIZE(memory_stats); i++) {
int nid;
atomic_long_read(&parent->memory.children_low_usage)));
}
- static int __mem_cgroup_charge(struct page *page, struct mem_cgroup *memcg,
- gfp_t gfp)
+ static int charge_memcg(struct page *page, struct mem_cgroup *memcg, gfp_t gfp)
{
unsigned int nr_pages = thp_nr_pages(page);
int ret;
}
/**
- * mem_cgroup_charge - charge a newly allocated page to a cgroup
+ * __mem_cgroup_charge - charge a newly allocated page to a cgroup
* @page: page to charge
* @mm: mm context of the victim
* @gfp_mask: reclaim mode
*
* Returns 0 on success. Otherwise, an error code is returned.
*/
- int mem_cgroup_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask)
+ int __mem_cgroup_charge(struct page *page, struct mm_struct *mm,
+ gfp_t gfp_mask)
{
struct mem_cgroup *memcg;
int ret;
- if (mem_cgroup_disabled())
- return 0;
-
memcg = get_mem_cgroup_from_mm(mm);
- ret = __mem_cgroup_charge(page, memcg, gfp_mask);
+ ret = charge_memcg(page, memcg, gfp_mask);
css_put(&memcg->css);
return ret;
memcg = get_mem_cgroup_from_mm(mm);
rcu_read_unlock();
- ret = __mem_cgroup_charge(page, memcg, gfp);
+ ret = charge_memcg(page, memcg, gfp);
css_put(&memcg->css);
return ret;
}
/**
- * mem_cgroup_uncharge - uncharge a page
+ * __mem_cgroup_uncharge - uncharge a page
* @page: page to uncharge
*
- * Uncharge a page previously charged with mem_cgroup_charge().
+ * Uncharge a page previously charged with __mem_cgroup_charge().
*/
- void mem_cgroup_uncharge(struct page *page)
+ void __mem_cgroup_uncharge(struct page *page)
{
struct uncharge_gather ug;
- if (mem_cgroup_disabled())
- return;
-
/* Don't touch page->lru of any random page, pre-check: */
if (!page_memcg(page))
return;
}
/**
- * mem_cgroup_uncharge_list - uncharge a list of page
+ * __mem_cgroup_uncharge_list - uncharge a list of page
* @page_list: list of pages to uncharge
*
* Uncharge a list of pages previously charged with
- * mem_cgroup_charge().
+ * __mem_cgroup_charge().
*/
- void mem_cgroup_uncharge_list(struct list_head *page_list)
+ void __mem_cgroup_uncharge_list(struct list_head *page_list)
{
struct uncharge_gather ug;
struct page *page;
- if (mem_cgroup_disabled())
- return;
-
uncharge_gather_clear(&ug);
list_for_each_entry(page, page_list, lru)
uncharge_page(page, &ug);
* mem_cgroup_charge_skmem - charge socket memory
* @memcg: memcg to charge
* @nr_pages: number of pages to charge
+ * @gfp_mask: reclaim mode
*
* Charges @nr_pages to @memcg. Returns %true if the charge fit within
- * @memcg's configured limit, %false if the charge had to be forced.
+ * @memcg's configured limit, %false if it doesn't.
*/
-bool mem_cgroup_charge_skmem(struct mem_cgroup *memcg, unsigned int nr_pages)
+bool mem_cgroup_charge_skmem(struct mem_cgroup *memcg, unsigned int nr_pages,
+ gfp_t gfp_mask)
{
- gfp_t gfp_mask = GFP_KERNEL;
-
if (!cgroup_subsys_on_dfl(memory_cgrp_subsys)) {
struct page_counter *fail;
memcg->tcpmem_pressure = 0;
return true;
}
- page_counter_charge(&memcg->tcpmem, nr_pages);
memcg->tcpmem_pressure = 1;
+ if (gfp_mask & __GFP_NOFAIL) {
+ page_counter_charge(&memcg->tcpmem, nr_pages);
+ return true;
+ }
return false;
}
- /* Don't block in the packet receive path */
- if (in_softirq())
- gfp_mask = GFP_NOWAIT;
-
- mod_memcg_state(memcg, MEMCG_SOCK, nr_pages);
-
- if (try_charge(memcg, gfp_mask, nr_pages) == 0)
+ if (try_charge(memcg, gfp_mask, nr_pages) == 0) {
+ mod_memcg_state(memcg, MEMCG_SOCK, nr_pages);
return true;
+ }
- try_charge(memcg, gfp_mask|__GFP_NOFAIL, nr_pages);
return false;
}
}
/**
- * mem_cgroup_try_charge_swap - try charging swap space for a page
+ * __mem_cgroup_try_charge_swap - try charging swap space for a page
* @page: page being added to swap
* @entry: swap entry to charge
*
*
* Returns 0 on success, -ENOMEM on failure.
*/
- int mem_cgroup_try_charge_swap(struct page *page, swp_entry_t entry)
+ int __mem_cgroup_try_charge_swap(struct page *page, swp_entry_t entry)
{
unsigned int nr_pages = thp_nr_pages(page);
struct page_counter *counter;
struct mem_cgroup *memcg;
unsigned short oldid;
- if (mem_cgroup_disabled())
- return 0;
-
if (!cgroup_subsys_on_dfl(memory_cgrp_subsys))
return 0;
}
/**
- * mem_cgroup_uncharge_swap - uncharge swap space
+ * __mem_cgroup_uncharge_swap - uncharge swap space
* @entry: swap entry to uncharge
* @nr_pages: the amount of swap space to uncharge
*/
- void mem_cgroup_uncharge_swap(swp_entry_t entry, unsigned int nr_pages)
+ void __mem_cgroup_uncharge_swap(swp_entry_t entry, unsigned int nr_pages)
{
struct mem_cgroup *memcg;
unsigned short id;
static bool __page_handle_poison(struct page *page)
{
- bool ret;
+ int ret;
zone_pcp_disable(page_zone(page));
ret = dissolve_free_huge_page(page);
ret = take_page_off_buddy(page);
zone_pcp_enable(page_zone(page));
- return ret;
+ return ret > 0;
}
static bool page_handle_poison(struct page *page, bool hugepage_or_freepage, bool release)
/*
* Unknown page type encountered. Try to check whether it can turn PageLRU by
- * lru_add_drain_all, or a free page by reclaiming slabs when possible.
+ * lru_add_drain_all.
*/
- void shake_page(struct page *p, int access)
+ void shake_page(struct page *p)
{
if (PageHuge(p))
return;
}
/*
- * Only call shrink_node_slabs here (which would also shrink
- * other caches) if access is not potentially fatal.
+ * TODO: Could shrink slab caches here if a lightweight range-based
+ * shrinker will be available.
*/
- if (access)
- drop_slab_node(page_to_nid(p));
}
EXPORT_SYMBOL_GPL(shake_page);
/*
* Kill the processes that have been collected earlier.
*
- * Only do anything when DOIT is set, otherwise just free the list
- * (this is used for clean pages which do not need killing)
+ * Only do anything when FORCEKILL is set, otherwise just free the
+ * list (this is used for clean pages which do not need killing)
* Also when FAIL is set do a force kill because something went
* wrong earlier.
*/
{
struct hwp_walk *hwp = (struct hwp_walk *)walk->private;
int ret = 0;
- pte_t *ptep;
+ pte_t *ptep, *mapped_pte;
spinlock_t *ptl;
ptl = pmd_trans_huge_lock(pmdp, walk->vma);
if (pmd_trans_unstable(pmdp))
goto out;
- ptep = pte_offset_map_lock(walk->vma->vm_mm, pmdp, addr, &ptl);
+ mapped_pte = ptep = pte_offset_map_lock(walk->vma->vm_mm, pmdp,
+ addr, &ptl);
for (; addr != end; ptep++, addr += PAGE_SIZE) {
ret = check_hwpoisoned_entry(*ptep, addr, PAGE_SHIFT,
hwp->pfn, &hwp->tk);
if (ret == 1)
break;
}
- pte_unmap_unlock(ptep - 1, ptl);
+ pte_unmap_unlock(mapped_pte, ptl);
out:
cond_resched();
return ret;
/*
* Truncation is a bit tricky. Enable it per file system for now.
*
- * Open: to take i_mutex or not for this? Right now we don't.
+ * Open: to take i_rwsem or not for this? Right now we don't.
*/
ret = truncate_error_page(p, pfn, mapping);
out:
* page, retry.
*/
if (pass++ < 3) {
- shake_page(p, 1);
+ shake_page(p);
goto try_again;
}
ret = -EIO;
*/
if (pass++ < 3) {
put_page(p);
- shake_page(p, 1);
+ shake_page(p);
count_increased = false;
goto try_again;
}
ret = -EIO;
}
out:
+ if (ret == -EIO)
+ dump_page(p, "hwpoison: unhandlable page");
+
return ret;
}
* the pages and send SIGBUS to the processes if the data was dirty.
*/
static bool hwpoison_user_mappings(struct page *p, unsigned long pfn,
- int flags, struct page **hpagep)
+ int flags, struct page *hpage)
{
enum ttu_flags ttu = TTU_IGNORE_MLOCK | TTU_SYNC;
struct address_space *mapping;
LIST_HEAD(tokill);
bool unmap_success;
int kill = 1, forcekill;
- struct page *hpage = *hpagep;
bool mlocked = PageMlocked(hpage);
/*
* shake_page() again to ensure that it's flushed.
*/
if (mlocked)
- shake_page(hpage, 0);
+ shake_page(hpage);
/*
* Now that the dirty bit has been propagated to the
goto out;
}
- if (!hwpoison_user_mappings(p, pfn, flags, &head)) {
+ if (!hwpoison_user_mappings(p, pfn, flags, head)) {
action_result(pfn, MF_MSG_UNMAP_FAILED, MF_IGNORED);
res = -EBUSY;
goto out;
struct dev_pagemap *pgmap)
{
struct page *page = pfn_to_page(pfn);
- const bool unmap_success = true;
unsigned long size = 0;
struct to_kill *tk;
LIST_HEAD(tokill);
start = (page->index << PAGE_SHIFT) & ~(size - 1);
unmap_mapping_range(page->mapping, start, size, 0);
}
- kill_procs(&tokill, flags & MF_MUST_KILL, !unmap_success, pfn, flags);
+ kill_procs(&tokill, flags & MF_MUST_KILL, false, pfn, flags);
rc = 0;
unlock:
dax_unlock_page(page, cookie);
* The check (unnecessarily) ignores LRU pages being isolated and
* walked by the page reclaim code, however that's not a big loss.
*/
- shake_page(p, 0);
+ shake_page(p);
lock_page(p);
* Now take care of user space mappings.
* Abort on fail: __delete_from_page_cache() assumes unmapped page.
*/
- if (!hwpoison_user_mappings(p, pfn, flags, &p)) {
+ if (!hwpoison_user_mappings(p, pfn, flags, p)) {
action_result(pfn, MF_MSG_UNMAP_FAILED, MF_IGNORED);
res = -EBUSY;
goto unlock_page;
if (isolate_page(hpage, &pagelist)) {
ret = migrate_pages(&pagelist, alloc_migration_target, NULL,
- (unsigned long)&mtc, MIGRATE_SYNC, MR_MEMORY_FAILURE);
+ (unsigned long)&mtc, MIGRATE_SYNC, MR_MEMORY_FAILURE, NULL);
if (!ret) {
bool release = !huge;
try_again = false;
goto retry;
}
- } else if (ret == -EIO) {
- pr_info("%s: %#lx: unknown page type: %lx (%pGp)\n",
- __func__, pfn, page->flags, &page->flags);
}
return ret;
{
struct rb_node **__rb_link, *__rb_parent, *rb_prev;
+ mmap_assert_locked(mm);
__rb_link = &mm->mm_rb.rb_node;
rb_prev = __rb_parent = NULL;
if (IS_APPEND(inode) && (file->f_mode & FMODE_WRITE))
return -EACCES;
- /*
- * Make sure there are no mandatory locks on the file.
- */
- if (locks_verify_locked(file))
- return -EAGAIN;
-
vm_flags |= VM_SHARED | VM_MAYSHARE;
if (!(file->f_mode & FMODE_WRITE))
vm_flags &= ~(VM_MAYWRITE | VM_SHARED);
struct rb_node *rb_node;
struct vm_area_struct *vma;
+ mmap_assert_locked(mm);
/* Check the cache first. */
vma = vmacache_find(mm, addr);
if (likely(vma))
if (mmap_write_lock_killable(mm))
return -EINTR;
- vma = find_vma(mm, start);
+ vma = vma_lookup(mm, start);
if (!vma || !(vma->vm_flags & VM_SHARED))
goto out;
- if (start < vma->vm_start)
- goto out;
-
if (start + size > vma->vm_end) {
struct vm_area_struct *next;
static void wb_min_max_ratio(struct bdi_writeback *wb,
unsigned long *minp, unsigned long *maxp)
{
- unsigned long this_bw = wb->avg_write_bandwidth;
+ unsigned long this_bw = READ_ONCE(wb->avg_write_bandwidth);
unsigned long tot_bw = atomic_long_read(&wb->bdi->tot_write_bandwidth);
unsigned long long min = wb->bdi->min_ratio;
unsigned long long max = wb->bdi->max_ratio;
static void wb_position_ratio(struct dirty_throttle_control *dtc)
{
struct bdi_writeback *wb = dtc->wb;
- unsigned long write_bw = wb->avg_write_bandwidth;
+ unsigned long write_bw = READ_ONCE(wb->avg_write_bandwidth);
unsigned long freerun = dirty_freerun_ceiling(dtc->thresh, dtc->bg_thresh);
unsigned long limit = hard_dirty_limit(dtc_dom(dtc), dtc->thresh);
unsigned long wb_thresh = dtc->wb_thresh;
&wb->bdi->tot_write_bandwidth) <= 0);
}
wb->write_bandwidth = bw;
- wb->avg_write_bandwidth = avg;
+ WRITE_ONCE(wb->avg_write_bandwidth, avg);
}
static void update_dirty_limit(struct dirty_throttle_control *dtc)
dom->dirty_limit = limit;
}
- static void domain_update_bandwidth(struct dirty_throttle_control *dtc,
- unsigned long now)
+ static void domain_update_dirty_limit(struct dirty_throttle_control *dtc,
+ unsigned long now)
{
struct wb_domain *dom = dtc_dom(dtc);
else
dirty_ratelimit -= step;
- wb->dirty_ratelimit = max(dirty_ratelimit, 1UL);
+ WRITE_ONCE(wb->dirty_ratelimit, max(dirty_ratelimit, 1UL));
wb->balanced_dirty_ratelimit = balanced_dirty_ratelimit;
trace_bdi_dirty_ratelimit(wb, dirty_rate, task_ratelimit);
static void __wb_update_bandwidth(struct dirty_throttle_control *gdtc,
struct dirty_throttle_control *mdtc,
- unsigned long start_time,
bool update_ratelimit)
{
struct bdi_writeback *wb = gdtc->wb;
unsigned long now = jiffies;
- unsigned long elapsed = now - wb->bw_time_stamp;
+ unsigned long elapsed;
unsigned long dirtied;
unsigned long written;
- lockdep_assert_held(&wb->list_lock);
+ spin_lock(&wb->list_lock);
/*
- * rate-limit, only update once every 200ms.
+ * Lockless checks for elapsed time are racy and delayed update after
+ * IO completion doesn't do it at all (to make sure written pages are
+ * accounted reasonably quickly). Make sure elapsed >= 1 to avoid
+ * division errors.
*/
- if (elapsed < BANDWIDTH_INTERVAL)
- return;
-
+ elapsed = max(now - wb->bw_time_stamp, 1UL);
dirtied = percpu_counter_read(&wb->stat[WB_DIRTIED]);
written = percpu_counter_read(&wb->stat[WB_WRITTEN]);
- /*
- * Skip quiet periods when disk bandwidth is under-utilized.
- * (at least 1s idle time between two flusher runs)
- */
- if (elapsed > HZ && time_before(wb->bw_time_stamp, start_time))
- goto snapshot;
-
if (update_ratelimit) {
- domain_update_bandwidth(gdtc, now);
+ domain_update_dirty_limit(gdtc, now);
wb_update_dirty_ratelimit(gdtc, dirtied, elapsed);
/*
* compiler has no way to figure that out. Help it.
*/
if (IS_ENABLED(CONFIG_CGROUP_WRITEBACK) && mdtc) {
- domain_update_bandwidth(mdtc, now);
+ domain_update_dirty_limit(mdtc, now);
wb_update_dirty_ratelimit(mdtc, dirtied, elapsed);
}
}
wb_update_write_bandwidth(wb, elapsed, written);
- snapshot:
wb->dirtied_stamp = dirtied;
wb->written_stamp = written;
- wb->bw_time_stamp = now;
+ WRITE_ONCE(wb->bw_time_stamp, now);
+ spin_unlock(&wb->list_lock);
}
- void wb_update_bandwidth(struct bdi_writeback *wb, unsigned long start_time)
+ void wb_update_bandwidth(struct bdi_writeback *wb)
{
struct dirty_throttle_control gdtc = { GDTC_INIT(wb) };
- __wb_update_bandwidth(&gdtc, NULL, start_time, false);
+ __wb_update_bandwidth(&gdtc, NULL, false);
+ }
+
+ /* Interval after which we consider wb idle and don't estimate bandwidth */
+ #define WB_BANDWIDTH_IDLE_JIF (HZ)
+
+ static void wb_bandwidth_estimate_start(struct bdi_writeback *wb)
+ {
+ unsigned long now = jiffies;
+ unsigned long elapsed = now - READ_ONCE(wb->bw_time_stamp);
+
+ if (elapsed > WB_BANDWIDTH_IDLE_JIF &&
+ !atomic_read(&wb->writeback_inodes)) {
+ spin_lock(&wb->list_lock);
+ wb->dirtied_stamp = wb_stat(wb, WB_DIRTIED);
+ wb->written_stamp = wb_stat(wb, WB_WRITTEN);
+ WRITE_ONCE(wb->bw_time_stamp, now);
+ spin_unlock(&wb->list_lock);
+ }
}
/*
static unsigned long wb_max_pause(struct bdi_writeback *wb,
unsigned long wb_dirty)
{
- unsigned long bw = wb->avg_write_bandwidth;
+ unsigned long bw = READ_ONCE(wb->avg_write_bandwidth);
unsigned long t;
/*
unsigned long dirty_ratelimit,
int *nr_dirtied_pause)
{
- long hi = ilog2(wb->avg_write_bandwidth);
- long lo = ilog2(wb->dirty_ratelimit);
+ long hi = ilog2(READ_ONCE(wb->avg_write_bandwidth));
+ long lo = ilog2(READ_ONCE(wb->dirty_ratelimit));
long t; /* target pause */
long pause; /* estimated next pause */
int pages; /* target nr_dirtied_pause */
if (dirty_exceeded && !wb->dirty_exceeded)
wb->dirty_exceeded = 1;
- if (time_is_before_jiffies(wb->bw_time_stamp +
- BANDWIDTH_INTERVAL)) {
- spin_lock(&wb->list_lock);
- __wb_update_bandwidth(gdtc, mdtc, start_time, true);
- spin_unlock(&wb->list_lock);
- }
+ if (time_is_before_jiffies(READ_ONCE(wb->bw_time_stamp) +
+ BANDWIDTH_INTERVAL))
+ __wb_update_bandwidth(gdtc, mdtc, true);
/* throttle according to the chosen dtc */
- dirty_ratelimit = wb->dirty_ratelimit;
+ dirty_ratelimit = READ_ONCE(wb->dirty_ratelimit);
task_ratelimit = ((u64)dirty_ratelimit * sdtc->pos_ratio) >>
RATELIMIT_CALC_SHIFT;
max_pause = wb_max_pause(wb, sdtc->wb_dirty);
return ret;
}
-#ifdef CONFIG_BLOCK
void laptop_mode_timer_fn(struct timer_list *t)
{
struct backing_dev_info *backing_dev_info =
rcu_read_unlock();
}
-#endif
/*
* If ratelimit_pages is too high then we can get into dirty-data overload
int do_writepages(struct address_space *mapping, struct writeback_control *wbc)
{
int ret;
+ struct bdi_writeback *wb;
if (wbc->nr_to_write <= 0)
return 0;
+ wb = inode_to_wb_wbc(mapping->host, wbc);
+ wb_bandwidth_estimate_start(wb);
while (1) {
if (mapping->a_ops->writepages)
ret = mapping->a_ops->writepages(mapping, wbc);
cond_resched();
congestion_wait(BLK_RW_ASYNC, HZ/50);
}
+ /*
+ * Usually few pages are written by now from those we've just submitted
+ * but if there's constant writeback being submitted, this makes sure
+ * writeback bandwidth is updated once in a while.
+ */
+ if (time_is_before_jiffies(READ_ONCE(wb->bw_time_stamp) +
+ BANDWIDTH_INTERVAL))
+ wb_update_bandwidth(wb);
return ret;
}
}
EXPORT_SYMBOL(clear_page_dirty_for_io);
+ static void wb_inode_writeback_start(struct bdi_writeback *wb)
+ {
+ atomic_inc(&wb->writeback_inodes);
+ }
+
+ static void wb_inode_writeback_end(struct bdi_writeback *wb)
+ {
+ atomic_dec(&wb->writeback_inodes);
+ /*
+ * Make sure estimate of writeback throughput gets updated after
+ * writeback completed. We delay the update by BANDWIDTH_INTERVAL
+ * (which is the interval other bandwidth updates use for batching) so
+ * that if multiple inodes end writeback at a similar time, they get
+ * batched into one bandwidth update.
+ */
+ queue_delayed_work(bdi_wq, &wb->bw_dwork, BANDWIDTH_INTERVAL);
+ }
+
int test_clear_page_writeback(struct page *page)
{
struct address_space *mapping = page_mapping(page);
dec_wb_stat(wb, WB_WRITEBACK);
__wb_writeout_inc(wb);
+ if (!mapping_tagged(mapping,
+ PAGECACHE_TAG_WRITEBACK))
+ wb_inode_writeback_end(wb);
}
}
PAGECACHE_TAG_WRITEBACK);
xas_set_mark(&xas, PAGECACHE_TAG_WRITEBACK);
- if (bdi->capabilities & BDI_CAP_WRITEBACK_ACCT)
- inc_wb_stat(inode_to_wb(inode), WB_WRITEBACK);
+ if (bdi->capabilities & BDI_CAP_WRITEBACK_ACCT) {
+ struct bdi_writeback *wb = inode_to_wb(inode);
+
+ inc_wb_stat(wb, WB_WRITEBACK);
+ if (!on_wblist)
+ wb_inode_writeback_start(wb);
+ }
/*
* We can come through here when swapping anonymous
#include <linux/hugetlb.h>
#include <linux/frontswap.h>
#include <linux/fs_parser.h>
-
- #include <asm/tlbflush.h> /* for arch/microblaze update_mmu_cache() */
+ #include <linux/swapfile.h>
static struct vfsmount *shm_mnt;
/*
* shmem_fallocate communicates with shmem_fault or shmem_writepage via
- * inode->i_private (with i_mutex making sure that it has only one user at
+ * inode->i_private (with i_rwsem making sure that it has only one user at
* a time): we would prefer not to enlarge the shmem inode just for that.
*/
struct shmem_falloc {
}
#endif
- static bool shmem_should_replace_page(struct page *page, gfp_t gfp);
- static int shmem_replace_page(struct page **pagep, gfp_t gfp,
- struct shmem_inode_info *info, pgoff_t index);
static int shmem_swapin_page(struct inode *inode, pgoff_t index,
struct page **pagep, enum sgp_type sgp,
gfp_t gfp, struct vm_area_struct *vma,
ino_t ino;
if (!(sb->s_flags & SB_KERNMOUNT)) {
- spin_lock(&sbinfo->stat_lock);
+ raw_spin_lock(&sbinfo->stat_lock);
if (sbinfo->max_inodes) {
if (!sbinfo->free_inodes) {
- spin_unlock(&sbinfo->stat_lock);
+ raw_spin_unlock(&sbinfo->stat_lock);
return -ENOSPC;
}
sbinfo->free_inodes--;
}
*inop = ino;
}
- spin_unlock(&sbinfo->stat_lock);
+ raw_spin_unlock(&sbinfo->stat_lock);
} else if (inop) {
/*
* __shmem_file_setup, one of our callers, is lock-free: it
* to worry about things like glibc compatibility.
*/
ino_t *next_ino;
+
next_ino = per_cpu_ptr(sbinfo->ino_batch, get_cpu());
ino = *next_ino;
if (unlikely(ino % SHMEM_INO_BATCH == 0)) {
- spin_lock(&sbinfo->stat_lock);
+ raw_spin_lock(&sbinfo->stat_lock);
ino = sbinfo->next_ino;
sbinfo->next_ino += SHMEM_INO_BATCH;
- spin_unlock(&sbinfo->stat_lock);
+ raw_spin_unlock(&sbinfo->stat_lock);
if (unlikely(is_zero_ino(ino)))
ino++;
}
{
struct shmem_sb_info *sbinfo = SHMEM_SB(sb);
if (sbinfo->max_inodes) {
- spin_lock(&sbinfo->stat_lock);
+ raw_spin_lock(&sbinfo->stat_lock);
sbinfo->free_inodes++;
- spin_unlock(&sbinfo->stat_lock);
+ raw_spin_unlock(&sbinfo->stat_lock);
}
}
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
/* ifdef here to avoid bloating shmem.o when not necessary */
- static int shmem_huge __read_mostly;
+ static int shmem_huge __read_mostly = SHMEM_HUGE_NEVER;
+
+ bool shmem_is_huge(struct vm_area_struct *vma,
+ struct inode *inode, pgoff_t index)
+ {
+ loff_t i_size;
+
+ if (shmem_huge == SHMEM_HUGE_DENY)
+ return false;
+ if (vma && ((vma->vm_flags & VM_NOHUGEPAGE) ||
+ test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags)))
+ return false;
+ if (shmem_huge == SHMEM_HUGE_FORCE)
+ return true;
+
+ switch (SHMEM_SB(inode->i_sb)->huge) {
+ case SHMEM_HUGE_ALWAYS:
+ return true;
+ case SHMEM_HUGE_WITHIN_SIZE:
+ index = round_up(index, HPAGE_PMD_NR);
+ i_size = round_up(i_size_read(inode), PAGE_SIZE);
+ if (i_size >= HPAGE_PMD_SIZE && (i_size >> PAGE_SHIFT) >= index)
+ return true;
+ fallthrough;
+ case SHMEM_HUGE_ADVISE:
+ if (vma && (vma->vm_flags & VM_HUGEPAGE))
+ return true;
+ fallthrough;
+ default:
+ return false;
+ }
+ }
#if defined(CONFIG_SYSFS)
static int shmem_parse_huge(const char *str)
#define shmem_huge SHMEM_HUGE_DENY
+ bool shmem_is_huge(struct vm_area_struct *vma,
+ struct inode *inode, pgoff_t index)
+ {
+ return false;
+ }
+
static unsigned long shmem_unused_huge_shrink(struct shmem_sb_info *sbinfo,
struct shrink_control *sc, unsigned long nr_to_split)
{
}
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
- static inline bool is_huge_enabled(struct shmem_sb_info *sbinfo)
- {
- if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) &&
- (shmem_huge == SHMEM_HUGE_FORCE || sbinfo->huge) &&
- shmem_huge != SHMEM_HUGE_DENY)
- return true;
- return false;
- }
-
/*
* Like add_to_page_cache_locked, but error if expected item has gone.
*/
* Determine (in bytes) how many of the shmem object's pages mapped by the
* given offsets are swapped out.
*
- * This is safe to call without i_mutex or the i_pages lock thanks to RCU,
+ * This is safe to call without i_rwsem or the i_pages lock thanks to RCU,
* as long as the inode doesn't go away and racy results are not a problem.
*/
unsigned long shmem_partial_swap_usage(struct address_space *mapping,
* Determine (in bytes) how many of the shmem object's pages mapped by the
* given vma is swapped out.
*
- * This is safe to call without i_mutex or the i_pages lock thanks to RCU,
+ * This is safe to call without i_rwsem or the i_pages lock thanks to RCU,
* as long as the inode doesn't go away and racy results are not a problem.
*/
unsigned long shmem_swap_usage(struct vm_area_struct *vma)
if (lend == -1)
end = -1; /* unsigned, so actually very big */
+ if (info->fallocend > start && info->fallocend <= end && !unfalloc)
+ info->fallocend = start;
+
pagevec_init(&pvec);
index = start;
while (index < end && find_lock_entries(mapping, index, end - 1,
{
struct inode *inode = path->dentry->d_inode;
struct shmem_inode_info *info = SHMEM_I(inode);
- struct shmem_sb_info *sb_info = SHMEM_SB(inode->i_sb);
if (info->alloced - info->swapped != inode->i_mapping->nrpages) {
spin_lock_irq(&info->lock);
}
generic_fillattr(&init_user_ns, inode, stat);
- if (is_huge_enabled(sb_info))
+ if (shmem_is_huge(NULL, inode, 0))
stat->blksize = HPAGE_PMD_SIZE;
return 0;
{
struct inode *inode = d_inode(dentry);
struct shmem_inode_info *info = SHMEM_I(inode);
- struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb);
int error;
error = setattr_prepare(&init_user_ns, dentry, attr);
loff_t oldsize = inode->i_size;
loff_t newsize = attr->ia_size;
- /* protected by i_mutex */
+ /* protected by i_rwsem */
if ((newsize < oldsize && (info->seals & F_SEAL_SHRINK)) ||
(newsize > oldsize && (info->seals & F_SEAL_GROW)))
return -EPERM;
if (oldsize > holebegin)
unmap_mapping_range(inode->i_mapping,
holebegin, 0, 1);
-
- /*
- * Part of the huge page can be beyond i_size: subject
- * to shrink under memory pressure.
- */
- if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) {
- spin_lock(&sbinfo->shrinklist_lock);
- /*
- * _careful to defend against unlocked access to
- * ->shrink_list in shmem_unused_huge_shrink()
- */
- if (list_empty_careful(&info->shrinklist)) {
- list_add_tail(&info->shrinklist,
- &sbinfo->shrinklist);
- sbinfo->shrinklist_len++;
- }
- spin_unlock(&sbinfo->shrinklist_lock);
- }
}
}
clear_inode(inode);
}
- extern struct swap_info_struct *swap_info[];
-
static int shmem_find_swap_entries(struct address_space *mapping,
pgoff_t start, unsigned int nr_entries,
struct page **entries, pgoff_t *indices,
swp_entry_t swap;
pgoff_t index;
- VM_BUG_ON_PAGE(PageCompound(page), page);
+ /*
+ * If /sys/kernel/mm/transparent_hugepage/shmem_enabled is "always" or
+ * "force", drivers/gpu/drm/i915/gem/i915_gem_shmem.c gets huge pages,
+ * and its shmem_writeback() needs them to be split when swapping.
+ */
+ if (PageTransCompound(page)) {
+ /* Ensure the subpages are still dirty */
+ SetPageDirty(page);
+ if (split_huge_page(page) < 0)
+ goto redirty;
+ ClearPageDirty(page);
+ }
+
BUG_ON(!PageLocked(page));
mapping = page->mapping;
index = page->index;
{
struct mempolicy *mpol = NULL;
if (sbinfo->mpol) {
- spin_lock(&sbinfo->stat_lock); /* prevent replace/use races */
+ raw_spin_lock(&sbinfo->stat_lock); /* prevent replace/use races */
mpol = sbinfo->mpol;
mpol_get(mpol);
- spin_unlock(&sbinfo->stat_lock);
+ raw_spin_unlock(&sbinfo->stat_lock);
}
return mpol;
}
struct shmem_sb_info *sbinfo;
struct mm_struct *charge_mm;
struct page *page;
- enum sgp_type sgp_huge = sgp;
pgoff_t hindex = index;
gfp_t huge_gfp;
int error;
if (index > (MAX_LFS_FILESIZE >> PAGE_SHIFT))
return -EFBIG;
- if (sgp == SGP_NOHUGE || sgp == SGP_HUGE)
- sgp = SGP_CACHE;
repeat:
if (sgp <= SGP_CACHE &&
((loff_t)index << PAGE_SHIFT) >= i_size_read(inode)) {
return error;
}
- if (page)
+ if (page) {
hindex = page->index;
- if (page && sgp == SGP_WRITE)
- mark_page_accessed(page);
-
- /* fallocated page? */
- if (page && !PageUptodate(page)) {
+ if (sgp == SGP_WRITE)
+ mark_page_accessed(page);
+ if (PageUptodate(page))
+ goto out;
+ /* fallocated page */
if (sgp != SGP_READ)
goto clear;
unlock_page(page);
put_page(page);
- page = NULL;
- hindex = index;
}
- if (page || sgp == SGP_READ)
- goto out;
/*
- * Fast cache lookup did not find it:
- * bring it back from swap or allocate.
+ * SGP_READ: succeed on hole, with NULL page, letting caller zero.
+ * SGP_NOALLOC: fail on hole, with NULL page, letting caller fail.
+ */
+ *pagep = NULL;
+ if (sgp == SGP_READ)
+ return 0;
+ if (sgp == SGP_NOALLOC)
+ return -ENOENT;
+
+ /*
+ * Fast cache lookup and swap lookup did not find it: allocate.
*/
if (vma && userfaultfd_missing(vma)) {
return 0;
}
- /* shmem_symlink() */
- if (!shmem_mapping(mapping))
- goto alloc_nohuge;
- if (shmem_huge == SHMEM_HUGE_DENY || sgp_huge == SGP_NOHUGE)
- goto alloc_nohuge;
- if (shmem_huge == SHMEM_HUGE_FORCE)
- goto alloc_huge;
- switch (sbinfo->huge) {
- case SHMEM_HUGE_NEVER:
+ /* Never use a huge page for shmem_symlink() */
+ if (S_ISLNK(inode->i_mode))
goto alloc_nohuge;
- case SHMEM_HUGE_WITHIN_SIZE: {
- loff_t i_size;
- pgoff_t off;
-
- off = round_up(index, HPAGE_PMD_NR);
- i_size = round_up(i_size_read(inode), PAGE_SIZE);
- if (i_size >= HPAGE_PMD_SIZE &&
- i_size >> PAGE_SHIFT >= off)
- goto alloc_huge;
-
- fallthrough;
- }
- case SHMEM_HUGE_ADVISE:
- if (sgp_huge == SGP_HUGE)
- goto alloc_huge;
- /* TODO: implement fadvise() hints */
+ if (!shmem_is_huge(vma, inode, index))
goto alloc_nohuge;
- }
- alloc_huge:
huge_gfp = vma_thp_gfp_mask(vma);
huge_gfp = limit_gfp_mask(huge_gfp, gfp);
page = shmem_alloc_and_acct_page(huge_gfp, inode, index, true);
struct vm_area_struct *vma = vmf->vma;
struct inode *inode = file_inode(vma->vm_file);
gfp_t gfp = mapping_gfp_mask(inode->i_mapping);
- enum sgp_type sgp;
int err;
vm_fault_t ret = VM_FAULT_LOCKED;
/*
* Trinity finds that probing a hole which tmpfs is punching can
* prevent the hole-punch from ever completing: which in turn
- * locks writers out with its hold on i_mutex. So refrain from
+ * locks writers out with its hold on i_rwsem. So refrain from
* faulting pages into the hole while it's being punched. Although
* shmem_undo_range() does remove the additions, it may be unable to
* keep up, as each new page needs its own unmap_mapping_range() call,
* we just need to make racing faults a rare case.
*
* The implementation below would be much simpler if we just used a
- * standard mutex or completion: but we cannot take i_mutex in fault,
+ * standard mutex or completion: but we cannot take i_rwsem in fault,
* and bloating every shmem inode for this unlikely case would be sad.
*/
if (unlikely(inode->i_private)) {
spin_unlock(&inode->i_lock);
}
- sgp = SGP_CACHE;
-
- if ((vma->vm_flags & VM_NOHUGEPAGE) ||
- test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags))
- sgp = SGP_NOHUGE;
- else if (vma->vm_flags & VM_HUGEPAGE)
- sgp = SGP_HUGE;
-
- err = shmem_getpage_gfp(inode, vmf->pgoff, &vmf->page, sgp,
+ err = shmem_getpage_gfp(inode, vmf->pgoff, &vmf->page, SGP_CACHE,
gfp, vma, vmf, &ret);
if (err)
return vmf_error(err);
struct shmem_inode_info *info = SHMEM_I(inode);
pgoff_t index = pos >> PAGE_SHIFT;
- /* i_mutex is held by caller */
+ /* i_rwsem is held by caller */
if (unlikely(info->seals & (F_SEAL_GROW |
F_SEAL_WRITE | F_SEAL_FUTURE_WRITE))) {
if (info->seals & (F_SEAL_WRITE | F_SEAL_FUTURE_WRITE))
/*
* We must evaluate after, since reads (unlike writes)
- * are called without i_mutex protection against truncate
+ * are called without i_rwsem protection against truncate
*/
nr = PAGE_SIZE;
i_size = i_size_read(inode);
return -ENXIO;
inode_lock(inode);
- /* We're holding i_mutex so we can access i_size directly */
+ /* We're holding i_rwsem so we can access i_size directly */
offset = mapping_seek_hole_data(mapping, offset, inode->i_size, whence);
if (offset >= 0)
offset = vfs_setpos(file, offset, MAX_LFS_FILESIZE);
struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb);
struct shmem_inode_info *info = SHMEM_I(inode);
struct shmem_falloc shmem_falloc;
- pgoff_t start, index, end;
+ pgoff_t start, index, end, undo_fallocend;
int error;
if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE))
loff_t unmap_end = round_down(offset + len, PAGE_SIZE) - 1;
DECLARE_WAIT_QUEUE_HEAD_ONSTACK(shmem_falloc_waitq);
- /* protected by i_mutex */
+ /* protected by i_rwsem */
if (info->seals & (F_SEAL_WRITE | F_SEAL_FUTURE_WRITE)) {
error = -EPERM;
goto out;
inode->i_private = &shmem_falloc;
spin_unlock(&inode->i_lock);
- for (index = start; index < end; index++) {
+ /*
+ * info->fallocend is only relevant when huge pages might be
+ * involved: to prevent split_huge_page() freeing fallocated
+ * pages when FALLOC_FL_KEEP_SIZE committed beyond i_size.
+ */
+ undo_fallocend = info->fallocend;
+ if (info->fallocend < end)
+ info->fallocend = end;
+
+ for (index = start; index < end; ) {
struct page *page;
/*
else
error = shmem_getpage(inode, index, &page, SGP_FALLOC);
if (error) {
+ info->fallocend = undo_fallocend;
/* Remove the !PageUptodate pages we added */
if (index > start) {
shmem_undo_range(inode,
goto undone;
}
+ index++;
+ /*
+ * Here is a more important optimization than it appears:
+ * a second SGP_FALLOC on the same huge page will clear it,
+ * making it PageUptodate and un-undoable if we fail later.
+ */
+ if (PageTransCompound(page)) {
+ index = round_up(index, HPAGE_PMD_NR);
+ /* Beware 32-bit wraparound */
+ if (!index)
+ index--;
+ }
+
/*
* Inform shmem_writepage() how far we have reached.
* No need for lock or barrier: we have the page lock.
*/
- shmem_falloc.next++;
if (!PageUptodate(page))
- shmem_falloc.nr_falloced++;
+ shmem_falloc.nr_falloced += index - shmem_falloc.next;
+ shmem_falloc.next = index;
/*
* If !PageUptodate, leave it that way so that freeable pages
struct shmem_options *ctx = fc->fs_private;
struct shmem_sb_info *sbinfo = SHMEM_SB(fc->root->d_sb);
unsigned long inodes;
+ struct mempolicy *mpol = NULL;
const char *err;
- spin_lock(&sbinfo->stat_lock);
+ raw_spin_lock(&sbinfo->stat_lock);
inodes = sbinfo->max_inodes - sbinfo->free_inodes;
if ((ctx->seen & SHMEM_SEEN_BLOCKS) && ctx->blocks) {
if (!sbinfo->max_blocks) {
* Preserve previous mempolicy unless mpol remount option was specified.
*/
if (ctx->mpol) {
- mpol_put(sbinfo->mpol);
+ mpol = sbinfo->mpol;
sbinfo->mpol = ctx->mpol; /* transfers initial ref */
ctx->mpol = NULL;
}
- spin_unlock(&sbinfo->stat_lock);
+ raw_spin_unlock(&sbinfo->stat_lock);
+ mpol_put(mpol);
return 0;
out:
- spin_unlock(&sbinfo->stat_lock);
+ raw_spin_unlock(&sbinfo->stat_lock);
return invalfc(fc, "%s", err);
}
struct shmem_options *ctx = fc->fs_private;
struct inode *inode;
struct shmem_sb_info *sbinfo;
- int err = -ENOMEM;
/* Round up to L1_CACHE_BYTES to resist false sharing */
sbinfo = kzalloc(max((int)sizeof(struct shmem_sb_info),
sbinfo->mpol = ctx->mpol;
ctx->mpol = NULL;
- spin_lock_init(&sbinfo->stat_lock);
+ raw_spin_lock_init(&sbinfo->stat_lock);
if (percpu_counter_init(&sbinfo->used_blocks, 0, GFP_KERNEL))
goto failed;
spin_lock_init(&sbinfo->shrinklist_lock);
failed:
shmem_put_super(sb);
- return err;
+ return -ENOMEM;
}
static int shmem_get_tree(struct fs_context *fc)
if (has_transparent_hugepage() && shmem_huge > SHMEM_HUGE_DENY)
SHMEM_SB(shm_mnt->mnt_sb)->huge = shmem_huge;
else
- shmem_huge = 0; /* just in case it was patched */
+ shmem_huge = SHMEM_HUGE_NEVER; /* just in case it was patched */
#endif
return 0;
__ATTR(shmem_enabled, 0644, shmem_enabled_show, shmem_enabled_store);
#endif /* CONFIG_TRANSPARENT_HUGEPAGE && CONFIG_SYSFS */
- #ifdef CONFIG_TRANSPARENT_HUGEPAGE
- bool shmem_huge_enabled(struct vm_area_struct *vma)
- {
- struct inode *inode = file_inode(vma->vm_file);
- struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb);
- loff_t i_size;
- pgoff_t off;
-
- if (!transhuge_vma_enabled(vma, vma->vm_flags))
- return false;
- if (shmem_huge == SHMEM_HUGE_FORCE)
- return true;
- if (shmem_huge == SHMEM_HUGE_DENY)
- return false;
- switch (sbinfo->huge) {
- case SHMEM_HUGE_NEVER:
- return false;
- case SHMEM_HUGE_ALWAYS:
- return true;
- case SHMEM_HUGE_WITHIN_SIZE:
- off = round_up(vma->vm_pgoff, HPAGE_PMD_NR);
- i_size = round_up(i_size_read(inode), PAGE_SIZE);
- if (i_size >= HPAGE_PMD_SIZE &&
- i_size >> PAGE_SHIFT >= off)
- return true;
- fallthrough;
- case SHMEM_HUGE_ADVISE:
- /* TODO: implement fadvise() hints */
- return (vma->vm_flags & VM_HUGEPAGE);
- default:
- VM_BUG_ON(1);
- return false;
- }
- }
- #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
-
#else /* !CONFIG_SHMEM */
/*
* @mapping: mapping to truncate
* @lstart: offset from which to truncate
*
- * Called under (and serialised by) inode->i_mutex.
+ * Called under (and serialised by) inode->i_rwsem and
+ * mapping->invalidate_lock.
*
* Note: When this function returns, there can be a page in the process of
* deletion (inside __delete_from_page_cache()) in the specified range. Thus
* truncate_inode_pages_final - truncate *all* pages before inode dies
* @mapping: mapping to truncate
*
- * Called under (and serialized by) inode->i_mutex.
+ * Called under (and serialized by) inode->i_rwsem.
*
* Filesystems have to use this in the .evict_inode path to inform the
* VM that this is the final truncate and the inode is going away.
index = indices[i];
if (xa_is_value(page)) {
- invalidate_exceptional_entry(mapping, index,
- page);
+ count += invalidate_exceptional_entry(mapping,
+ index,
+ page);
continue;
}
index += thp_nr_pages(page) - 1;
}
/**
- * invalidate_mapping_pages - Invalidate all the unlocked pages of one inode
- * @mapping: the address_space which holds the pages to invalidate
+ * invalidate_mapping_pages - Invalidate all clean, unlocked cache of one inode
+ * @mapping: the address_space which holds the cache to invalidate
* @start: the offset 'from' which to invalidate
* @end: the offset 'to' which to invalidate (inclusive)
*
- * This function only removes the unlocked pages, if you want to
- * remove all the pages of one inode, you must call truncate_inode_pages.
+ * This function removes pages that are clean, unmapped and unlocked,
+ * as well as shadow entries. It will not block on IO activity.
*
- * invalidate_mapping_pages() will not block on IO activity. It will not
- * invalidate pages which are dirty, locked, under writeback or mapped into
- * pagetables.
+ * If you want to remove all the pages of one inode, regardless of
+ * their use and writeback state, use truncate_inode_pages().
*
- * Return: the number of the pages that were invalidated
+ * Return: the number of the cache entries that were invalidated
*/
unsigned long invalidate_mapping_pages(struct address_space *mapping,
pgoff_t start, pgoff_t end)
static int
invalidate_complete_page2(struct address_space *mapping, struct page *page)
{
- unsigned long flags;
-
if (page->mapping != mapping)
return 0;
if (page_has_private(page) && !try_to_release_page(page, GFP_KERNEL))
return 0;
- xa_lock_irqsave(&mapping->i_pages, flags);
+ xa_lock_irq(&mapping->i_pages);
if (PageDirty(page))
goto failed;
BUG_ON(page_has_private(page));
__delete_from_page_cache(page, NULL);
- xa_unlock_irqrestore(&mapping->i_pages, flags);
+ xa_unlock_irq(&mapping->i_pages);
if (mapping->a_ops->freepage)
mapping->a_ops->freepage(page);
put_page(page); /* pagecache ref */
return 1;
failed:
- xa_unlock_irqrestore(&mapping->i_pages, flags);
+ xa_unlock_irq(&mapping->i_pages);
return 0;
}
* setattr function when ATTR_SIZE is passed in.
*
* Must be called with a lock serializing truncates and writes (generally
- * i_mutex but e.g. xfs uses a different lock) and before all filesystem
+ * i_rwsem but e.g. xfs uses a different lock) and before all filesystem
* specific block truncation has been performed.
*/
void truncate_setsize(struct inode *inode, loff_t newsize)
*
* The function must be called after i_size is updated so that page fault
* coming after we unlock the page will already see the new i_size.
- * The function must be called while we still hold i_mutex - this not only
+ * The function must be called while we still hold i_rwsem - this not only
* makes sure i_size is stable but also that userspace cannot observe new
* i_size value before we are prepared to store mmap writes at new inode size.
*/
*/
void all_vm_events(unsigned long *ret)
{
- get_online_cpus();
+ cpus_read_lock();
sum_vm_events(ret);
- put_online_cpus();
+ cpus_read_unlock();
}
EXPORT_SYMBOL_GPL(all_vm_events);
*
* Some sample thresholds:
*
- * Threshold Processors (fls) Zonesize fls(mem+1)
+ * Threshold Processors (fls) Zonesize fls(mem)+1
* ------------------------------------------------------------------
* 8 1 1 0.9-1 GB 4
* 16 2 2 0.9-1 GB 4
"pgreuse",
"pgsteal_kswapd",
"pgsteal_direct",
+ "pgdemote_kswapd",
+ "pgdemote_direct",
"pgscan_kswapd",
"pgscan_direct",
"pgscan_direct_throttle",
}
/* Print out the free pages at each order for each migatetype */
- static int pagetypeinfo_showfree(struct seq_file *m, void *arg)
+ static void pagetypeinfo_showfree(struct seq_file *m, void *arg)
{
int order;
pg_data_t *pgdat = (pg_data_t *)arg;
seq_putc(m, '\n');
walk_zones_in_node(m, pgdat, true, false, pagetypeinfo_showfree_print);
-
- return 0;
}
static void pagetypeinfo_showblockcount_print(struct seq_file *m,
}
/* Print out the number of pageblocks for each migratetype */
- static int pagetypeinfo_showblockcount(struct seq_file *m, void *arg)
+ static void pagetypeinfo_showblockcount(struct seq_file *m, void *arg)
{
int mtype;
pg_data_t *pgdat = (pg_data_t *)arg;
seq_putc(m, '\n');
walk_zones_in_node(m, pgdat, true, false,
pagetypeinfo_showblockcount_print);
-
- return 0;
}
/*
}
}
- /*
- * Switch off vmstat processing and then fold all the remaining differentials
- * until the diffs stay at zero. The function is used by NOHZ and can only be
- * invoked when tick processing is not active.
- */
/*
* Check if the diffs for a certain cpu indicate that
* an update is needed.
/*
* The fast way of checking if there are any vmstat diffs.
*/
- if (memchr_inv(pzstats->vm_stat_diff, 0, NR_VM_ZONE_STAT_ITEMS *
- sizeof(pzstats->vm_stat_diff[0])))
+ if (memchr_inv(pzstats->vm_stat_diff, 0, sizeof(pzstats->vm_stat_diff)))
return true;
if (last_pgdat == zone->zone_pgdat)
continue;
last_pgdat = zone->zone_pgdat;
n = per_cpu_ptr(zone->zone_pgdat->per_cpu_nodestats, cpu);
- if (memchr_inv(n->vm_node_stat_diff, 0, NR_VM_NODE_STAT_ITEMS *
- sizeof(n->vm_node_stat_diff[0])))
- return true;
+ if (memchr_inv(n->vm_node_stat_diff, 0, sizeof(n->vm_node_stat_diff)))
+ return true;
}
return false;
}
{
int cpu;
- get_online_cpus();
+ cpus_read_lock();
/* Check processors whose vmstat worker threads have been disabled */
for_each_online_cpu(cpu) {
struct delayed_work *dw = &per_cpu(vmstat_work, cpu);
cond_resched();
}
- put_online_cpus();
+ cpus_read_unlock();
schedule_delayed_work(&shepherd,
round_jiffies_relative(sysctl_stat_interval));
if (ret < 0)
pr_err("vmstat: failed to register 'online' hotplug state\n");
- get_online_cpus();
+ cpus_read_lock();
init_cpu_node_state();
- put_online_cpus();
+ cpus_read_unlock();
start_shepherd_timer();
#endif