quiet_cmd_mk_schema = SCHEMA $@
cmd_mk_schema = $(DT_MK_SCHEMA) $(DT_MK_SCHEMA_FLAGS) -o $@ $(filter-out FORCE, $^)
-DT_DOCS = $(shell cd $(srctree)/$(src) && find * -name '*.yaml')
+DT_DOCS = $(shell \
+ cd $(srctree)/$(src) && \
+ find * \( -name '*.yaml' ! -name $(DT_TMP_SCHEMA) \) \
+ )
+
DT_SCHEMA_FILES ?= $(addprefix $(src)/,$(DT_DOCS))
extra-y += $(patsubst $(src)/%.yaml,%.example.dts, $(DT_SCHEMA_FILES))
- compatible : "olpc,ap-sp"
- reg : base address and length of SoC's WTM registers
- interrupts : SP-AP interrupt
-- clocks : phandle + clock-specifier for the clock that drives the WTM
-- clock-names: should be "sp"
Example:
ap-sp@d4290000 {
compatible = "olpc,ap-sp";
reg = <0xd4290000 0x1000>;
interrupts = <40>;
- clocks = <&soc_clocks MMP2_CLK_SP>;
- clock-names = "sp";
}
dentry-state:
-From linux/fs/dentry.c:
+From linux/include/linux/dcache.h:
--------------------------------------------------------------
-struct {
+struct dentry_stat_t dentry_stat {
int nr_dentry;
int nr_unused;
int age_limit; /* age in seconds */
int want_pages; /* pages requested by system */
- int dummy[2];
-} dentry_stat = {0, 0, 45, 0,};
---------------------------------------------------------------
-
-Dentries are dynamically allocated and deallocated, and
-nr_dentry seems to be 0 all the time. Hence it's safe to
-assume that only nr_unused, age_limit and want_pages are
-used. Nr_unused seems to be exactly what its name says.
+ int nr_negative; /* # of unused negative dentries */
+ int dummy; /* Reserved for future use */
+};
+--------------------------------------------------------------
+
+Dentries are dynamically allocated and deallocated.
+
+nr_dentry shows the total number of dentries allocated (active
++ unused). nr_unused shows the number of dentries that are not
+actively used, but are saved in the LRU list for future reuse.
+
Age_limit is the age in seconds after which dcache entries
can be reclaimed when memory is short and want_pages is
nonzero when shrink_dcache_pages() has been called and the
dcache isn't pruned yet.
+nr_negative shows the number of unused dentries that are also
+negative dentries which do not mapped to actual files.
+
==============================================================
dquot-max & dquot-nr:
S: Maintained
F: drivers/media/tuners/tuner-xc2028.*
+XDP (eXpress Data Path)
+M: Alexei Starovoitov <ast@kernel.org>
+M: Daniel Borkmann <daniel@iogearbox.net>
+M: David S. Miller <davem@davemloft.net>
+M: Jakub Kicinski <jakub.kicinski@netronome.com>
+M: Jesper Dangaard Brouer <hawk@kernel.org>
+M: John Fastabend <john.fastabend@gmail.com>
+L: netdev@vger.kernel.org
+L: xdp-newbies@vger.kernel.org
+S: Supported
+F: net/core/xdp.c
+F: include/net/xdp.h
+F: kernel/bpf/devmap.c
+F: kernel/bpf/cpumap.c
+F: include/trace/events/xdp.h
+K: xdp
+N: xdp
+
XDP SOCKETS (AF_XDP)
M: Björn Töpel <bjorn.topel@intel.com>
M: Magnus Karlsson <magnus.karlsson@intel.com>
} else /* remote PCI bus */
base = cnspci->cfg1_regs + ((busno & 0xf) << 20);
- return base + (where & 0xffc) + (devfn << 12);
+ return base + where + (devfn << 12);
}
static int cns3xxx_pci_read_config(struct pci_bus *bus, unsigned int devfn,
u32 mask = (0x1ull << (size * 8)) - 1;
int shift = (where % 4) * 8;
- ret = pci_generic_config_read32(bus, devfn, where, size, val);
+ ret = pci_generic_config_read(bus, devfn, where, size, val);
if (ret == PCIBIOS_SUCCESSFUL && !bus->number && !devfn &&
(where & 0xffc) == PCI_CLASS_REVISION)
dcache_clean_range(__idmap_text_start, __idmap_text_end);
/* Clean kvm setup code to PoC? */
- if (el2_reset_needed())
+ if (el2_reset_needed()) {
dcache_clean_range(__hyp_idmap_text_start, __hyp_idmap_text_end);
+ dcache_clean_range(__hyp_text_start, __hyp_text_end);
+ }
/* make the crash dump kernel image protected again */
crash_post_resume();
#include <asm/virt.h>
.text
+ .pushsection .hyp.text, "ax"
+
.align 11
ENTRY(__hyp_stub_vectors)
* we end up running with module randomization disabled.
*/
module_alloc_base = (u64)_etext - MODULES_VSIZE;
+ __flush_dcache_area(&module_alloc_base, sizeof(module_alloc_base));
/*
* Try to map the FDT early. If this fails, we simply bail,
addr < (unsigned long)__entry_text_end) ||
(addr >= (unsigned long)__idmap_text_start &&
addr < (unsigned long)__idmap_text_end) ||
+ (addr >= (unsigned long)__hyp_text_start &&
+ addr < (unsigned long)__hyp_text_end) ||
!!search_exception_tables(addr))
return true;
if (!is_kernel_in_hyp_mode()) {
- if ((addr >= (unsigned long)__hyp_text_start &&
- addr < (unsigned long)__hyp_text_end) ||
- (addr >= (unsigned long)__hyp_idmap_text_start &&
+ if ((addr >= (unsigned long)__hyp_idmap_text_start &&
addr < (unsigned long)__hyp_idmap_text_end))
return true;
}
__clean_dcache_area_pou(kaddr, len);
__flush_icache_all();
} else {
- flush_icache_range(addr, addr + len);
+ /*
+ * Don't issue kick_all_cpus_sync() after I-cache invalidation
+ * for user mappings.
+ */
+ __flush_icache_range(addr, addr + len);
}
}
generic-y += preempt.h
generic-y += segment.h
generic-y += serial.h
+generic-y += shmparam.h
generic-y += tlbflush.h
generic-y += topology.h
generic-y += trace_clock.h
include include/uapi/asm-generic/Kbuild.asm
generic-y += kvm_para.h
-generic-y += shmparam.h
generic-y += ucontext.h
generic-y += scatterlist.h
generic-y += sections.h
generic-y += serial.h
+generic-y += shmparam.h
generic-y += sizes.h
generic-y += spinlock.h
generic-y += timex.h
include include/uapi/asm-generic/Kbuild.asm
generic-y += kvm_para.h
-generic-y += shmparam.h
generic-y += ucontext.h
generic-y += sections.h
generic-y += segment.h
generic-y += serial.h
+generic-y += shmparam.h
generic-y += sizes.h
generic-y += topology.h
generic-y += trace_clock.h
include include/uapi/asm-generic/Kbuild.asm
-generic-y += shmparam.h
generic-y += ucontext.h
generic-y += percpu.h
generic-y += preempt.h
generic-y += sections.h
+generic-y += shmparam.h
generic-y += spinlock.h
generic-y += topology.h
generic-y += trace_clock.h
generated-y += unistd_32.h
generic-y += kvm_para.h
-generic-y += shmparam.h
generic-y += percpu.h
generic-y += preempt.h
generic-y += serial.h
+generic-y += shmparam.h
generic-y += syscalls.h
generic-y += topology.h
generic-y += trace_clock.h
generated-y += unistd_32.h
generic-y += kvm_para.h
-generic-y += shmparam.h
generic-y += ucontext.h
generic-y += qrwlock.h
generic-y += sections.h
generic-y += segment.h
+generic-y += shmparam.h
generic-y += string.h
generic-y += switch_to.h
generic-y += topology.h
include include/uapi/asm-generic/Kbuild.asm
generic-y += kvm_para.h
-generic-y += shmparam.h
generic-y += ucontext.h
prompt "Base ISA"
default ARCH_RV64I
help
- This selects the base ISA that this kernel will traget and must match
+ This selects the base ISA that this kernel will target and must match
the target platform.
config ARCH_RV32I
CONFIG_EXPERT=y
CONFIG_BPF_SYSCALL=y
CONFIG_SMP=y
-CONFIG_PCI=y
-CONFIG_PCIE_XILINX=y
CONFIG_MODULES=y
CONFIG_MODULE_UNLOAD=y
CONFIG_NET=y
CONFIG_IP_PNP_BOOTP=y
CONFIG_IP_PNP_RARP=y
CONFIG_NETLINK_DIAG=y
+CONFIG_PCI=y
+CONFIG_PCIEPORTBUS=y
+CONFIG_PCI_HOST_GENERIC=y
+CONFIG_PCIE_XILINX=y
CONFIG_DEVTMPFS=y
CONFIG_BLK_DEV_LOOP=y
CONFIG_VIRTIO_BLK=y
CONFIG_USB_UAS=y
CONFIG_VIRTIO_MMIO=y
CONFIG_SIFIVE_PLIC=y
-CONFIG_RAS=y
CONFIG_EXT4_FS=y
CONFIG_EXT4_FS_POSIX_ACL=y
CONFIG_AUTOFS4_FS=y
CONFIG_NFS_V4_2=y
CONFIG_ROOT_NFS=y
CONFIG_CRYPTO_USER_API_HASH=y
+CONFIG_CRYPTO_DEV_VIRTIO=y
CONFIG_PRINTK_TIME=y
# CONFIG_RCU_TRACE is not set
#define __pgd(x) ((pgd_t) { (x) })
#define __pgprot(x) ((pgprot_t) { (x) })
-#ifdef CONFIG_64BITS
+#ifdef CONFIG_64BIT
#define PTE_FMT "%016lx"
#else
#define PTE_FMT "%08lx"
* This decides where the kernel will search for a free chunk of vm
* space during mmap's.
*/
-#define TASK_UNMAPPED_BASE PAGE_ALIGN(TASK_SIZE >> 1)
+#define TASK_UNMAPPED_BASE PAGE_ALIGN(TASK_SIZE / 3)
#define STACK_TOP TASK_SIZE
#define STACK_TOP_MAX STACK_TOP
OFFSET(TASK_STACK, task_struct, stack);
OFFSET(TASK_TI, task_struct, thread_info);
OFFSET(TASK_TI_FLAGS, task_struct, thread_info.flags);
+ OFFSET(TASK_TI_PREEMPT_COUNT, task_struct, thread_info.preempt_count);
OFFSET(TASK_TI_KERNEL_SP, task_struct, thread_info.kernel_sp);
OFFSET(TASK_TI_USER_SP, task_struct, thread_info.user_sp);
OFFSET(TASK_TI_CPU, task_struct, thread_info.cpu);
REG_L x2, PT_SP(sp)
.endm
+#if !IS_ENABLED(CONFIG_PREEMPT)
+.set resume_kernel, restore_all
+#endif
+
ENTRY(handle_exception)
SAVE_ALL
REG_L s0, PT_SSTATUS(sp)
csrc sstatus, SR_SIE
andi s0, s0, SR_SPP
- bnez s0, restore_all
+ bnez s0, resume_kernel
resume_userspace:
/* Interrupts must be disabled here so flags are checked atomically */
RESTORE_ALL
sret
+#if IS_ENABLED(CONFIG_PREEMPT)
+resume_kernel:
+ REG_L s0, TASK_TI_PREEMPT_COUNT(tp)
+ bnez s0, restore_all
+need_resched:
+ REG_L s0, TASK_TI_FLAGS(tp)
+ andi s0, s0, _TIF_NEED_RESCHED
+ beqz s0, restore_all
+ call preempt_schedule_irq
+ j need_resched
+#endif
+
work_pending:
/* Enter slow path for supplementary processing */
la ra, ret_from_exception
BUG_ON(mem_size == 0);
set_max_mapnr(PFN_DOWN(mem_size));
- max_low_pfn = memblock_end_of_DRAM();
+ max_low_pfn = PFN_DOWN(memblock_end_of_DRAM());
#ifdef CONFIG_BLK_DEV_INITRD
setup_initrd();
while ((dn = of_find_node_by_type(dn, "cpu"))) {
hart = riscv_of_processor_hartid(dn);
- if (hart < 0) {
- of_node_put(dn);
+ if (hart < 0)
continue;
- }
if (hart == cpuid_to_hartid_map(0)) {
BUG_ON(found_boot_cpu);
found_boot_cpu = 1;
- of_node_put(dn);
continue;
}
set_cpu_possible(cpuid, true);
set_cpu_present(cpuid, true);
cpuid++;
- of_node_put(dn);
}
BUG_ON(!found_boot_cpu);
unsigned long max_zone_pfns[MAX_NR_ZONES] = { 0, };
#ifdef CONFIG_ZONE_DMA32
- max_zone_pfns[ZONE_DMA32] = PFN_DOWN(min(4UL * SZ_1G, max_low_pfn));
+ max_zone_pfns[ZONE_DMA32] = PFN_DOWN(min(4UL * SZ_1G,
+ (unsigned long) PFN_PHYS(max_low_pfn)));
#endif
max_zone_pfns[ZONE_NORMAL] = max_low_pfn;
generic-y += sections.h
generic-y += segment.h
generic-y += serial.h
+generic-y += shmparam.h
generic-y += sizes.h
generic-y += syscalls.h
generic-y += topology.h
include include/uapi/asm-generic/Kbuild.asm
generic-y += kvm_para.h
-generic-y += shmparam.h
generic-y += ucontext.h
#endif
#ifdef CONFIG_KASAN
+#ifdef CONFIG_KASAN_EXTRA
+#define KASAN_STACK_ORDER 2
+#else
#define KASAN_STACK_ORDER 1
+#endif
#else
#define KASAN_STACK_ORDER 0
#endif
#include <linux/module.h>
#include <linux/io.h>
+#define movs(type,to,from) \
+ asm volatile("movs" type:"=&D" (to), "=&S" (from):"0" (to), "1" (from):"memory")
+
/* Originally from i386/string.h */
-static __always_inline void __iomem_memcpy(void *to, const void *from, size_t n)
+static __always_inline void rep_movs(void *to, const void *from, size_t n)
{
unsigned long d0, d1, d2;
asm volatile("rep ; movsl\n\t"
void memcpy_fromio(void *to, const volatile void __iomem *from, size_t n)
{
- __iomem_memcpy(to, (const void *)from, n);
+ if (unlikely(!n))
+ return;
+
+ /* Align any unaligned source IO */
+ if (unlikely(1 & (unsigned long)from)) {
+ movs("b", to, from);
+ n--;
+ }
+ if (n > 1 && unlikely(2 & (unsigned long)from)) {
+ movs("w", to, from);
+ n-=2;
+ }
+ rep_movs(to, (const void *)from, n);
}
EXPORT_SYMBOL(memcpy_fromio);
void memcpy_toio(volatile void __iomem *to, const void *from, size_t n)
{
- __iomem_memcpy((void *)to, (const void *) from, n);
+ if (unlikely(!n))
+ return;
+
+ /* Align any unaligned destination IO */
+ if (unlikely(1 & (unsigned long)to)) {
+ movs("b", to, from);
+ n--;
+ }
+ if (n > 1 && unlikely(2 & (unsigned long)to)) {
+ movs("w", to, from);
+ n-=2;
+ }
+ rep_movs((void *)to, (const void *) from, n);
}
EXPORT_SYMBOL(memcpy_toio);
If unsure, say N.
config XTENSA_UNALIGNED_USER
- bool "Unaligned memory access in use space"
+ bool "Unaligned memory access in user space"
help
The Xtensa architecture currently does not handle unaligned
memory accesses in hardware but through an exception handler.
help
Include support for flattened device tree machine descriptions.
-config BUILTIN_DTB
+config BUILTIN_DTB_SOURCE
string "DTB to build into the kernel image"
depends on OF
#
#
-BUILTIN_DTB := $(patsubst "%",%,$(CONFIG_BUILTIN_DTB)).dtb.o
-ifneq ($(CONFIG_BUILTIN_DTB),"")
-obj-$(CONFIG_OF) += $(BUILTIN_DTB)
+BUILTIN_DTB_SOURCE := $(patsubst "%",%,$(CONFIG_BUILTIN_DTB_SOURCE)).dtb.o
+ifneq ($(CONFIG_BUILTIN_DTB_SOURCE),"")
+obj-$(CONFIG_OF) += $(BUILTIN_DTB_SOURCE)
endif
# for CONFIG_OF_ALL_DTBS test
CONFIG_CMDLINE_BOOL=y
CONFIG_CMDLINE="earlycon=uart8250,mmio32native,0xfd050020,115200n8 console=ttyS0,115200n8 ip=dhcp root=/dev/nfs rw debug memmap=0x38000000@0"
CONFIG_USE_OF=y
-CONFIG_BUILTIN_DTB="kc705"
+CONFIG_BUILTIN_DTB_SOURCE="kc705"
# CONFIG_COMPACTION is not set
# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
CONFIG_PM=y
# CONFIG_PCI is not set
CONFIG_XTENSA_PLATFORM_XTFPGA=y
CONFIG_USE_OF=y
-CONFIG_BUILTIN_DTB="csp"
+CONFIG_BUILTIN_DTB_SOURCE="csp"
# CONFIG_COMPACTION is not set
CONFIG_XTFPGA_LCD=y
# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
CONFIG_CMDLINE_BOOL=y
CONFIG_CMDLINE="earlycon=uart8250,mmio32native,0xfd050020,115200n8 console=ttyS0,115200n8 ip=dhcp root=/dev/nfs rw debug memmap=0x38000000@0"
CONFIG_USE_OF=y
-CONFIG_BUILTIN_DTB="kc705"
+CONFIG_BUILTIN_DTB_SOURCE="kc705"
# CONFIG_COMPACTION is not set
# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
CONFIG_NET=y
CONFIG_CMDLINE_BOOL=y
CONFIG_CMDLINE="earlycon=uart8250,mmio32native,0x9d050020,115200n8 console=ttyS0,115200n8 ip=dhcp root=/dev/nfs rw debug memmap=256M@0x60000000"
CONFIG_USE_OF=y
-CONFIG_BUILTIN_DTB="kc705_nommu"
+CONFIG_BUILTIN_DTB_SOURCE="kc705_nommu"
CONFIG_BINFMT_FLAT=y
CONFIG_NET=y
CONFIG_PACKET=y
CONFIG_HOTPLUG_CPU=y
# CONFIG_INITIALIZE_XTENSA_MMU_INSIDE_VMLINUX is not set
# CONFIG_PCI is not set
+CONFIG_VECTORS_OFFSET=0x00002000
CONFIG_XTENSA_PLATFORM_XTFPGA=y
CONFIG_CMDLINE_BOOL=y
CONFIG_CMDLINE="earlycon=uart8250,mmio32native,0xfd050020,115200n8 console=ttyS0,115200n8 ip=dhcp root=/dev/nfs rw debug memmap=96M@0"
CONFIG_USE_OF=y
-CONFIG_BUILTIN_DTB="lx200mx"
+CONFIG_BUILTIN_DTB_SOURCE="lx200mx"
# CONFIG_COMPACTION is not set
# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
CONFIG_NET=y
movi a2, cpu_start_ccount
1:
+ memw
l32i a3, a2, 0
beqi a3, 0, 1b
movi a3, 0
s32i a3, a2, 0
- memw
1:
+ memw
l32i a3, a2, 0
beqi a3, 0, 1b
wsr a3, ccount
rsr a0, prid
neg a2, a0
movi a3, cpu_start_id
+ memw
s32i a2, a3, 0
#if XCHAL_DCACHE_IS_WRITEBACK
dhwbi a3, 0
#endif
1:
+ memw
l32i a2, a3, 0
dhi a3, 0
bne a2, a0, 1b
{
unsigned i;
- for (i = 0; i < max_cpus; ++i)
+ for_each_possible_cpu(i)
set_cpu_present(i, true);
}
pr_info("%s: Core Count = %d\n", __func__, ncpus);
pr_info("%s: Core Id = %d\n", __func__, core_id);
+ if (ncpus > NR_CPUS) {
+ ncpus = NR_CPUS;
+ pr_info("%s: limiting core count by %d\n", __func__, ncpus);
+ }
+
for (i = 0; i < ncpus; ++i)
set_cpu_possible(i, true);
}
int i;
#ifdef CONFIG_HOTPLUG_CPU
- cpu_start_id = cpu;
- system_flush_invalidate_dcache_range(
- (unsigned long)&cpu_start_id, sizeof(cpu_start_id));
+ WRITE_ONCE(cpu_start_id, cpu);
+ /* Pairs with the third memw in the cpu_restart */
+ mb();
+ system_flush_invalidate_dcache_range((unsigned long)&cpu_start_id,
+ sizeof(cpu_start_id));
#endif
smp_call_function_single(0, mx_cpu_start, (void *)cpu, 1);
ccount = get_ccount();
while (!ccount);
- cpu_start_ccount = ccount;
+ WRITE_ONCE(cpu_start_ccount, ccount);
- while (time_before(jiffies, timeout)) {
+ do {
+ /*
+ * Pairs with the first two memws in the
+ * .Lboot_secondary.
+ */
mb();
- if (!cpu_start_ccount)
- break;
- }
+ ccount = READ_ONCE(cpu_start_ccount);
+ } while (ccount && time_before(jiffies, timeout));
- if (cpu_start_ccount) {
+ if (ccount) {
smp_call_function_single(0, mx_cpu_stop,
- (void *)cpu, 1);
- cpu_start_ccount = 0;
+ (void *)cpu, 1);
+ WRITE_ONCE(cpu_start_ccount, 0);
return -EIO;
}
}
pr_debug("%s: Calling wakeup_secondary(cpu:%d, idle:%p, sp: %08lx)\n",
__func__, cpu, idle, start_info.stack);
+ init_completion(&cpu_running);
ret = boot_secondary(cpu, idle);
if (ret == 0) {
wait_for_completion_timeout(&cpu_running,
unsigned long timeout = jiffies + msecs_to_jiffies(1000);
while (time_before(jiffies, timeout)) {
system_invalidate_dcache_range((unsigned long)&cpu_start_id,
- sizeof(cpu_start_id));
- if (cpu_start_id == -cpu) {
+ sizeof(cpu_start_id));
+ /* Pairs with the second memw in the cpu_restart */
+ mb();
+ if (READ_ONCE(cpu_start_id) == -cpu) {
platform_cpu_kill(cpu);
return;
}
container_of(evt, struct ccount_timer, evt);
if (timer->irq_enabled) {
- disable_irq(evt->irq);
+ disable_irq_nosync(evt->irq);
timer->irq_enabled = 0;
}
return 0;
kblockd_schedule_work(&q->timeout_work);
}
+static void blk_timeout_work(struct work_struct *work)
+{
+}
+
/**
* blk_alloc_queue_node - allocate a request queue
* @gfp_mask: memory allocation flags
timer_setup(&q->backing_dev_info->laptop_mode_wb_timer,
laptop_mode_timer_fn, 0);
timer_setup(&q->timeout, blk_rq_timed_out_timer, 0);
- INIT_WORK(&q->timeout_work, NULL);
+ INIT_WORK(&q->timeout_work, blk_timeout_work);
INIT_LIST_HEAD(&q->icq_list);
#ifdef CONFIG_BLK_CGROUP
INIT_LIST_HEAD(&q->blkg_list);
blk_flush_complete_seq(rq, fq, REQ_FSEQ_DATA, error);
spin_unlock_irqrestore(&fq->mq_flush_lock, flags);
- blk_mq_run_hw_queue(hctx, true);
+ blk_mq_sched_restart(hctx);
}
/**
{
int autosuspend_delay;
u64 last_busy, expires = 0;
- u64 now = ktime_to_ns(ktime_get());
+ u64 now = ktime_get_mono_fast_ns();
if (!dev->power.use_autosuspend)
goto out;
* If 'expires' is after the current time, we've been called
* too early.
*/
- if (expires > 0 && expires < ktime_to_ns(ktime_get())) {
+ if (expires > 0 && expires < ktime_get_mono_fast_ns()) {
dev->power.timer_expires = 0;
rpm_suspend(dev, dev->power.timer_autosuspends ?
(RPM_ASYNC | RPM_AUTO) : RPM_ASYNC);
int pm_schedule_suspend(struct device *dev, unsigned int delay)
{
unsigned long flags;
- ktime_t expires;
+ u64 expires;
int retval;
spin_lock_irqsave(&dev->power.lock, flags);
/* Other scheduled or pending requests need to be canceled. */
pm_runtime_cancel_pending(dev);
- expires = ktime_add(ktime_get(), ms_to_ktime(delay));
- dev->power.timer_expires = ktime_to_ns(expires);
+ expires = ktime_get_mono_fast_ns() + (u64)delay * NSEC_PER_MSEC;
+ dev->power.timer_expires = expires;
dev->power.timer_autosuspends = 0;
hrtimer_start(&dev->power.suspend_timer, expires, HRTIMER_MODE_ABS);
if (!parent)
return -EINVAL;
- for (i = 0; i < core->num_parents; i++)
- if (clk_core_get_parent_by_index(core, i) == parent)
+ for (i = 0; i < core->num_parents; i++) {
+ if (core->parents[i] == parent)
+ return i;
+
+ if (core->parents[i])
+ continue;
+
+ /* Fallback to comparing globally unique names */
+ if (!strcmp(parent->name, core->parent_names[i])) {
+ core->parents[i] = parent;
return i;
+ }
+ }
return -EINVAL;
}
{
struct clk_frac_pll *pll = to_clk_frac_pll(hw);
u32 val, divfi, divff;
- u64 temp64 = parent_rate;
+ u64 temp64;
int ret;
parent_rate *= 8;
rate *= 2;
divfi = rate / parent_rate;
- temp64 *= rate - divfi;
+ temp64 = parent_rate * divfi;
+ temp64 = rate - temp64;
temp64 *= PLL_FRAC_DENOM;
do_div(temp64, parent_rate);
divff = temp64;
#define APMU_DISP1 0x110
#define APMU_CCIC0 0x50
#define APMU_CCIC1 0xf4
-#define APMU_SP 0x68
#define MPMU_UART_PLL 0x14
struct mmp2_clk_unit {
.reg_info = DEFINE_MIX_REG_INFO(4, 16, 2, 6, 32),
};
-static DEFINE_SPINLOCK(sp_lock);
-
static struct mmp_param_mux_clk apmu_mux_clks[] = {
{MMP2_CLK_DISP0_MUX, "disp0_mux", disp_parent_names, ARRAY_SIZE(disp_parent_names), CLK_SET_RATE_PARENT, APMU_DISP0, 6, 2, 0, &disp0_lock},
{MMP2_CLK_DISP1_MUX, "disp1_mux", disp_parent_names, ARRAY_SIZE(disp_parent_names), CLK_SET_RATE_PARENT, APMU_DISP1, 6, 2, 0, &disp1_lock},
{MMP2_CLK_CCIC1, "ccic1_clk", "ccic1_mix_clk", CLK_SET_RATE_PARENT, APMU_CCIC1, 0x1b, 0x1b, 0x0, 0, &ccic1_lock},
{MMP2_CLK_CCIC1_PHY, "ccic1_phy_clk", "ccic1_mix_clk", CLK_SET_RATE_PARENT, APMU_CCIC1, 0x24, 0x24, 0x0, 0, &ccic1_lock},
{MMP2_CLK_CCIC1_SPHY, "ccic1_sphy_clk", "ccic1_sphy_div", CLK_SET_RATE_PARENT, APMU_CCIC1, 0x300, 0x300, 0x0, 0, &ccic1_lock},
- {MMP2_CLK_SP, "sp_clk", NULL, CLK_SET_RATE_PARENT, APMU_SP, 0x1b, 0x1b, 0x0, 0, &sp_lock},
};
static void mmp2_axi_periph_clk_init(struct mmp2_clk_unit *pxa_unit)
"core_bi_pll_test_se",
};
-static const char * const gcc_parent_names_7[] = {
- "bi_tcxo",
+static const char * const gcc_parent_names_7_ao[] = {
+ "bi_tcxo_ao",
"gpll0",
"gpll0_out_even",
"core_bi_pll_test_se",
"core_bi_pll_test_se",
};
+static const char * const gcc_parent_names_8_ao[] = {
+ "bi_tcxo_ao",
+ "gpll0",
+ "core_bi_pll_test_se",
+};
+
static const struct parent_map gcc_parent_map_10[] = {
{ P_BI_TCXO, 0 },
{ P_GPLL0_OUT_MAIN, 1 },
.freq_tbl = ftbl_gcc_cpuss_ahb_clk_src,
.clkr.hw.init = &(struct clk_init_data){
.name = "gcc_cpuss_ahb_clk_src",
- .parent_names = gcc_parent_names_7,
+ .parent_names = gcc_parent_names_7_ao,
.num_parents = 4,
.ops = &clk_rcg2_ops,
},
.freq_tbl = ftbl_gcc_cpuss_rbcpr_clk_src,
.clkr.hw.init = &(struct clk_init_data){
.name = "gcc_cpuss_rbcpr_clk_src",
- .parent_names = gcc_parent_names_8,
+ .parent_names = gcc_parent_names_8_ao,
.num_parents = 3,
.ops = &clk_rcg2_ops,
},
num_dividers = i;
tmp = kcalloc(valid_div + 1, sizeof(*tmp), GFP_KERNEL);
- if (!tmp)
+ if (!tmp) {
+ *table = ERR_PTR(-ENOMEM);
return -ENOMEM;
+ }
valid_div = 0;
*width = 0;
{
struct clk_omap_divider *div;
struct clk_omap_reg *reg;
+ int ret;
if (!setup)
return NULL;
div->flags |= CLK_DIVIDER_POWER_OF_TWO;
div->table = _get_div_table_from_setup(setup, &div->width);
+ if (IS_ERR(div->table)) {
+ ret = PTR_ERR(div->table);
+ kfree(div);
+ return ERR_PTR(ret);
+ }
+
div->shift = setup->bit_shift;
div->latch = -EINVAL;
local_irq_enable();
if (!current_set_polling_and_test()) {
unsigned int loop_count = 0;
- u64 limit = TICK_USEC;
+ u64 limit = TICK_NSEC;
int i;
for (i = 1; i < drv->state_count; i++) {
struct nitrox_device *ndev = cmdq->ndev;
struct nitrox_softreq *sr;
int req_completed = 0, err = 0, budget;
+ completion_t callback;
+ void *cb_arg;
/* check all pending requests */
budget = atomic_read(&cmdq->pending_count);
smp_mb__after_atomic();
/* remove from response list */
response_list_del(sr, cmdq);
-
/* ORH error code */
err = READ_ONCE(*sr->resp.orh) & 0xff;
-
- if (sr->callback)
- sr->callback(sr->cb_arg, err);
+ callback = sr->callback;
+ cb_arg = sr->cb_arg;
softreq_destroy(sr);
+ if (callback)
+ callback(cb_arg, err);
req_completed++;
}
static struct ptdump_info efi_ptdump_info = {
.mm = &efi_mm,
.markers = (struct addr_marker[]){
- { 0, "UEFI runtime start" },
- { DEFAULT_MAP_WINDOW_64, "UEFI runtime end" }
+ { 0, "UEFI runtime start" },
+ { DEFAULT_MAP_WINDOW_64, "UEFI runtime end" },
+ { -1, NULL }
},
.base_addr = 0,
};
static int altr_a10sr_gpio_direction_output(struct gpio_chip *gc,
unsigned int nr, int value)
{
- if (nr <= (ALTR_A10SR_OUT_VALID_RANGE_HI - ALTR_A10SR_LED_VALID_SHIFT))
+ if (nr <= (ALTR_A10SR_OUT_VALID_RANGE_HI - ALTR_A10SR_LED_VALID_SHIFT)) {
+ altr_a10sr_gpio_set(gc, nr, value);
return 0;
+ }
return -EINVAL;
}
static int sprd_eic_get(struct gpio_chip *chip, unsigned int offset)
{
- return sprd_eic_read(chip, offset, SPRD_EIC_DBNC_DATA);
+ struct sprd_eic *sprd_eic = gpiochip_get_data(chip);
+
+ switch (sprd_eic->type) {
+ case SPRD_EIC_DEBOUNCE:
+ return sprd_eic_read(chip, offset, SPRD_EIC_DBNC_DATA);
+ case SPRD_EIC_ASYNC:
+ return sprd_eic_read(chip, offset, SPRD_EIC_ASYNC_DATA);
+ case SPRD_EIC_SYNC:
+ return sprd_eic_read(chip, offset, SPRD_EIC_SYNC_DATA);
+ default:
+ return -ENOTSUPP;
+ }
}
static int sprd_eic_direction_input(struct gpio_chip *chip, unsigned int offset)
irq_set_handler_locked(data, handle_edge_irq);
break;
case IRQ_TYPE_EDGE_BOTH:
+ sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTMODE, 0);
sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTBOTH, 1);
irq_set_handler_locked(data, handle_edge_irq);
break;
*/
struct pcf857x {
struct gpio_chip chip;
+ struct irq_chip irqchip;
struct i2c_client *client;
struct mutex lock; /* protect 'out' */
unsigned out; /* software latch */
mutex_unlock(&gpio->lock);
}
-static struct irq_chip pcf857x_irq_chip = {
- .name = "pcf857x",
- .irq_enable = pcf857x_irq_enable,
- .irq_disable = pcf857x_irq_disable,
- .irq_ack = noop,
- .irq_mask = noop,
- .irq_unmask = noop,
- .irq_set_wake = pcf857x_irq_set_wake,
- .irq_bus_lock = pcf857x_irq_bus_lock,
- .irq_bus_sync_unlock = pcf857x_irq_bus_sync_unlock,
-};
-
/*-------------------------------------------------------------------------*/
static int pcf857x_probe(struct i2c_client *client,
/* Enable irqchip if we have an interrupt */
if (client->irq) {
+ gpio->irqchip.name = "pcf857x",
+ gpio->irqchip.irq_enable = pcf857x_irq_enable,
+ gpio->irqchip.irq_disable = pcf857x_irq_disable,
+ gpio->irqchip.irq_ack = noop,
+ gpio->irqchip.irq_mask = noop,
+ gpio->irqchip.irq_unmask = noop,
+ gpio->irqchip.irq_set_wake = pcf857x_irq_set_wake,
+ gpio->irqchip.irq_bus_lock = pcf857x_irq_bus_lock,
+ gpio->irqchip.irq_bus_sync_unlock = pcf857x_irq_bus_sync_unlock,
status = gpiochip_irqchip_add_nested(&gpio->chip,
- &pcf857x_irq_chip,
+ &gpio->irqchip,
0, handle_level_irq,
IRQ_TYPE_NONE);
if (status) {
if (status)
goto fail;
- gpiochip_set_nested_irqchip(&gpio->chip, &pcf857x_irq_chip,
+ gpiochip_set_nested_irqchip(&gpio->chip, &gpio->irqchip,
client->irq);
gpio->irq_parent = client->irq;
}
struct vf610_gpio_port *port;
struct resource *iores;
struct gpio_chip *gc;
+ int i;
int ret;
port = devm_kzalloc(&pdev->dev, sizeof(*port), GFP_KERNEL);
if (ret < 0)
return ret;
+ /* Mask all GPIO interrupts */
+ for (i = 0; i < gc->ngpio; i++)
+ vf610_gpio_writel(0, port->base + PORT_PCR(i));
+
/* Clear the interrupt status register for all GPIO's */
vf610_gpio_writel(~0, port->base + PORT_ISFR);
/* Do not leak kernel stack to userspace */
memset(&ge, 0, sizeof(ge));
- ge.timestamp = le->timestamp;
+ /*
+ * We may be running from a nested threaded interrupt in which case
+ * we didn't get the timestamp from lineevent_irq_handler().
+ */
+ if (!le->timestamp)
+ ge.timestamp = ktime_get_real_ns();
+ else
+ ge.timestamp = le->timestamp;
if (le->eflags & GPIOEVENT_REQUEST_RISING_EDGE
&& le->eflags & GPIOEVENT_REQUEST_FALLING_EDGE) {
ret = i3c_master_retrieve_dev_info(newdev);
if (ret)
- goto err_free_dev;
+ goto err_detach_dev;
olddev = i3c_master_search_i3c_dev_duplicate(newdev);
if (olddev) {
spin_unlock_irqrestore(&master->xferqueue.lock, flags);
}
-static void dw_i3c_master_dequeue_xfer(struct dw_i3c_master *master,
- struct dw_i3c_xfer *xfer)
+static void dw_i3c_master_dequeue_xfer_locked(struct dw_i3c_master *master,
+ struct dw_i3c_xfer *xfer)
{
- unsigned long flags;
-
- spin_lock_irqsave(&master->xferqueue.lock, flags);
if (master->xferqueue.cur == xfer) {
u32 status;
} else {
list_del_init(&xfer->node);
}
+}
+
+static void dw_i3c_master_dequeue_xfer(struct dw_i3c_master *master,
+ struct dw_i3c_xfer *xfer)
+{
+ unsigned long flags;
+
+ spin_lock_irqsave(&master->xferqueue.lock, flags);
+ dw_i3c_master_dequeue_xfer_locked(master, xfer);
spin_unlock_irqrestore(&master->xferqueue.lock, flags);
}
complete(&xfer->comp);
if (ret < 0) {
- dw_i3c_master_dequeue_xfer(master, xfer);
+ dw_i3c_master_dequeue_xfer_locked(master, xfer);
writel(readl(master->regs + DEVICE_CTRL) | DEV_CTRL_RESUME,
master->regs + DEVICE_CTRL);
}
int ide_queue_sense_rq(ide_drive_t *drive, void *special)
{
- struct request *sense_rq = drive->sense_rq;
+ ide_hwif_t *hwif = drive->hwif;
+ struct request *sense_rq;
+ unsigned long flags;
+
+ spin_lock_irqsave(&hwif->lock, flags);
/* deferred failure from ide_prep_sense() */
if (!drive->sense_rq_armed) {
printk(KERN_WARNING PFX "%s: error queuing a sense request\n",
drive->name);
+ spin_unlock_irqrestore(&hwif->lock, flags);
return -ENOMEM;
}
+ sense_rq = drive->sense_rq;
ide_req(sense_rq)->special = special;
drive->sense_rq_armed = false;
drive->hwif->rq = NULL;
ide_insert_request_head(drive, sense_rq);
+ spin_unlock_irqrestore(&hwif->lock, flags);
return 0;
}
EXPORT_SYMBOL_GPL(ide_queue_sense_rq);
}
if (!blk_update_request(rq, error, nr_bytes)) {
- if (rq == drive->sense_rq)
+ if (rq == drive->sense_rq) {
drive->sense_rq = NULL;
+ drive->sense_rq_active = false;
+ }
__blk_mq_end_request(rq, error);
return 0;
blk_mq_delay_run_hw_queue(q->queue_hw_ctx[0], 3);
}
-/*
- * Issue a new request to a device.
- */
-blk_status_t ide_queue_rq(struct blk_mq_hw_ctx *hctx,
- const struct blk_mq_queue_data *bd)
+blk_status_t ide_issue_rq(ide_drive_t *drive, struct request *rq,
+ bool local_requeue)
{
- ide_drive_t *drive = hctx->queue->queuedata;
- ide_hwif_t *hwif = drive->hwif;
+ ide_hwif_t *hwif = drive->hwif;
struct ide_host *host = hwif->host;
- struct request *rq = bd->rq;
ide_startstop_t startstop;
if (!blk_rq_is_passthrough(rq) && !(rq->rq_flags & RQF_DONTPREP)) {
if (ide_lock_host(host, hwif))
return BLK_STS_DEV_RESOURCE;
- blk_mq_start_request(rq);
-
spin_lock_irq(&hwif->lock);
if (!ide_lock_port(hwif)) {
drive->dev_flags &= ~(IDE_DFLAG_SLEEPING | IDE_DFLAG_PARKED);
/*
- * we know that the queue isn't empty, but this can happen
- * if ->prep_rq() decides to kill a request
- */
- if (!rq) {
- rq = bd->rq;
- if (!rq) {
- ide_unlock_port(hwif);
- goto out;
- }
- }
-
- /*
* Sanity: don't accept a request that isn't a PM request
* if we are currently power managed. This is very important as
* blk_stop_queue() doesn't prevent the blk_fetch_request()
}
} else {
plug_device:
+ if (local_requeue)
+ list_add(&rq->queuelist, &drive->rq_list);
spin_unlock_irq(&hwif->lock);
ide_unlock_host(host);
- ide_requeue_and_plug(drive, rq);
+ if (!local_requeue)
+ ide_requeue_and_plug(drive, rq);
return BLK_STS_OK;
}
return BLK_STS_OK;
}
+/*
+ * Issue a new request to a device.
+ */
+blk_status_t ide_queue_rq(struct blk_mq_hw_ctx *hctx,
+ const struct blk_mq_queue_data *bd)
+{
+ ide_drive_t *drive = hctx->queue->queuedata;
+ ide_hwif_t *hwif = drive->hwif;
+
+ spin_lock_irq(&hwif->lock);
+ if (drive->sense_rq_active) {
+ spin_unlock_irq(&hwif->lock);
+ return BLK_STS_DEV_RESOURCE;
+ }
+ spin_unlock_irq(&hwif->lock);
+
+ blk_mq_start_request(bd->rq);
+ return ide_issue_rq(drive, bd->rq, false);
+}
+
static int drive_is_ready(ide_drive_t *drive)
{
ide_hwif_t *hwif = drive->hwif;
void ide_insert_request_head(ide_drive_t *drive, struct request *rq)
{
- ide_hwif_t *hwif = drive->hwif;
- unsigned long flags;
-
- spin_lock_irqsave(&hwif->lock, flags);
+ drive->sense_rq_active = true;
list_add_tail(&rq->queuelist, &drive->rq_list);
- spin_unlock_irqrestore(&hwif->lock, flags);
-
kblockd_schedule_work(&drive->rq_work);
}
EXPORT_SYMBOL_GPL(ide_insert_request_head);
scsi_req(rq)->cmd[0] = REQ_UNPARK_HEADS;
scsi_req(rq)->cmd_len = 1;
ide_req(rq)->type = ATA_PRIV_MISC;
+ spin_lock_irq(&hwif->lock);
ide_insert_request_head(drive, rq);
+ spin_unlock_irq(&hwif->lock);
out:
return;
ide_drive_t *drive = container_of(work, ide_drive_t, rq_work);
ide_hwif_t *hwif = drive->hwif;
struct request *rq;
+ blk_status_t ret;
LIST_HEAD(list);
- spin_lock_irq(&hwif->lock);
- if (!list_empty(&drive->rq_list))
- list_splice_init(&drive->rq_list, &list);
- spin_unlock_irq(&hwif->lock);
+ blk_mq_quiesce_queue(drive->queue);
- while (!list_empty(&list)) {
- rq = list_first_entry(&list, struct request, queuelist);
+ ret = BLK_STS_OK;
+ spin_lock_irq(&hwif->lock);
+ while (!list_empty(&drive->rq_list)) {
+ rq = list_first_entry(&drive->rq_list, struct request, queuelist);
list_del_init(&rq->queuelist);
- blk_execute_rq_nowait(drive->queue, rq->rq_disk, rq, true, NULL);
+
+ spin_unlock_irq(&hwif->lock);
+ ret = ide_issue_rq(drive, rq, true);
+ spin_lock_irq(&hwif->lock);
}
+ spin_unlock_irq(&hwif->lock);
+
+ blk_mq_unquiesce_queue(drive->queue);
+
+ if (ret != BLK_STS_OK)
+ kblockd_schedule_work(&drive->rq_work);
}
static const u8 ide_hwif_to_major[] =
#endif
struct ib_device *ib_device_get_by_index(u32 ifindex);
-void ib_device_put(struct ib_device *device);
/* RDMA device netlink */
void nldev_init(void);
void nldev_exit(void);
down_read(&lists_rwsem);
device = __ib_device_get_by_index(index);
if (device) {
- /* Do not return a device if unregistration has started. */
- if (!refcount_inc_not_zero(&device->refcount))
+ if (!ib_device_try_get(device))
device = NULL;
}
up_read(&lists_rwsem);
return device;
}
+/**
+ * ib_device_put - Release IB device reference
+ * @device: device whose reference to be released
+ *
+ * ib_device_put() releases reference to the IB device to allow it to be
+ * unregistered and eventually free.
+ */
void ib_device_put(struct ib_device *device)
{
if (refcount_dec_and_test(&device->refcount))
complete(&device->unreg_completion);
}
+EXPORT_SYMBOL(ib_device_put);
static struct ib_device *__ib_device_get_by_name(const char *name)
{
rwlock_init(&device->client_data_lock);
INIT_LIST_HEAD(&device->client_data_list);
INIT_LIST_HEAD(&device->port_list);
- refcount_set(&device->refcount, 1);
init_completion(&device->unreg_completion);
return device;
goto cg_cleanup;
}
+ refcount_set(&device->refcount, 1);
device->reg_state = IB_DEV_REGISTERED;
list_for_each_entry(client, &client_list, list)
umem->writable = 1;
umem->is_odp = 1;
odp_data->per_mm = per_mm;
+ umem->owning_mm = per_mm->mm;
+ mmgrab(umem->owning_mm);
mutex_init(&odp_data->umem_mutex);
init_completion(&odp_data->notifier_completion);
out_page_list:
vfree(odp_data->page_list);
out_odp_data:
+ mmdrop(umem->owning_mm);
kfree(odp_data);
return ERR_PTR(ret);
}
if (atomic_dec_and_test(&file->device->refcount))
ib_uverbs_comp_dev(file->device);
+ if (file->async_file)
+ kref_put(&file->async_file->ref,
+ ib_uverbs_release_async_event_file);
put_device(&file->device->dev);
kfree(file);
}
/* Get an arbitrary mm pointer that hasn't been cleaned yet */
mutex_lock(&ufile->umap_lock);
- if (!list_empty(&ufile->umaps)) {
- mm = list_first_entry(&ufile->umaps,
- struct rdma_umap_priv, list)
- ->vma->vm_mm;
- mmget(mm);
+ while (!list_empty(&ufile->umaps)) {
+ int ret;
+
+ priv = list_first_entry(&ufile->umaps,
+ struct rdma_umap_priv, list);
+ mm = priv->vma->vm_mm;
+ ret = mmget_not_zero(mm);
+ if (!ret) {
+ list_del_init(&priv->list);
+ mm = NULL;
+ continue;
+ }
+ break;
}
mutex_unlock(&ufile->umap_lock);
if (!mm)
list_del_init(&file->list);
mutex_unlock(&file->device->lists_mutex);
- if (file->async_file)
- kref_put(&file->async_file->ref,
- ib_uverbs_release_async_event_file);
-
kref_put(&file->ref, ib_uverbs_release_file);
return 0;
static int UVERBS_HANDLER(UVERBS_METHOD_QUERY_PORT)(
struct uverbs_attr_bundle *attrs)
{
- struct ib_device *ib_dev = attrs->ufile->device->ib_dev;
+ struct ib_device *ib_dev;
struct ib_port_attr attr = {};
struct ib_uverbs_query_port_resp_ex resp = {};
+ struct ib_ucontext *ucontext;
int ret;
u8 port_num;
+ ucontext = ib_uverbs_get_ucontext(attrs);
+ if (IS_ERR(ucontext))
+ return PTR_ERR(ucontext);
+ ib_dev = ucontext->device;
+
/* FIXME: Extend the UAPI_DEF_OBJ_NEEDS_FN stuff.. */
if (!ib_dev->ops.query_port)
return -EOPNOTSUPP;
vmf = 1;
break;
case STATUS:
- if (flags & (unsigned long)(VM_WRITE | VM_EXEC)) {
+ if (flags & VM_WRITE) {
ret = -EPERM;
goto done;
}
opcode == IB_OPCODE_UD_SEND_ONLY_WITH_IMMEDIATE) {
wc.ex.imm_data = packet->ohdr->u.ud.imm_data;
wc.wc_flags = IB_WC_WITH_IMM;
- tlen -= sizeof(u32);
} else if (opcode == IB_OPCODE_UD_SEND_ONLY) {
wc.ex.imm_data = 0;
wc.wc_flags = 0;
struct ib_udata *udata)
{
struct hns_roce_dev *hr_dev = to_hr_dev(pd->device);
+ struct hns_roce_ib_create_srq_resp resp = {};
struct hns_roce_srq *srq;
int srq_desc_size;
int srq_buf_size;
srq->event = hns_roce_ib_srq_event;
srq->ibsrq.ext.xrc.srq_num = srq->srqn;
+ resp.srqn = srq->srqn;
if (udata) {
- if (ib_copy_to_udata(udata, &srq->srqn, sizeof(__u32))) {
+ if (ib_copy_to_udata(udata, &resp,
+ min(udata->outlen, sizeof(resp)))) {
ret = -EFAULT;
- goto err_wrid;
+ goto err_srqc_alloc;
}
}
return &srq->ibsrq;
+err_srqc_alloc:
+ hns_roce_srq_free(hr_dev, srq);
+
err_wrid:
kvfree(srq->wrid);
sqp_mad = (struct mlx4_mad_snd_buf *) (sqp->tx_ring[wire_tx_ix].buf.addr);
if (sqp->tx_ring[wire_tx_ix].ah)
- rdma_destroy_ah(sqp->tx_ring[wire_tx_ix].ah, 0);
+ mlx4_ib_destroy_ah(sqp->tx_ring[wire_tx_ix].ah, 0);
sqp->tx_ring[wire_tx_ix].ah = ah;
ib_dma_sync_single_for_cpu(&dev->ib_dev,
sqp->tx_ring[wire_tx_ix].buf.map,
if (wc.status == IB_WC_SUCCESS) {
switch (wc.opcode) {
case IB_WC_SEND:
- rdma_destroy_ah(sqp->tx_ring[wc.wr_id &
+ mlx4_ib_destroy_ah(sqp->tx_ring[wc.wr_id &
(MLX4_NUM_TUNNEL_BUFS - 1)].ah, 0);
sqp->tx_ring[wc.wr_id & (MLX4_NUM_TUNNEL_BUFS - 1)].ah
= NULL;
" status = %d, wrid = 0x%llx\n",
ctx->slave, wc.status, wc.wr_id);
if (!MLX4_TUN_IS_RECV(wc.wr_id)) {
- rdma_destroy_ah(sqp->tx_ring[wc.wr_id &
+ mlx4_ib_destroy_ah(sqp->tx_ring[wc.wr_id &
(MLX4_NUM_TUNNEL_BUFS - 1)].ah, 0);
sqp->tx_ring[wc.wr_id & (MLX4_NUM_TUNNEL_BUFS - 1)].ah
= NULL;
UAPI_DEF_IS_OBJ_SUPPORTED(flow_is_supported)),
UAPI_DEF_CHAIN_OBJ_TREE(
UVERBS_OBJECT_FLOW,
- &mlx5_ib_fs,
- UAPI_DEF_IS_OBJ_SUPPORTED(flow_is_supported)),
+ &mlx5_ib_fs),
UAPI_DEF_CHAIN_OBJ_TREE(UVERBS_OBJECT_FLOW_ACTION,
&mlx5_ib_flow_actions),
{},
struct prefetch_mr_work *w =
container_of(work, struct prefetch_mr_work, work);
- if (w->dev->ib_dev.reg_state == IB_DEV_REGISTERED)
+ if (ib_device_try_get(&w->dev->ib_dev)) {
mlx5_ib_prefetch_sg_list(w->dev, w->pf_flags, w->sg_list,
w->num_sge);
-
+ ib_device_put(&w->dev->ib_dev);
+ }
+ put_device(&w->dev->ib_dev.dev);
kfree(w);
}
return mlx5_ib_prefetch_sg_list(dev, pf_flags, sg_list,
num_sge);
- if (dev->ib_dev.reg_state != IB_DEV_REGISTERED)
- return -ENODEV;
-
work = kvzalloc(struct_size(work, sg_list, num_sge), GFP_KERNEL);
if (!work)
return -ENOMEM;
memcpy(work->sg_list, sg_list, num_sge * sizeof(struct ib_sge));
+ get_device(&dev->ib_dev.dev);
work->dev = dev;
work->pf_flags = pf_flags;
work->num_sge = num_sge;
}
if (!check_flags_mask(ucmd.flags,
+ MLX5_QP_FLAG_ALLOW_SCATTER_CQE |
+ MLX5_QP_FLAG_BFREG_INDEX |
+ MLX5_QP_FLAG_PACKET_BASED_CREDIT_MODE |
+ MLX5_QP_FLAG_SCATTER_CQE |
MLX5_QP_FLAG_SIGNATURE |
- MLX5_QP_FLAG_SCATTER_CQE |
- MLX5_QP_FLAG_TUNNEL_OFFLOADS |
- MLX5_QP_FLAG_BFREG_INDEX |
- MLX5_QP_FLAG_TYPE_DCT |
- MLX5_QP_FLAG_TYPE_DCI |
- MLX5_QP_FLAG_ALLOW_SCATTER_CQE |
- MLX5_QP_FLAG_PACKET_BASED_CREDIT_MODE))
+ MLX5_QP_FLAG_TIR_ALLOW_SELF_LB_MC |
+ MLX5_QP_FLAG_TIR_ALLOW_SELF_LB_UC |
+ MLX5_QP_FLAG_TUNNEL_OFFLOADS |
+ MLX5_QP_FLAG_TYPE_DCI |
+ MLX5_QP_FLAG_TYPE_DCT))
return -EINVAL;
err = get_qp_user_index(to_mucontext(pd->uobject->context),
opcode == IB_OPCODE_UD_SEND_ONLY_WITH_IMMEDIATE) {
wc.ex.imm_data = ohdr->u.ud.imm_data;
wc.wc_flags = IB_WC_WITH_IMM;
- tlen -= sizeof(u32);
} else if (opcode == IB_OPCODE_UD_SEND_ONLY) {
wc.ex.imm_data = 0;
wc.wc_flags = 0;
goto op_err;
if (!ret)
goto rnr_nak;
+ if (wqe->length > qp->r_len)
+ goto inv_err;
break;
case IB_WR_RDMA_WRITE_WITH_IMM:
goto err;
inv_err:
- send_status = IB_WC_REM_INV_REQ_ERR;
+ send_status =
+ sqp->ibqp.qp_type == IB_QPT_RC ?
+ IB_WC_REM_INV_REQ_ERR :
+ IB_WC_SUCCESS;
wc.status = IB_WC_LOC_QP_OP_ERR;
goto err;
struct list_head list;
struct net_device *dev;
struct ipoib_neigh *neigh;
- struct ipoib_path *path;
struct ipoib_tx_buf *tx_ring;
unsigned int tx_head;
unsigned int tx_tail;
neigh->cm = tx;
tx->neigh = neigh;
- tx->path = path;
tx->dev = dev;
list_add(&tx->list, &priv->cm.start_list);
set_bit(IPOIB_FLAG_INITIALIZED, &tx->flags);
neigh->daddr + QPN_AND_OPTIONS_OFFSET);
goto free_neigh;
}
- memcpy(&pathrec, &p->path->pathrec, sizeof(pathrec));
+ memcpy(&pathrec, &path->pathrec, sizeof(pathrec));
spin_unlock_irqrestore(&priv->lock, flags);
netif_tx_unlock_bh(dev);
#include <linux/of.h>
#include <linux/slab.h>
#include <linux/delay.h>
-#include <linux/clk.h>
/*
* The OLPC XO-1.75 and XO-4 laptops do not have a hardware PS/2 controller.
struct serio *kbio;
struct serio *padio;
void __iomem *base;
- struct clk *clk;
int open_count;
int irq;
};
struct olpc_apsp *priv = port->port_data;
unsigned int tmp;
unsigned long l;
- int error;
if (priv->open_count++ == 0) {
- error = clk_prepare_enable(priv->clk);
- if (error)
- return error;
-
l = readl(priv->base + COMMAND_FIFO_STATUS);
if (!(l & CMD_STS_MASK)) {
dev_err(priv->dev, "SP cannot accept commands.\n");
- clk_disable_unprepare(priv->clk);
return -EIO;
}
/* Disable interrupt 0 */
tmp = readl(priv->base + PJ_INTERRUPT_MASK);
writel(tmp | INT_0, priv->base + PJ_INTERRUPT_MASK);
-
- clk_disable_unprepare(priv->clk);
}
}
if (priv->irq < 0)
return priv->irq;
- priv->clk = devm_clk_get(&pdev->dev, "sp");
- if (IS_ERR(priv->clk))
- return PTR_ERR(priv->clk);
-
/* KEYBOARD */
kb_serio = kzalloc(sizeof(struct serio), GFP_KERNEL);
if (!kb_serio)
static void do_detach(struct iommu_dev_data *dev_data)
{
+ struct protection_domain *domain = dev_data->domain;
struct amd_iommu *iommu;
u16 alias;
iommu = amd_iommu_rlookup_table[dev_data->devid];
alias = dev_data->alias;
- /* decrease reference counters */
- dev_data->domain->dev_iommu[iommu->index] -= 1;
- dev_data->domain->dev_cnt -= 1;
-
/* Update data structures */
dev_data->domain = NULL;
list_del(&dev_data->list);
/* Flush the DTE entry */
device_flush_dte(dev_data);
+
+ /* Flush IOTLB */
+ domain_flush_tlb_pde(domain);
+
+ /* Wait for the flushes to finish */
+ domain_flush_complete(domain);
+
+ /* decrease reference counters - needs to happen after the flushes */
+ domain->dev_iommu[iommu->index] -= 1;
+ domain->dev_cnt -= 1;
}
/*
bus_addr = address + s->dma_address + (j << PAGE_SHIFT);
iommu_unmap_page(domain, bus_addr, PAGE_SIZE);
- if (--mapped_pages)
+ if (--mapped_pages == 0)
goto out_free_iova;
}
}
out_free_iova:
- free_iova_fast(&dma_dom->iovad, address, npages);
+ free_iova_fast(&dma_dom->iovad, address >> PAGE_SHIFT, npages);
out_err:
return 0;
struct iommu_resv_region *entry, *next;
list_for_each_entry_safe(entry, next, head, list) {
- if (entry->type == IOMMU_RESV_RESERVED)
+ if (entry->type == IOMMU_RESV_MSI)
kfree(entry);
}
}
iommu_spec.args_count = count;
mtk_iommu_create_mapping(dev, &iommu_spec);
+
+ /* dev->iommu_fwspec might have changed */
+ fwspec = dev_iommu_fwspec_get(dev);
+
of_node_put(iommu_spec.np);
}
unsigned int mask = 1u << d->hwirq;
if (mask & (XCHAL_INTTYPE_MASK_EXTERN_EDGE |
- XCHAL_INTTYPE_MASK_EXTERN_LEVEL)) {
- set_er(1u << (xtensa_get_ext_irq_no(d->hwirq) -
- HW_IRQ_MX_BASE), MIENG);
- } else {
- mask = __this_cpu_read(cached_irq_mask) & ~mask;
- __this_cpu_write(cached_irq_mask, mask);
- xtensa_set_sr(mask, intenable);
+ XCHAL_INTTYPE_MASK_EXTERN_LEVEL)) {
+ unsigned int ext_irq = xtensa_get_ext_irq_no(d->hwirq);
+
+ if (ext_irq >= HW_IRQ_MX_BASE) {
+ set_er(1u << (ext_irq - HW_IRQ_MX_BASE), MIENG);
+ return;
+ }
}
+ mask = __this_cpu_read(cached_irq_mask) & ~mask;
+ __this_cpu_write(cached_irq_mask, mask);
+ xtensa_set_sr(mask, intenable);
}
static void xtensa_mx_irq_unmask(struct irq_data *d)
unsigned int mask = 1u << d->hwirq;
if (mask & (XCHAL_INTTYPE_MASK_EXTERN_EDGE |
- XCHAL_INTTYPE_MASK_EXTERN_LEVEL)) {
- set_er(1u << (xtensa_get_ext_irq_no(d->hwirq) -
- HW_IRQ_MX_BASE), MIENGSET);
- } else {
- mask |= __this_cpu_read(cached_irq_mask);
- __this_cpu_write(cached_irq_mask, mask);
- xtensa_set_sr(mask, intenable);
+ XCHAL_INTTYPE_MASK_EXTERN_LEVEL)) {
+ unsigned int ext_irq = xtensa_get_ext_irq_no(d->hwirq);
+
+ if (ext_irq >= HW_IRQ_MX_BASE) {
+ set_er(1u << (ext_irq - HW_IRQ_MX_BASE), MIENGSET);
+ return;
+ }
}
+ mask |= __this_cpu_read(cached_irq_mask);
+ __this_cpu_write(cached_irq_mask, mask);
+ xtensa_set_sr(mask, intenable);
}
static void xtensa_mx_irq_enable(struct irq_data *d)
static int xtensa_mx_irq_retrigger(struct irq_data *d)
{
- xtensa_set_sr(1 << d->hwirq, intset);
+ unsigned int mask = 1u << d->hwirq;
+
+ if (WARN_ON(mask & ~XCHAL_INTTYPE_MASK_SOFTWARE))
+ return 0;
+ xtensa_set_sr(mask, intset);
return 1;
}
static int xtensa_irq_retrigger(struct irq_data *d)
{
- xtensa_set_sr(1 << d->hwirq, intset);
+ unsigned int mask = 1u << d->hwirq;
+
+ if (WARN_ON(mask & ~XCHAL_INTTYPE_MASK_SOFTWARE))
+ return 0;
+ xtensa_set_sr(mask, intset);
return 1;
}
}
static struct stripe_head *
-r5c_recovery_alloc_stripe(struct r5conf *conf,
- sector_t stripe_sect)
+r5c_recovery_alloc_stripe(
+ struct r5conf *conf,
+ sector_t stripe_sect,
+ int noblock)
{
struct stripe_head *sh;
- sh = raid5_get_active_stripe(conf, stripe_sect, 0, 1, 0);
+ sh = raid5_get_active_stripe(conf, stripe_sect, 0, noblock, 0);
if (!sh)
return NULL; /* no more stripe available */
stripe_sect);
if (!sh) {
- sh = r5c_recovery_alloc_stripe(conf, stripe_sect);
+ sh = r5c_recovery_alloc_stripe(conf, stripe_sect, 1);
/*
* cannot get stripe from raid5_get_active_stripe
* try replay some stripes
r5c_recovery_replay_stripes(
cached_stripe_list, ctx);
sh = r5c_recovery_alloc_stripe(
- conf, stripe_sect);
+ conf, stripe_sect, 1);
}
if (!sh) {
+ int new_size = conf->min_nr_stripes * 2;
pr_debug("md/raid:%s: Increasing stripe cache size to %d to recovery data on journal.\n",
mdname(mddev),
- conf->min_nr_stripes * 2);
- raid5_set_cache_size(mddev,
- conf->min_nr_stripes * 2);
- sh = r5c_recovery_alloc_stripe(conf,
- stripe_sect);
+ new_size);
+ ret = raid5_set_cache_size(mddev, new_size);
+ if (conf->min_nr_stripes <= new_size / 2) {
+ pr_err("md/raid:%s: Cannot increase cache size, ret=%d, new_size=%d, min_nr_stripes=%d, max_nr_stripes=%d\n",
+ mdname(mddev),
+ ret,
+ new_size,
+ conf->min_nr_stripes,
+ conf->max_nr_stripes);
+ return -ENOMEM;
+ }
+ sh = r5c_recovery_alloc_stripe(
+ conf, stripe_sect, 0);
}
if (!sh) {
pr_err("md/raid:%s: Cannot get enough stripes due to memory pressure. Recovery failed.\n",
- mdname(mddev));
+ mdname(mddev));
return -ENOMEM;
}
list_add_tail(&sh->lru, cached_stripe_list);
int
raid5_set_cache_size(struct mddev *mddev, int size)
{
+ int result = 0;
struct r5conf *conf = mddev->private;
if (size <= 16 || size > 32768)
mutex_lock(&conf->cache_size_mutex);
while (size > conf->max_nr_stripes)
- if (!grow_one_stripe(conf, GFP_KERNEL))
+ if (!grow_one_stripe(conf, GFP_KERNEL)) {
+ conf->min_nr_stripes = conf->max_nr_stripes;
+ result = -ENOMEM;
break;
+ }
mutex_unlock(&conf->cache_size_mutex);
- return 0;
+ return result;
}
EXPORT_SYMBOL(raid5_set_cache_size);
config MFD_TPS68470
bool "TI TPS68470 Power Management / LED chips"
- depends on ACPI && I2C=y
+ depends on ACPI && PCI && I2C=y
select MFD_CORE
select REGMAP_I2C
select I2C_DESIGNWARE_PLATFORM
err:
dev_dbg(dev, "%s -> err %d\n", __func__, ret);
+ if (host->dma_chan_rxtx)
+ dma_release_channel(host->dma_chan_rxtx);
mmc_free_host(mmc);
return ret;
if (timing == MMC_TIMING_MMC_HS400 &&
host->dev_comp->hs400_tune)
- sdr_set_field(host->base + PAD_CMD_TUNE,
+ sdr_set_field(host->base + tune_reg,
MSDC_PAD_TUNE_CMDRRDLY,
host->hs400_cmd_int_delay);
dev_dbg(host->dev, "sclk: %d, timing: %d\n", host->mmc->actual_clock,
if (skb->len == 0) {
struct sk_buff *tmp = skb_dequeue(&ser->head);
WARN_ON(tmp != skb);
- if (in_interrupt())
- dev_kfree_skb_irq(skb);
- else
- kfree_skb(skb);
+ dev_consume_skb_any(skb);
}
}
/* Send flow off if queue is empty */
if (port < 9)
return 0;
- return mv88e6390_serdes_irq_setup(chip, port);
+ return mv88e6390x_serdes_irq_setup(chip, port);
}
void mv88e6390x_serdes_irq_free(struct mv88e6xxx_chip *chip, int port)
if (skb) {
dev->stats.tx_packets++;
dev->stats.tx_bytes += skb->len;
- dev_kfree_skb_irq(skb);
+ dev_consume_skb_irq(skb);
info->skb = NULL;
}
& 0xffff;
if (inuse) { /* Tx FIFO is not empty */
- ready = priv->tx_prod - priv->tx_cons - inuse - 1;
+ ready = max_t(int,
+ priv->tx_prod - priv->tx_cons - inuse - 1, 0);
} else {
/* Check for buffered last packet */
status = csrrd32(priv->tx_dma_csr, msgdma_csroffs(status));
pci_unmap_single(lp->pci_dev, lp->tx_dma_addr[tx_index],
lp->tx_skbuff[tx_index]->len,
PCI_DMA_TODEVICE);
- dev_kfree_skb_irq (lp->tx_skbuff[tx_index]);
+ dev_consume_skb_irq(lp->tx_skbuff[tx_index]);
lp->tx_skbuff[tx_index] = NULL;
lp->tx_dma_addr[tx_index] = 0;
}
if (bp->tx_bufs[bp->tx_empty]) {
++dev->stats.tx_packets;
- dev_kfree_skb_irq(bp->tx_bufs[bp->tx_empty]);
+ dev_consume_skb_irq(bp->tx_bufs[bp->tx_empty]);
}
bp->tx_bufs[bp->tx_empty] = NULL;
bp->tx_fullup = 0;
bytes_compl += skb->len;
pkts_compl++;
- dev_kfree_skb_irq(skb);
+ dev_consume_skb_irq(skb);
}
netdev_completed_queue(bp->dev, pkts_compl, bytes_compl);
}
skb_copy_from_linear_data(skb, skb_put(bounce_skb, len), len);
- dev_kfree_skb_any(skb);
+ dev_consume_skb_any(skb);
skb = bounce_skb;
}
#define MACB_CAPS_JUMBO 0x00000020
#define MACB_CAPS_GEM_HAS_PTP 0x00000040
#define MACB_CAPS_BD_RD_PREFETCH 0x00000080
+#define MACB_CAPS_NEEDS_RSTONUBR 0x00000100
#define MACB_CAPS_FIFO_MODE 0x10000000
#define MACB_CAPS_GIGABIT_MODE_AVAILABLE 0x20000000
#define MACB_CAPS_SG_DISABLED 0x40000000
int rx_bd_rd_prefetch;
int tx_bd_rd_prefetch;
+
+ u32 rx_intr_mask;
};
#ifdef CONFIG_MACB_USE_HWSTAMP
/* level of occupied TX descriptors under which we wake up TX process */
#define MACB_TX_WAKEUP_THRESH(bp) (3 * (bp)->tx_ring_size / 4)
-#define MACB_RX_INT_FLAGS (MACB_BIT(RCOMP) | MACB_BIT(RXUBR) \
- | MACB_BIT(ISR_ROVR))
+#define MACB_RX_INT_FLAGS (MACB_BIT(RCOMP) | MACB_BIT(ISR_ROVR))
#define MACB_TX_ERR_FLAGS (MACB_BIT(ISR_TUND) \
| MACB_BIT(ISR_RLE) \
| MACB_BIT(TXERR))
queue_writel(queue, ISR, MACB_BIT(RCOMP));
napi_reschedule(napi);
} else {
- queue_writel(queue, IER, MACB_RX_INT_FLAGS);
+ queue_writel(queue, IER, bp->rx_intr_mask);
}
}
u32 ctrl;
for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) {
- queue_writel(queue, IDR, MACB_RX_INT_FLAGS |
+ queue_writel(queue, IDR, bp->rx_intr_mask |
MACB_TX_INT_FLAGS |
MACB_BIT(HRESP));
}
/* Enable interrupts */
queue_writel(queue, IER,
- MACB_RX_INT_FLAGS |
+ bp->rx_intr_mask |
MACB_TX_INT_FLAGS |
MACB_BIT(HRESP));
}
(unsigned int)(queue - bp->queues),
(unsigned long)status);
- if (status & MACB_RX_INT_FLAGS) {
+ if (status & bp->rx_intr_mask) {
/* There's no point taking any more interrupts
* until we have processed the buffers. The
* scheduling call may fail if the poll routine
* is already scheduled, so disable interrupts
* now.
*/
- queue_writel(queue, IDR, MACB_RX_INT_FLAGS);
+ queue_writel(queue, IDR, bp->rx_intr_mask);
if (bp->caps & MACB_CAPS_ISR_CLEAR_ON_WRITE)
queue_writel(queue, ISR, MACB_BIT(RCOMP));
/* There is a hardware issue under heavy load where DMA can
* stop, this causes endless "used buffer descriptor read"
* interrupts but it can be cleared by re-enabling RX. See
- * the at91 manual, section 41.3.1 or the Zynq manual
- * section 16.7.4 for details.
+ * the at91rm9200 manual, section 41.3.1 or the Zynq manual
+ * section 16.7.4 for details. RXUBR is only enabled for
+ * these two versions.
*/
if (status & MACB_BIT(RXUBR)) {
ctrl = macb_readl(bp, NCR);
/* Enable interrupts */
queue_writel(queue, IER,
- MACB_RX_INT_FLAGS |
+ bp->rx_intr_mask |
MACB_TX_INT_FLAGS |
MACB_BIT(HRESP));
}
};
static const struct macb_config emac_config = {
+ .caps = MACB_CAPS_NEEDS_RSTONUBR,
.clk_init = at91ether_clk_init,
.init = at91ether_init,
};
};
static const struct macb_config zynq_config = {
- .caps = MACB_CAPS_GIGABIT_MODE_AVAILABLE | MACB_CAPS_NO_GIGABIT_HALF,
+ .caps = MACB_CAPS_GIGABIT_MODE_AVAILABLE | MACB_CAPS_NO_GIGABIT_HALF |
+ MACB_CAPS_NEEDS_RSTONUBR,
.dma_burst_length = 16,
.clk_init = macb_clk_init,
.init = macb_init,
macb_dma_desc_get_size(bp);
}
+ bp->rx_intr_mask = MACB_RX_INT_FLAGS;
+ if (bp->caps & MACB_CAPS_NEEDS_RSTONUBR)
+ bp->rx_intr_mask |= MACB_BIT(RXUBR);
+
mac = of_get_mac_address(np);
if (mac) {
ether_addr_copy(bp->dev->dev_addr, mac);
out_notify_fail:
(void)cancel_work_sync(&priv->service_task);
out_read_prop_fail:
+ /* safe for ACPI FW */
+ of_node_put(to_of_node(priv->fwnode));
free_netdev(ndev);
return ret;
}
set_bit(NIC_STATE_REMOVING, &priv->state);
(void)cancel_work_sync(&priv->service_task);
+ /* safe for ACPI FW */
+ of_node_put(to_of_node(priv->fwnode));
+
free_netdev(ndev);
return 0;
}
*/
static int hns_nic_nway_reset(struct net_device *netdev)
{
- int ret = 0;
struct phy_device *phy = netdev->phydev;
- if (netif_running(netdev)) {
- /* if autoneg is disabled, don't restart auto-negotiation */
- if (phy && phy->autoneg == AUTONEG_ENABLE)
- ret = genphy_restart_aneg(phy);
- }
+ if (!netif_running(netdev))
+ return 0;
- return ret;
+ if (!phy)
+ return -EOPNOTSUPP;
+
+ if (phy->autoneg != AUTONEG_ENABLE)
+ return -EINVAL;
+
+ return genphy_restart_aneg(phy);
}
static u32
}
hns_mdio_cmd_write(mdio_dev, is_c45,
- MDIO_C45_WRITE_ADDR, phy_id, devad);
+ MDIO_C45_READ, phy_id, devad);
}
/* Step 5: waitting for MDIO_COMMAND_REG 's mdio_start==0,*/
dev->stats.tx_aborted_errors++;
}
- dev_kfree_skb_irq(skb);
+ dev_consume_skb_irq(skb);
tx_cmd->cmd.command = 0; /* Mark free */
break;
if (params->rx_dim_enabled)
__set_bit(MLX5E_RQ_STATE_AM, &c->rq.state);
- if (params->pflags & MLX5E_PFLAG_RX_NO_CSUM_COMPLETE)
+ if (MLX5E_GET_PFLAG(params, MLX5E_PFLAG_RX_NO_CSUM_COMPLETE))
__set_bit(MLX5E_RQ_STATE_NO_CSUM_COMPLETE, &c->rq.state);
return 0;
struct mlx5e_priv *priv = netdev_priv(dev);
struct mlx5e_rep_priv *rpriv = priv->ppriv;
struct mlx5_eswitch_rep *rep = rpriv->rep;
- int ret;
+ int ret, pf_num;
+
+ ret = mlx5_lag_get_pf_num(priv->mdev, &pf_num);
+ if (ret)
+ return ret;
+
+ if (rep->vport == FDB_UPLINK_VPORT)
+ ret = snprintf(buf, len, "p%d", pf_num);
+ else
+ ret = snprintf(buf, len, "pf%dvf%d", pf_num, rep->vport - 1);
- ret = snprintf(buf, len, "%d", rep->vport - 1);
if (ret >= len)
return -EOPNOTSUPP;
return 0;
}
+static int mlx5e_uplink_rep_set_vf_vlan(struct net_device *dev, int vf, u16 vlan, u8 qos,
+ __be16 vlan_proto)
+{
+ netdev_warn_once(dev, "legacy vf vlan setting isn't supported in switchdev mode\n");
+
+ if (vlan != 0)
+ return -EOPNOTSUPP;
+
+ /* allow setting 0-vid for compatibility with libvirt */
+ return 0;
+}
+
static const struct switchdev_ops mlx5e_rep_switchdev_ops = {
.switchdev_port_attr_get = mlx5e_attr_get,
};
.ndo_set_vf_rate = mlx5e_set_vf_rate,
.ndo_get_vf_config = mlx5e_get_vf_config,
.ndo_get_vf_stats = mlx5e_get_vf_stats,
+ .ndo_set_vf_vlan = mlx5e_uplink_rep_set_vf_vlan,
};
bool mlx5e_eswitch_rep(struct net_device *netdev)
int err = 0;
u8 *smac_v;
- if (vport->info.spoofchk && !is_valid_ether_addr(vport->info.mac)) {
- mlx5_core_warn(esw->dev,
- "vport[%d] configure ingress rules failed, illegal mac with spoofchk\n",
- vport->vport);
- return -EPERM;
- }
-
esw_vport_cleanup_ingress_rules(esw, vport);
if (!vport->info.vlan && !vport->info.qos && !vport->info.spoofchk) {
int vport_num;
int err;
- if (!MLX5_ESWITCH_MANAGER(dev))
+ if (!MLX5_VPORT_MANAGER(dev))
return 0;
esw_info(dev,
void mlx5_eswitch_cleanup(struct mlx5_eswitch *esw)
{
- if (!esw || !MLX5_ESWITCH_MANAGER(esw->dev))
+ if (!esw || !MLX5_VPORT_MANAGER(esw->dev))
return;
esw_info(esw->dev, "cleanup\n");
mutex_lock(&esw->state_lock);
evport = &esw->vports[vport];
- if (evport->info.spoofchk && !is_valid_ether_addr(mac)) {
+ if (evport->info.spoofchk && !is_valid_ether_addr(mac))
mlx5_core_warn(esw->dev,
- "MAC invalidation is not allowed when spoofchk is on, vport(%d)\n",
+ "Set invalid MAC while spoofchk is on, vport(%d)\n",
vport);
- err = -EPERM;
- goto unlock;
- }
err = mlx5_modify_nic_vport_mac_address(esw->dev, vport, mac);
if (err) {
evport = &esw->vports[vport];
pschk = evport->info.spoofchk;
evport->info.spoofchk = spoofchk;
+ if (pschk && !is_valid_ether_addr(evport->info.mac))
+ mlx5_core_warn(esw->dev,
+ "Spoofchk in set while MAC is invalid, vport(%d)\n",
+ evport->vport);
if (evport->enabled && esw->mode == SRIOV_LEGACY)
err = esw_vport_ingress_config(esw, evport);
if (err)
}
}
+int mlx5_lag_get_pf_num(struct mlx5_core_dev *dev, int *pf_num)
+{
+ struct mlx5_lag *ldev;
+ int n;
+
+ ldev = mlx5_lag_dev_get(dev);
+ if (!ldev) {
+ mlx5_core_warn(dev, "no lag device, can't get pf num\n");
+ return -EINVAL;
+ }
+
+ for (n = 0; n < MLX5_MAX_PORTS; n++)
+ if (ldev->pf[n].dev == dev) {
+ *pf_num = n;
+ return 0;
+ }
+
+ mlx5_core_warn(dev, "wasn't able to locate pf in the lag device\n");
+ return -EINVAL;
+}
+
/* Must be called with intf_mutex held */
void mlx5_lag_remove(struct mlx5_core_dev *dev)
{
MLX5_CAP_GEN(dev, lag_master);
}
+int mlx5_lag_get_pf_num(struct mlx5_core_dev *dev, int *pf_num);
+
void mlx5_reload_interface(struct mlx5_core_dev *mdev, int protocol);
void mlx5_lag_update(struct mlx5_core_dev *dev);
mlx5_get_rsc(struct mlx5_qp_table *table, u32 rsn)
{
struct mlx5_core_rsc_common *common;
+ unsigned long flags;
- spin_lock(&table->lock);
+ spin_lock_irqsave(&table->lock, flags);
common = radix_tree_lookup(&table->tree, rsn);
if (common)
atomic_inc(&common->refcount);
- spin_unlock(&table->lock);
+ spin_unlock_irqrestore(&table->lock, flags);
return common;
}
/* get pq index according to PQ_FLAGS */
static u16 *qed_init_qm_get_idx_from_flags(struct qed_hwfn *p_hwfn,
- u32 pq_flags)
+ unsigned long pq_flags)
{
struct qed_qm_info *qm_info = &p_hwfn->qm_info;
/* Can't have multiple flags set here */
- if (bitmap_weight((unsigned long *)&pq_flags,
+ if (bitmap_weight(&pq_flags,
sizeof(pq_flags) * BITS_PER_BYTE) > 1) {
- DP_ERR(p_hwfn, "requested multiple pq flags 0x%x\n", pq_flags);
+ DP_ERR(p_hwfn, "requested multiple pq flags 0x%lx\n", pq_flags);
goto err;
}
if (!(qed_get_pq_flags(p_hwfn) & pq_flags)) {
- DP_ERR(p_hwfn, "pq flag 0x%x is not set\n", pq_flags);
+ DP_ERR(p_hwfn, "pq flag 0x%lx is not set\n", pq_flags);
goto err;
}
(!!(accept_filter & QED_ACCEPT_MCAST_MATCHED) &&
!!(accept_filter & QED_ACCEPT_MCAST_UNMATCHED)));
+ SET_FIELD(state, ETH_VPORT_TX_MODE_UCAST_ACCEPT_ALL,
+ (!!(accept_filter & QED_ACCEPT_UCAST_MATCHED) &&
+ !!(accept_filter & QED_ACCEPT_UCAST_UNMATCHED)));
+
SET_FIELD(state, ETH_VPORT_TX_MODE_BCAST_ACCEPT_ALL,
!!(accept_filter & QED_ACCEPT_BCAST));
return rc;
}
+ if (p_params->update_ctl_frame_check) {
+ p_cmn->ctl_frame_mac_check_en = p_params->mac_chk_en;
+ p_cmn->ctl_frame_ethtype_check_en = p_params->ethtype_chk_en;
+ }
+
/* Update mcast bins for VFs, PF doesn't use this functionality */
qed_sp_update_mcast_bin(p_hwfn, p_ramrod, p_params);
if (type == QED_FILTER_RX_MODE_TYPE_PROMISC) {
accept_flags.rx_accept_filter |= QED_ACCEPT_UCAST_UNMATCHED |
QED_ACCEPT_MCAST_UNMATCHED;
- accept_flags.tx_accept_filter |= QED_ACCEPT_MCAST_UNMATCHED;
+ accept_flags.tx_accept_filter |= QED_ACCEPT_UCAST_UNMATCHED |
+ QED_ACCEPT_MCAST_UNMATCHED;
} else if (type == QED_FILTER_RX_MODE_TYPE_MULTI_PROMISC) {
accept_flags.rx_accept_filter |= QED_ACCEPT_MCAST_UNMATCHED;
accept_flags.tx_accept_filter |= QED_ACCEPT_MCAST_UNMATCHED;
struct qed_rss_params *rss_params;
struct qed_filter_accept_flags accept_flags;
struct qed_sge_tpa_params *sge_tpa_params;
+ u8 update_ctl_frame_check;
+ u8 mac_chk_en;
+ u8 ethtype_chk_en;
};
int qed_sp_vport_update(struct qed_hwfn *p_hwfn,
{
struct qed_ll2_tx_pkt_info pkt;
const skb_frag_t *frag;
+ u8 flags = 0, nr_frags;
int rc = -EINVAL, i;
dma_addr_t mapping;
u16 vlan = 0;
- u8 flags = 0;
if (unlikely(skb->ip_summed != CHECKSUM_NONE)) {
DP_INFO(cdev, "Cannot transmit a checksummed packet\n");
return -EINVAL;
}
- if (1 + skb_shinfo(skb)->nr_frags > CORE_LL2_TX_MAX_BDS_PER_PACKET) {
+ /* Cache number of fragments from SKB since SKB may be freed by
+ * the completion routine after calling qed_ll2_prepare_tx_packet()
+ */
+ nr_frags = skb_shinfo(skb)->nr_frags;
+
+ if (1 + nr_frags > CORE_LL2_TX_MAX_BDS_PER_PACKET) {
DP_ERR(cdev, "Cannot transmit a packet with %d fragments\n",
- 1 + skb_shinfo(skb)->nr_frags);
+ 1 + nr_frags);
return -EINVAL;
}
}
memset(&pkt, 0, sizeof(pkt));
- pkt.num_of_bds = 1 + skb_shinfo(skb)->nr_frags;
+ pkt.num_of_bds = 1 + nr_frags;
pkt.vlan = vlan;
pkt.bd_flags = flags;
pkt.tx_dest = QED_LL2_TX_DEST_NW;
test_bit(QED_LL2_XMIT_FLAGS_FIP_DISCOVERY, &xmit_flags))
pkt.remove_stag = true;
+ /* qed_ll2_prepare_tx_packet() may actually send the packet if
+ * there are no fragments in the skb and subsequently the completion
+ * routine may run and free the SKB, so no dereferencing the SKB
+ * beyond this point unless skb has any fragments.
+ */
rc = qed_ll2_prepare_tx_packet(&cdev->hwfns[0], cdev->ll2->handle,
&pkt, 1);
if (rc)
goto err;
- for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
+ for (i = 0; i < nr_frags; i++) {
frag = &skb_shinfo(skb)->frags[i];
mapping = skb_frag_dma_map(&cdev->pdev->dev, frag, 0,
params.vport_id = vf->vport_id;
params.max_buffers_per_cqe = start->max_buffers_per_cqe;
params.mtu = vf->mtu;
- params.check_mac = true;
+
+ /* Non trusted VFs should enable control frame filtering */
+ params.check_mac = !vf->p_vf_info.is_trusted_configured;
rc = qed_sp_eth_vport_start(p_hwfn, ¶ms);
if (rc) {
params.opaque_fid = vf->opaque_fid;
params.vport_id = vf->vport_id;
+ params.update_ctl_frame_check = 1;
+ params.mac_chk_en = !vf_info->is_trusted_configured;
+
if (vf_info->rx_accept_mode & mask) {
flags->update_rx_mode_config = 1;
flags->rx_accept_filter = vf_info->rx_accept_mode;
}
if (flags->update_rx_mode_config ||
- flags->update_tx_mode_config)
+ flags->update_tx_mode_config ||
+ params.update_ctl_frame_check)
qed_sp_vport_update(hwfn, ¶ms,
QED_SPQ_MODE_EBLOCK, NULL);
}
struct pfvf_acquire_resp_tlv *resp = &p_iov->pf2vf_reply->acquire_resp;
struct pf_vf_pfdev_info *pfdev_info = &resp->pfdev_info;
struct vf_pf_resc_request *p_resc;
+ u8 retry_cnt = VF_ACQUIRE_THRESH;
bool resources_acquired = false;
struct vfpf_acquire_tlv *req;
int rc = 0, attempts = 0;
/* send acquire request */
rc = qed_send_msg2pf(p_hwfn, &resp->hdr.status, sizeof(*resp));
+
+ /* Re-try acquire in case of vf-pf hw channel timeout */
+ if (retry_cnt && rc == -EBUSY) {
+ DP_VERBOSE(p_hwfn, QED_MSG_IOV,
+ "VF retrying to acquire due to VPC timeout\n");
+ retry_cnt--;
+ continue;
+ }
+
if (rc)
goto exit;
}
bytes_compl += skb->len;
pkts_compl++;
- dev_kfree_skb_irq(skb);
+ dev_consume_skb_irq(skb);
}
cp->tx_skb[tx_tail] = NULL;
}
ret = phy_power_on(bsp_priv, true);
- if (ret)
+ if (ret) {
+ gmac_clk_enable(bsp_priv, false);
return ret;
+ }
pm_runtime_enable(dev);
pm_runtime_get_sync(dev);
netdev_dbg(dev, "sent 0x%p, len=%d\n",
desc->skb, desc->skb->len);
- dev_kfree_skb_irq(desc->skb);
+ dev_consume_skb_irq(desc->skb);
desc->skb = NULL;
if (__netif_subqueue_stopped(dev, queue))
netif_wake_subqueue(dev, queue);
imx6_pcie->pd_pcie = dev_pm_domain_attach_by_name(dev, "pcie");
if (IS_ERR(imx6_pcie->pd_pcie))
return PTR_ERR(imx6_pcie->pd_pcie);
+ /* Do nothing when power domain missing */
+ if (!imx6_pcie->pd_pcie)
+ return 0;
link = device_link_add(dev, imx6_pcie->pd_pcie,
DL_FLAG_STATELESS |
DL_FLAG_PM_RUNTIME |
if (IS_ERR(imx6_pcie->pd_pcie_phy))
return PTR_ERR(imx6_pcie->pd_pcie_phy);
- device_link_add(dev, imx6_pcie->pd_pcie_phy,
+ link = device_link_add(dev, imx6_pcie->pd_pcie_phy,
DL_FLAG_STATELESS |
DL_FLAG_PM_RUNTIME |
DL_FLAG_RPM_ACTIVE);
- if (IS_ERR(link)) {
- dev_err(dev, "Failed to add device_link to pcie_phy pd: %ld\n", PTR_ERR(link));
- return PTR_ERR(link);
+ if (!link) {
+ dev_err(dev, "Failed to add device_link to pcie_phy pd.\n");
+ return -EINVAL;
}
return 0;
#include <linux/resource.h>
#include <linux/of_pci.h>
#include <linux/of_irq.h>
-#include <linux/gpio/consumer.h>
#include "pcie-designware.h"
struct dw_pcie *pci;
struct clk *clk;
struct clk *clk_reg;
- struct gpio_desc *reset_gpio;
};
#define PCIE_VENDOR_REGS_OFFSET 0x8000
struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
struct armada8k_pcie *pcie = to_armada8k_pcie(pci);
- if (pcie->reset_gpio) {
- /* assert and then deassert the reset signal */
- gpiod_set_value_cansleep(pcie->reset_gpio, 1);
- msleep(100);
- gpiod_set_value_cansleep(pcie->reset_gpio, 0);
- }
dw_pcie_setup_rc(pp);
armada8k_pcie_establish_link(pcie);
goto fail_clkreg;
}
- /* Get reset gpio signal and hold asserted (logically high) */
- pcie->reset_gpio = devm_gpiod_get_optional(dev, "reset",
- GPIOD_OUT_HIGH);
- if (IS_ERR(pcie->reset_gpio)) {
- ret = PTR_ERR(pcie->reset_gpio);
- goto fail_clkreg;
- }
-
platform_set_drvdata(pdev, pcie);
ret = armada8k_add_pcie_port(pcie, pdev);
config ACPI_CMPC
tristate "CMPC Laptop Extras"
depends on ACPI && INPUT
+ depends on BACKLIGHT_LCD_SUPPORT
depends on RFKILL || RFKILL=n
select BACKLIGHT_CLASS_DEVICE
help
config SAMSUNG_Q10
tristate "Samsung Q10 Extras"
depends on ACPI
+ depends on BACKLIGHT_LCD_SUPPORT
select BACKLIGHT_CLASS_DEVICE
---help---
This driver provides support for backlight control on Samsung Q10
goto failed;
/* report size limit per scatter-gather segment */
- adapter->dma_parms.max_segment_size = ZFCP_QDIO_SBALE_LEN;
adapter->ccw_device->dev.dma_parms = &adapter->dma_parms;
adapter->stat_read_buf_num = FSF_STATUS_READS_RECOM;
.max_sectors = (((QDIO_MAX_ELEMENTS_PER_BUFFER - 1)
* ZFCP_QDIO_MAX_SBALS_PER_REQ) - 2) * 8,
/* GCD, adjusted later */
+ /* report size limit per scatter-gather segment */
+ .max_segment_size = ZFCP_QDIO_SBALE_LEN,
.dma_boundary = ZFCP_QDIO_SBALE_LEN - 1,
.shost_attrs = zfcp_sysfs_shost_attrs,
.sdev_attrs = zfcp_sysfs_sdev_attrs,
if(tpnt->sdev_attrs == NULL)
tpnt->sdev_attrs = NCR_700_dev_attrs;
- memory = dma_alloc_attrs(hostdata->dev, TOTAL_MEM_SIZE, &pScript,
+ memory = dma_alloc_attrs(dev, TOTAL_MEM_SIZE, &pScript,
GFP_KERNEL, DMA_ATTR_NON_CONSISTENT);
if(memory == NULL) {
printk(KERN_ERR "53c700: Failed to allocate memory for driver, detaching\n");
return NULL;
}
+ cmgr->hba = hba;
cmgr->free_list = kcalloc(arr_sz, sizeof(*cmgr->free_list),
GFP_KERNEL);
if (!cmgr->free_list) {
goto mem_err;
}
- cmgr->hba = hba;
cmgr->cmds = (struct bnx2fc_cmd **)(cmgr + 1);
for (i = 0; i < arr_sz; i++) {
/* Allocate pool of io_bdts - one for each bnx2fc_cmd */
mem_size = num_ios * sizeof(struct io_bdt *);
- cmgr->io_bdt_pool = kmalloc(mem_size, GFP_KERNEL);
+ cmgr->io_bdt_pool = kzalloc(mem_size, GFP_KERNEL);
if (!cmgr->io_bdt_pool) {
printk(KERN_ERR PFX "failed to alloc io_bdt_pool\n");
goto mem_err;
fc_frame_payload_op(fp) != ELS_LS_ACC) {
FC_LPORT_DBG(lport, "FLOGI not accepted or bad response\n");
fc_lport_error(lport, fp);
- goto err;
+ goto out;
}
flp = fc_frame_payload_get(fp, sizeof(*flp));
if (!flp) {
FC_LPORT_DBG(lport, "FLOGI bad response\n");
fc_lport_error(lport, fp);
- goto err;
+ goto out;
}
mfs = ntohs(flp->fl_csp.sp_bb_data) &
FC_LPORT_DBG(lport, "FLOGI bad mfs:%hu response, "
"lport->mfs:%hu\n", mfs, lport->mfs);
fc_lport_error(lport, fp);
- goto err;
+ goto out;
}
if (mfs <= lport->mfs) {
/* make sure inq_product_rev string corresponds to this version */
#define SDEBUG_VERSION "0188" /* format to fit INQUIRY revision field */
-static const char *sdebug_version_date = "20180128";
+static const char *sdebug_version_date = "20190125";
#define MY_NAME "scsi_debug"
(sdebug_lbpu || sdebug_lbpws || sdebug_lbpws10);
}
-static void *fake_store(unsigned long long lba)
+static void *lba2fake_store(unsigned long long lba)
{
lba = do_div(lba, sdebug_store_sectors);
return ret;
}
-/* If fake_store(lba,num) compares equal to arr(num), then copy top half of
- * arr into fake_store(lba,num) and return true. If comparison fails then
+/* If lba2fake_store(lba,num) compares equal to arr(num), then copy top half of
+ * arr into lba2fake_store(lba,num) and return true. If comparison fails then
* return false. */
static bool comp_write_worker(u64 lba, u32 num, const u8 *arr)
{
if (sdt->app_tag == cpu_to_be16(0xffff))
continue;
- ret = dif_verify(sdt, fake_store(sector), sector, ei_lba);
+ ret = dif_verify(sdt, lba2fake_store(sector), sector, ei_lba);
if (ret) {
dif_errors++;
return ret;
static int resp_write_same(struct scsi_cmnd *scp, u64 lba, u32 num,
u32 ei_lba, bool unmap, bool ndob)
{
+ int ret;
unsigned long iflags;
unsigned long long i;
- int ret;
- u64 lba_off;
+ u32 lb_size = sdebug_sector_size;
+ u64 block, lbaa;
+ u8 *fs1p;
ret = check_device_access_params(scp, lba, num);
if (ret)
unmap_region(lba, num);
goto out;
}
-
- lba_off = lba * sdebug_sector_size;
+ lbaa = lba;
+ block = do_div(lbaa, sdebug_store_sectors);
/* if ndob then zero 1 logical block, else fetch 1 logical block */
+ fs1p = fake_storep + (block * lb_size);
if (ndob) {
- memset(fake_storep + lba_off, 0, sdebug_sector_size);
+ memset(fs1p, 0, lb_size);
ret = 0;
} else
- ret = fetch_to_dev_buffer(scp, fake_storep + lba_off,
- sdebug_sector_size);
+ ret = fetch_to_dev_buffer(scp, fs1p, lb_size);
if (-1 == ret) {
write_unlock_irqrestore(&atomic_rw, iflags);
return DID_ERROR << 16;
- } else if (sdebug_verbose && !ndob && (ret < sdebug_sector_size))
+ } else if (sdebug_verbose && !ndob && (ret < lb_size))
sdev_printk(KERN_INFO, scp->device,
"%s: %s: lb size=%u, IO sent=%d bytes\n",
- my_name, "write same",
- sdebug_sector_size, ret);
+ my_name, "write same", lb_size, ret);
/* Copy first sector to remaining blocks */
- for (i = 1 ; i < num ; i++)
- memcpy(fake_storep + ((lba + i) * sdebug_sector_size),
- fake_storep + lba_off,
- sdebug_sector_size);
-
+ for (i = 1 ; i < num ; i++) {
+ lbaa = lba + i;
+ block = do_div(lbaa, sdebug_store_sectors);
+ memmove(fake_storep + (block * lb_size), fs1p, lb_size);
+ }
if (scsi_debug_lbp())
map_region(lba, num);
out:
#include <linux/serial_core.h>
#include <asm/sbi.h>
-static void sbi_console_write(struct console *con,
- const char *s, unsigned int n)
+static void sbi_putc(struct uart_port *port, int c)
{
- int i;
+ sbi_console_putchar(c);
+}
- for (i = 0; i < n; ++i)
- sbi_console_putchar(s[i]);
+static void sbi_console_write(struct console *con,
+ const char *s, unsigned n)
+{
+ struct earlycon_device *dev = con->data;
+ uart_console_write(&dev->port, s, n, sbi_putc);
}
static int __init early_sbi_setup(struct earlycon_device *device,
n->vqs[i].rx_ring = NULL;
vhost_net_buf_init(&n->vqs[i].rxq);
}
- vhost_dev_init(dev, vqs, VHOST_NET_VQ_MAX);
+ vhost_dev_init(dev, vqs, VHOST_NET_VQ_MAX,
+ UIO_MAXIOV + VHOST_NET_BATCH);
vhost_poll_init(n->poll + VHOST_NET_VQ_TX, handle_tx_net, EPOLLOUT, dev);
vhost_poll_init(n->poll + VHOST_NET_VQ_RX, handle_rx_net, EPOLLIN, dev);
vqs[i] = &vs->vqs[i].vq;
vs->vqs[i].vq.handle_kick = vhost_scsi_handle_kick;
}
- vhost_dev_init(&vs->dev, vqs, VHOST_SCSI_MAX_VQ);
+ vhost_dev_init(&vs->dev, vqs, VHOST_SCSI_MAX_VQ, UIO_MAXIOV);
vhost_scsi_init_inflight(vs, NULL);
vq->indirect = kmalloc_array(UIO_MAXIOV,
sizeof(*vq->indirect),
GFP_KERNEL);
- vq->log = kmalloc_array(UIO_MAXIOV, sizeof(*vq->log),
+ vq->log = kmalloc_array(dev->iov_limit, sizeof(*vq->log),
GFP_KERNEL);
- vq->heads = kmalloc_array(UIO_MAXIOV, sizeof(*vq->heads),
+ vq->heads = kmalloc_array(dev->iov_limit, sizeof(*vq->heads),
GFP_KERNEL);
if (!vq->indirect || !vq->log || !vq->heads)
goto err_nomem;
}
void vhost_dev_init(struct vhost_dev *dev,
- struct vhost_virtqueue **vqs, int nvqs)
+ struct vhost_virtqueue **vqs, int nvqs, int iov_limit)
{
struct vhost_virtqueue *vq;
int i;
dev->iotlb = NULL;
dev->mm = NULL;
dev->worker = NULL;
+ dev->iov_limit = iov_limit;
init_llist_head(&dev->work_list);
init_waitqueue_head(&dev->wait);
INIT_LIST_HEAD(&dev->read_list);
struct list_head read_list;
struct list_head pending_list;
wait_queue_head_t wait;
+ int iov_limit;
};
-void vhost_dev_init(struct vhost_dev *, struct vhost_virtqueue **vqs, int nvqs);
+void vhost_dev_init(struct vhost_dev *, struct vhost_virtqueue **vqs,
+ int nvqs, int iov_limit);
long vhost_dev_set_owner(struct vhost_dev *dev);
bool vhost_dev_has_owner(struct vhost_dev *dev);
long vhost_dev_check_owner(struct vhost_dev *);
vsock->vqs[VSOCK_VQ_TX].handle_kick = vhost_vsock_handle_tx_kick;
vsock->vqs[VSOCK_VQ_RX].handle_kick = vhost_vsock_handle_rx_kick;
- vhost_dev_init(&vsock->dev, vqs, ARRAY_SIZE(vsock->vqs));
+ vhost_dev_init(&vsock->dev, vqs, ARRAY_SIZE(vsock->vqs), UIO_MAXIOV);
file->private_data = vsock;
spin_lock_init(&vsock->send_pkt_list_lock);
pkt.len = dentry->d_name.len;
memcpy(pkt.name, dentry->d_name.name, pkt.len);
pkt.name[pkt.len] = '\0';
- dput(dentry);
if (copy_to_user(pkt_p, &pkt, sizeof(struct autofs_packet_expire)))
ret = -EFAULT;
complete_all(&ino->expire_complete);
spin_unlock(&sbi->fs_lock);
+ dput(dentry);
+
return ret;
}
}
root_inode = autofs_get_inode(s, S_IFDIR | 0755);
root = d_make_root(root_inode);
- if (!root)
+ if (!root) {
+ ret = -ENOMEM;
goto fail_ino;
+ }
pipe = NULL;
root->d_fsdata = ino;
return 0;
}
+static struct extent_buffer *alloc_tree_block_no_bg_flush(
+ struct btrfs_trans_handle *trans,
+ struct btrfs_root *root,
+ u64 parent_start,
+ const struct btrfs_disk_key *disk_key,
+ int level,
+ u64 hint,
+ u64 empty_size)
+{
+ struct btrfs_fs_info *fs_info = root->fs_info;
+ struct extent_buffer *ret;
+
+ /*
+ * If we are COWing a node/leaf from the extent, chunk, device or free
+ * space trees, make sure that we do not finish block group creation of
+ * pending block groups. We do this to avoid a deadlock.
+ * COWing can result in allocation of a new chunk, and flushing pending
+ * block groups (btrfs_create_pending_block_groups()) can be triggered
+ * when finishing allocation of a new chunk. Creation of a pending block
+ * group modifies the extent, chunk, device and free space trees,
+ * therefore we could deadlock with ourselves since we are holding a
+ * lock on an extent buffer that btrfs_create_pending_block_groups() may
+ * try to COW later.
+ * For similar reasons, we also need to delay flushing pending block
+ * groups when splitting a leaf or node, from one of those trees, since
+ * we are holding a write lock on it and its parent or when inserting a
+ * new root node for one of those trees.
+ */
+ if (root == fs_info->extent_root ||
+ root == fs_info->chunk_root ||
+ root == fs_info->dev_root ||
+ root == fs_info->free_space_root)
+ trans->can_flush_pending_bgs = false;
+
+ ret = btrfs_alloc_tree_block(trans, root, parent_start,
+ root->root_key.objectid, disk_key, level,
+ hint, empty_size);
+ trans->can_flush_pending_bgs = true;
+
+ return ret;
+}
+
/*
* does the dirty work in cow of a single block. The parent block (if
* supplied) is updated to point to the new cow copy. The new buffer is marked
if ((root->root_key.objectid == BTRFS_TREE_RELOC_OBJECTID) && parent)
parent_start = parent->start;
- /*
- * If we are COWing a node/leaf from the extent, chunk, device or free
- * space trees, make sure that we do not finish block group creation of
- * pending block groups. We do this to avoid a deadlock.
- * COWing can result in allocation of a new chunk, and flushing pending
- * block groups (btrfs_create_pending_block_groups()) can be triggered
- * when finishing allocation of a new chunk. Creation of a pending block
- * group modifies the extent, chunk, device and free space trees,
- * therefore we could deadlock with ourselves since we are holding a
- * lock on an extent buffer that btrfs_create_pending_block_groups() may
- * try to COW later.
- */
- if (root == fs_info->extent_root ||
- root == fs_info->chunk_root ||
- root == fs_info->dev_root ||
- root == fs_info->free_space_root)
- trans->can_flush_pending_bgs = false;
-
- cow = btrfs_alloc_tree_block(trans, root, parent_start,
- root->root_key.objectid, &disk_key, level,
- search_start, empty_size);
- trans->can_flush_pending_bgs = true;
+ cow = alloc_tree_block_no_bg_flush(trans, root, parent_start, &disk_key,
+ level, search_start, empty_size);
if (IS_ERR(cow))
return PTR_ERR(cow);
else
btrfs_node_key(lower, &lower_key, 0);
- c = btrfs_alloc_tree_block(trans, root, 0, root->root_key.objectid,
- &lower_key, level, root->node->start, 0);
+ c = alloc_tree_block_no_bg_flush(trans, root, 0, &lower_key, level,
+ root->node->start, 0);
if (IS_ERR(c))
return PTR_ERR(c);
mid = (c_nritems + 1) / 2;
btrfs_node_key(c, &disk_key, mid);
- split = btrfs_alloc_tree_block(trans, root, 0, root->root_key.objectid,
- &disk_key, level, c->start, 0);
+ split = alloc_tree_block_no_bg_flush(trans, root, 0, &disk_key, level,
+ c->start, 0);
if (IS_ERR(split))
return PTR_ERR(split);
else
btrfs_item_key(l, &disk_key, mid);
- right = btrfs_alloc_tree_block(trans, root, 0, root->root_key.objectid,
- &disk_key, 0, l->start, 0);
+ right = alloc_tree_block_no_bg_flush(trans, root, 0, &disk_key, 0,
+ l->start, 0);
if (IS_ERR(right))
return PTR_ERR(right);
flags | SB_RDONLY, device_name, data);
if (IS_ERR(mnt_root)) {
root = ERR_CAST(mnt_root);
+ kfree(subvol_name);
goto out;
}
if (error < 0) {
root = ERR_PTR(error);
mntput(mnt_root);
+ kfree(subvol_name);
goto out;
}
}
}
if (IS_ERR(mnt_root)) {
root = ERR_CAST(mnt_root);
+ kfree(subvol_name);
goto out;
}
btrfs_trans_release_chunk_metadata(trans);
- if (lock && should_end_transaction(trans) &&
- READ_ONCE(cur_trans->state) == TRANS_STATE_RUNNING) {
- spin_lock(&info->trans_lock);
- if (cur_trans->state == TRANS_STATE_RUNNING)
- cur_trans->state = TRANS_STATE_BLOCKED;
- spin_unlock(&info->trans_lock);
- }
-
if (lock && READ_ONCE(cur_trans->state) == TRANS_STATE_BLOCKED) {
if (throttle)
return btrfs_commit_transaction(trans);
kmem_cache_free(btrfs_trans_handle_cachep, trans);
}
+/*
+ * Release reserved delayed ref space of all pending block groups of the
+ * transaction and remove them from the list
+ */
+static void btrfs_cleanup_pending_block_groups(struct btrfs_trans_handle *trans)
+{
+ struct btrfs_fs_info *fs_info = trans->fs_info;
+ struct btrfs_block_group_cache *block_group, *tmp;
+
+ list_for_each_entry_safe(block_group, tmp, &trans->new_bgs, bg_list) {
+ btrfs_delayed_refs_rsv_release(fs_info, 1);
+ list_del_init(&block_group->bg_list);
+ }
+}
+
static inline int btrfs_start_delalloc_flush(struct btrfs_fs_info *fs_info)
{
/*
btrfs_scrub_continue(fs_info);
cleanup_transaction:
btrfs_trans_release_metadata(trans);
+ btrfs_cleanup_pending_block_groups(trans);
btrfs_trans_release_chunk_metadata(trans);
trans->block_rsv = NULL;
btrfs_warn(fs_info, "Skipping commit of aborted transaction.");
else
fs_devices = alloc_fs_devices(disk_super->fsid, NULL);
- fs_devices->fsid_change = fsid_change_in_progress;
-
if (IS_ERR(fs_devices))
return ERR_CAST(fs_devices);
+ fs_devices->fsid_change = fsid_change_in_progress;
+
mutex_lock(&fs_devices->device_list_mutex);
list_add(&fs_devices->fs_list, &fs_uuids);
extern const struct export_operations cifs_export_ops;
#endif /* CONFIG_CIFS_NFSD_EXPORT */
-#define CIFS_VERSION "2.16"
+#define CIFS_VERSION "2.17"
#endif /* _CIFSFS_H */
rc = cifs_write_allocate_pages(wdata->pages, nr_pages);
if (rc) {
+ kvfree(wdata->pages);
kfree(wdata);
add_credits_and_wake_if(server, credits, 0);
break;
if (rc) {
for (i = 0; i < nr_pages; i++)
put_page(wdata->pages[i]);
+ kvfree(wdata->pages);
kfree(wdata);
add_credits_and_wake_if(server, credits, 0);
break;
}
rc = cifs_read_allocate_pages(rdata, npages);
- if (rc)
- goto error;
+ if (rc) {
+ kvfree(rdata->pages);
+ kfree(rdata);
+ add_credits_and_wake_if(server, credits, 0);
+ break;
+ }
rdata->tailsz = PAGE_SIZE;
}
if (!rdata->cfile->invalidHandle ||
!(rc = cifs_reopen_file(rdata->cfile, true)))
rc = server->ops->async_readv(rdata);
-error:
if (rc) {
add_credits_and_wake_if(server, rdata->credits, 0);
kref_put(&rdata->refcount,
FILE_READ_EA,
FILE_FULL_EA_INFORMATION,
SMB2_O_INFO_FILE,
- SMB2_MAX_EA_BUF,
+ CIFSMaxBufSize -
+ MAX_SMB2_CREATE_RESPONSE_SIZE -
+ MAX_SMB2_CLOSE_RESPONSE_SIZE,
&rsp_iov, &buftype, cifs_sb);
if (rc) {
/*
rdata->mr = NULL;
}
#endif
- if (rdata->result)
+ if (rdata->result && rdata->result != -ENODATA) {
cifs_stats_fail_inc(tcon, SMB2_READ_HE);
+ trace_smb3_read_err(0 /* xid */,
+ rdata->cfile->fid.persistent_fid,
+ tcon->tid, tcon->ses->Suid, rdata->offset,
+ rdata->bytes, rdata->result);
+ } else
+ trace_smb3_read_done(0 /* xid */,
+ rdata->cfile->fid.persistent_fid,
+ tcon->tid, tcon->ses->Suid,
+ rdata->offset, rdata->got_bytes);
queue_work(cifsiod_wq, &rdata->work);
DeleteMidQEntry(mid);
if (rc) {
kref_put(&rdata->refcount, cifs_readdata_release);
cifs_stats_fail_inc(io_parms.tcon, SMB2_READ_HE);
- trace_smb3_read_err(rc, 0 /* xid */, io_parms.persistent_fid,
- io_parms.tcon->tid, io_parms.tcon->ses->Suid,
- io_parms.offset, io_parms.length);
- } else
- trace_smb3_read_done(0 /* xid */, io_parms.persistent_fid,
- io_parms.tcon->tid, io_parms.tcon->ses->Suid,
- io_parms.offset, io_parms.length);
+ trace_smb3_read_err(0 /* xid */, io_parms.persistent_fid,
+ io_parms.tcon->tid,
+ io_parms.tcon->ses->Suid,
+ io_parms.offset, io_parms.length, rc);
+ }
cifs_small_buf_release(buf);
return rc;
if (rc != -ENODATA) {
cifs_stats_fail_inc(io_parms->tcon, SMB2_READ_HE);
cifs_dbg(VFS, "Send error in read = %d\n", rc);
+ trace_smb3_read_err(xid, req->PersistentFileId,
+ io_parms->tcon->tid, ses->Suid,
+ io_parms->offset, io_parms->length,
+ rc);
}
- trace_smb3_read_err(rc, xid, req->PersistentFileId,
- io_parms->tcon->tid, ses->Suid,
- io_parms->offset, io_parms->length);
free_rsp_buf(resp_buftype, rsp_iov.iov_base);
return rc == -ENODATA ? 0 : rc;
} else
wdata->mr = NULL;
}
#endif
- if (wdata->result)
+ if (wdata->result) {
cifs_stats_fail_inc(tcon, SMB2_WRITE_HE);
+ trace_smb3_write_err(0 /* no xid */,
+ wdata->cfile->fid.persistent_fid,
+ tcon->tid, tcon->ses->Suid, wdata->offset,
+ wdata->bytes, wdata->result);
+ } else
+ trace_smb3_write_done(0 /* no xid */,
+ wdata->cfile->fid.persistent_fid,
+ tcon->tid, tcon->ses->Suid,
+ wdata->offset, wdata->bytes);
queue_work(cifsiod_wq, &wdata->work);
DeleteMidQEntry(mid);
wdata->bytes, rc);
kref_put(&wdata->refcount, release);
cifs_stats_fail_inc(tcon, SMB2_WRITE_HE);
- } else
- trace_smb3_write_done(0 /* no xid */, req->PersistentFileId,
- tcon->tid, tcon->ses->Suid, wdata->offset,
- wdata->bytes);
+ }
async_writev_out:
cifs_small_buf_release(req);
rsp->sync_hdr.Status == STATUS_NO_MORE_FILES) {
srch_inf->endOfSearch = true;
rc = 0;
- }
- cifs_stats_fail_inc(tcon, SMB2_QUERY_DIRECTORY_HE);
+ } else
+ cifs_stats_fail_inc(tcon, SMB2_QUERY_DIRECTORY_HE);
goto qdir_exit;
}
rc = cifs_send_recv(xid, ses, &rqst, &resp_buf_type, flags, &rsp_iov);
cifs_small_buf_release(req);
- please_key_low = (__u64 *)req->LeaseKey;
- please_key_high = (__u64 *)(req->LeaseKey+8);
+ please_key_low = (__u64 *)lease_key;
+ please_key_high = (__u64 *)(lease_key+8);
if (rc) {
cifs_stats_fail_inc(tcon, SMB2_OPLOCK_BREAK_HE);
trace_smb3_lease_err(le32_to_cpu(lease_state), tcon->tid,
#define NUMBER_OF_SMB2_COMMANDS 0x0013
-/* 4 len + 52 transform hdr + 64 hdr + 56 create rsp */
-#define MAX_SMB2_HDR_SIZE 0x00b0
+/* 52 transform hdr + 64 hdr + 88 create rsp */
+#define SMB2_TRANSFORM_HEADER_SIZE 52
+#define MAX_SMB2_HDR_SIZE 204
#define SMB2_PROTO_NUMBER cpu_to_le32(0x424d53fe)
#define SMB2_TRANSFORM_PROTO_NUM cpu_to_le32(0x424d53fd)
__u8 Buffer[0];
} __packed;
+/*
+ * Maximum size of a SMB2_CREATE response is 64 (smb2 header) +
+ * 88 (fixed part of create response) + 520 (path) + 150 (contexts) +
+ * 2 bytes of padding.
+ */
+#define MAX_SMB2_CREATE_RESPONSE_SIZE 824
+
struct smb2_create_rsp {
struct smb2_sync_hdr sync_hdr;
__le16 StructureSize; /* Must be 89 */
__u64 VolatileFileId; /* opaque endianness */
} __packed;
+/*
+ * Maximum size of a SMB2_CLOSE response is 64 (smb2 header) + 60 (data)
+ */
+#define MAX_SMB2_CLOSE_RESPONSE_SIZE 124
+
struct smb2_close_rsp {
struct smb2_sync_hdr sync_hdr;
__le16 StructureSize; /* 60 */
char FileName[0]; /* Name to be assigned to new link */
} __packed; /* level 11 Set */
-#define SMB2_MAX_EA_BUF 65536
-
struct smb2_file_full_ea_info { /* encoding of response for level 15 */
__le32 next_entry_offset;
__u8 flags;
static DEFINE_PER_CPU(long, nr_dentry);
static DEFINE_PER_CPU(long, nr_dentry_unused);
+static DEFINE_PER_CPU(long, nr_dentry_negative);
#if defined(CONFIG_SYSCTL) && defined(CONFIG_PROC_FS)
return sum < 0 ? 0 : sum;
}
+static long get_nr_dentry_negative(void)
+{
+ int i;
+ long sum = 0;
+
+ for_each_possible_cpu(i)
+ sum += per_cpu(nr_dentry_negative, i);
+ return sum < 0 ? 0 : sum;
+}
+
int proc_nr_dentry(struct ctl_table *table, int write, void __user *buffer,
size_t *lenp, loff_t *ppos)
{
dentry_stat.nr_dentry = get_nr_dentry();
dentry_stat.nr_unused = get_nr_dentry_unused();
+ dentry_stat.nr_negative = get_nr_dentry_negative();
return proc_doulongvec_minmax(table, write, buffer, lenp, ppos);
}
#endif
flags &= ~(DCACHE_ENTRY_TYPE | DCACHE_FALLTHRU);
WRITE_ONCE(dentry->d_flags, flags);
dentry->d_inode = NULL;
+ if (dentry->d_flags & DCACHE_LRU_LIST)
+ this_cpu_inc(nr_dentry_negative);
}
static void dentry_free(struct dentry *dentry)
* The per-cpu "nr_dentry_unused" counters are updated with
* the DCACHE_LRU_LIST bit.
*
+ * The per-cpu "nr_dentry_negative" counters are only updated
+ * when deleted from or added to the per-superblock LRU list, not
+ * from/to the shrink list. That is to avoid an unneeded dec/inc
+ * pair when moving from LRU to shrink list in select_collect().
+ *
* These helper functions make sure we always follow the
* rules. d_lock must be held by the caller.
*/
D_FLAG_VERIFY(dentry, 0);
dentry->d_flags |= DCACHE_LRU_LIST;
this_cpu_inc(nr_dentry_unused);
+ if (d_is_negative(dentry))
+ this_cpu_inc(nr_dentry_negative);
WARN_ON_ONCE(!list_lru_add(&dentry->d_sb->s_dentry_lru, &dentry->d_lru));
}
D_FLAG_VERIFY(dentry, DCACHE_LRU_LIST);
dentry->d_flags &= ~DCACHE_LRU_LIST;
this_cpu_dec(nr_dentry_unused);
+ if (d_is_negative(dentry))
+ this_cpu_dec(nr_dentry_negative);
WARN_ON_ONCE(!list_lru_del(&dentry->d_sb->s_dentry_lru, &dentry->d_lru));
}
D_FLAG_VERIFY(dentry, DCACHE_LRU_LIST);
dentry->d_flags &= ~DCACHE_LRU_LIST;
this_cpu_dec(nr_dentry_unused);
+ if (d_is_negative(dentry))
+ this_cpu_dec(nr_dentry_negative);
list_lru_isolate(lru, &dentry->d_lru);
}
{
D_FLAG_VERIFY(dentry, DCACHE_LRU_LIST);
dentry->d_flags |= DCACHE_SHRINK_LIST;
+ if (d_is_negative(dentry))
+ this_cpu_dec(nr_dentry_negative);
list_lru_isolate_move(lru, &dentry->d_lru, list);
}
*/
void shrink_dcache_sb(struct super_block *sb)
{
- long freed;
-
do {
LIST_HEAD(dispose);
- freed = list_lru_walk(&sb->s_dentry_lru,
+ list_lru_walk(&sb->s_dentry_lru,
dentry_lru_isolate_shrink, &dispose, 1024);
-
- this_cpu_sub(nr_dentry_unused, freed);
shrink_dentry_list(&dispose);
} while (list_lru_count(&sb->s_dentry_lru) > 0);
}
WARN_ON(d_in_lookup(dentry));
spin_lock(&dentry->d_lock);
+ /*
+ * Decrement negative dentry count if it was in the LRU list.
+ */
+ if (dentry->d_flags & DCACHE_LRU_LIST)
+ this_cpu_dec(nr_dentry_negative);
hlist_add_head(&dentry->d_u.d_alias, &inode->i_dentry);
raw_write_seqcount_begin(&dentry->d_seq);
__d_set_inode_and_type(dentry, inode, add_flags);
spin_lock(&sb->s_inode_list_lock);
list_for_each_entry(inode, &sb->s_inodes, i_sb_list) {
spin_lock(&inode->i_lock);
+ /*
+ * We must skip inodes in unusual state. We may also skip
+ * inodes without pages but we deliberately won't in case
+ * we need to reschedule to avoid softlockups.
+ */
if ((inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW)) ||
- (inode->i_mapping->nrpages == 0)) {
+ (inode->i_mapping->nrpages == 0 && !need_resched())) {
spin_unlock(&inode->i_lock);
continue;
}
spin_unlock(&inode->i_lock);
spin_unlock(&sb->s_inode_list_lock);
+ cond_resched();
invalidate_mapping_pages(inode->i_mapping, 0, -1);
iput(toput_inode);
toput_inode = inode;
goto next_iter;
}
if (ret == -E2BIG) {
- n += rbm->bii - initial_bii;
rbm->bii = 0;
rbm->offset = 0;
+ n += (rbm->bii - initial_bii);
goto res_covered_end_of_rgrp;
}
return ret;
atomic_set(&iop->read_count, 0);
atomic_set(&iop->write_count, 0);
bitmap_zero(iop->uptodate, PAGE_SIZE / SECTOR_SIZE);
+
+ /*
+ * migrate_page_move_mapping() assumes that pages with private data have
+ * their count elevated by 1.
+ */
+ get_page(page);
set_page_private(page, (unsigned long)iop);
SetPagePrivate(page);
return iop;
WARN_ON_ONCE(atomic_read(&iop->write_count));
ClearPagePrivate(page);
set_page_private(page, 0);
+ put_page(page);
kfree(iop);
}
if (page_has_private(page)) {
ClearPagePrivate(page);
+ get_page(newpage);
set_page_private(newpage, page_private(page));
set_page_private(page, 0);
+ put_page(page);
SetPagePrivate(newpage);
}
loff_t pos = iocb->ki_pos, start = pos;
loff_t end = iocb->ki_pos + count - 1, ret = 0;
unsigned int flags = IOMAP_DIRECT;
+ bool wait_for_completion = is_sync_kiocb(iocb);
struct blk_plug plug;
struct iomap_dio *dio;
dio->end_io = end_io;
dio->error = 0;
dio->flags = 0;
- dio->wait_for_completion = is_sync_kiocb(iocb);
dio->submit.iter = iter;
dio->submit.waiter = current;
dio_warn_stale_pagecache(iocb->ki_filp);
ret = 0;
- if (iov_iter_rw(iter) == WRITE && !dio->wait_for_completion &&
+ if (iov_iter_rw(iter) == WRITE && !wait_for_completion &&
!inode->i_sb->s_dio_done_wq) {
ret = sb_init_dio_done_wq(inode->i_sb);
if (ret < 0)
if (ret <= 0) {
/* magic error code to fall back to buffered I/O */
if (ret == -ENOTBLK) {
- dio->wait_for_completion = true;
+ wait_for_completion = true;
ret = 0;
}
break;
if (dio->flags & IOMAP_DIO_WRITE_FUA)
dio->flags &= ~IOMAP_DIO_NEED_SYNC;
+ /*
+ * We are about to drop our additional submission reference, which
+ * might be the last reference to the dio. There are three three
+ * different ways we can progress here:
+ *
+ * (a) If this is the last reference we will always complete and free
+ * the dio ourselves.
+ * (b) If this is not the last reference, and we serve an asynchronous
+ * iocb, we must never touch the dio after the decrement, the
+ * I/O completion handler will complete and free it.
+ * (c) If this is not the last reference, but we serve a synchronous
+ * iocb, the I/O completion handler will wake us up on the drop
+ * of the final reference, and we will complete and free it here
+ * after we got woken by the I/O completion handler.
+ */
+ dio->wait_for_completion = wait_for_completion;
if (!atomic_dec_and_test(&dio->ref)) {
- if (!dio->wait_for_completion)
+ if (!wait_for_completion)
return -EIOCBQUEUED;
for (;;) {
__set_current_state(TASK_RUNNING);
}
- ret = iomap_dio_complete(dio);
-
- return ret;
+ return iomap_dio_complete(dio);
out_free_dio:
kfree(dio);
size_t len;
char *end;
+ if (unlikely(!dev_name || !*dev_name)) {
+ dfprintk(MOUNT, "NFS: device name not specified\n");
+ return -EINVAL;
+ }
+
/* Is the host name protected with square brakcets? */
if (*dev_name == '[') {
end = strchr(++dev_name, ']');
nfs_set_page_writeback(page);
WARN_ON_ONCE(test_bit(PG_CLEAN, &req->wb_flags));
- ret = 0;
+ ret = req->wb_context->error;
/* If there is a fatal error that covers this write, just exit */
- if (nfs_error_is_fatal_on_server(req->wb_context->error))
+ if (nfs_error_is_fatal_on_server(ret))
goto out_launder;
+ ret = 0;
if (!nfs_pageio_add_request(pgio, req)) {
ret = pgio->pg_error;
/*
nfs_context_set_write_error(req->wb_context, ret);
if (nfs_error_is_fatal_on_server(ret))
goto out_launder;
- }
+ } else
+ ret = -EAGAIN;
nfs_redirty_request(req);
- ret = -EAGAIN;
} else
nfs_add_stats(page_file_mapping(page)->host,
NFSIOS_WRITEPAGES, 1);
inode = proc_get_inode(dir->i_sb, de);
if (!inode)
return ERR_PTR(-ENOMEM);
- d_set_d_op(dentry, &proc_misc_dentry_ops);
+ d_set_d_op(dentry, de->proc_dops);
return d_splice_alias(inode, dentry);
}
read_unlock(&proc_subdir_lock);
INIT_LIST_HEAD(&ent->pde_openers);
proc_set_user(ent, (*parent)->uid, (*parent)->gid);
+ ent->proc_dops = &proc_misc_dentry_ops;
+
out:
return ent;
}
struct completion *pde_unload_completion;
const struct inode_operations *proc_iops;
const struct file_operations *proc_fops;
+ const struct dentry_operations *proc_dops;
union {
const struct seq_operations *seq_ops;
int (*single_show)(struct seq_file *, void *);
return maybe_get_net(PDE_NET(PDE(inode)));
}
+static int proc_net_d_revalidate(struct dentry *dentry, unsigned int flags)
+{
+ return 0;
+}
+
+static const struct dentry_operations proc_net_dentry_ops = {
+ .d_revalidate = proc_net_d_revalidate,
+ .d_delete = always_delete_dentry,
+};
+
+static void pde_force_lookup(struct proc_dir_entry *pde)
+{
+ /* /proc/net/ entries can be changed under us by setns(CLONE_NEWNET) */
+ pde->proc_dops = &proc_net_dentry_ops;
+}
+
static int seq_open_net(struct inode *inode, struct file *file)
{
unsigned int state_size = PDE(inode)->state_size;
p = proc_create_reg(name, mode, &parent, data);
if (!p)
return NULL;
+ pde_force_lookup(p);
p->proc_fops = &proc_net_seq_fops;
p->seq_ops = ops;
p->state_size = state_size;
p = proc_create_reg(name, mode, &parent, data);
if (!p)
return NULL;
+ pde_force_lookup(p);
p->proc_fops = &proc_net_seq_fops;
p->seq_ops = ops;
p->state_size = state_size;
p = proc_create_reg(name, mode, &parent, data);
if (!p)
return NULL;
+ pde_force_lookup(p);
p->proc_fops = &proc_net_single_fops;
p->single_show = show;
return proc_register(parent, p);
p = proc_create_reg(name, mode, &parent, data);
if (!p)
return NULL;
+ pde_force_lookup(p);
p->proc_fops = &proc_net_single_fops;
p->single_show = show;
p->write = write;
#define MMP2_CLK_CCIC1_MIX 117
#define MMP2_CLK_CCIC1_PHY 118
#define MMP2_CLK_CCIC1_SPHY 119
-#define MMP2_CLK_SP 120
#define MMP2_NR_CLKS 200
#endif
struct dentry_stat_t {
long nr_dentry;
long nr_unused;
- long age_limit; /* age in seconds */
- long want_pages; /* pages requested by system */
- long dummy[2];
+ long age_limit; /* age in seconds */
+ long want_pages; /* pages requested by system */
+ long nr_negative; /* # of unused negative dentries */
+ long dummy; /* Reserved for future use */
};
extern struct dentry_stat_t dentry_stat;
struct user_namespace *s_user_ns;
/*
- * Keep the lru lists last in the structure so they always sit on their
- * own individual cachelines.
+ * The list_lru structure is essentially just a pointer to a table
+ * of per-node lru lists, each of which has its own spinlock.
+ * There is no need to put them into separate cachelines.
*/
- struct list_lru s_dentry_lru ____cacheline_aligned_in_smp;
- struct list_lru s_inode_lru ____cacheline_aligned_in_smp;
+ struct list_lru s_dentry_lru;
+ struct list_lru s_inode_lru;
struct rcu_head rcu;
struct work_struct destroy_work;
/* current sense rq and buffer */
bool sense_rq_armed;
+ bool sense_rq_active;
struct request *sense_rq;
struct request_sense sense_data;
extern void ide_timer_expiry(struct timer_list *t);
extern irqreturn_t ide_intr(int irq, void *dev_id);
extern blk_status_t ide_queue_rq(struct blk_mq_hw_ctx *, const struct blk_mq_queue_data *);
+extern blk_status_t ide_issue_rq(ide_drive_t *, struct request *, bool);
extern void ide_requeue_and_plug(ide_drive_t *drive, struct request *rq);
void ide_init_disk(struct gendisk *, ide_drive_t *);
* walkers which rely on the fully initialized page->flags and others
* should use this rather than pfn_valid && pfn_to_page
*/
-#define pfn_to_online_page(pfn) \
-({ \
- struct page *___page = NULL; \
- unsigned long ___nr = pfn_to_section_nr(pfn); \
- \
- if (___nr < NR_MEM_SECTIONS && online_section_nr(___nr))\
- ___page = pfn_to_page(pfn); \
- ___page; \
+#define pfn_to_online_page(pfn) \
+({ \
+ struct page *___page = NULL; \
+ unsigned long ___pfn = pfn; \
+ unsigned long ___nr = pfn_to_section_nr(___pfn); \
+ \
+ if (___nr < NR_MEM_SECTIONS && online_section_nr(___nr) && \
+ pfn_valid_within(___pfn)) \
+ ___page = pfn_to_page(___pfn); \
+ ___page; \
})
/*
static inline void pm_runtime_mark_last_busy(struct device *dev)
{
- WRITE_ONCE(dev->power.last_busy, ktime_to_ns(ktime_get()));
+ WRITE_ONCE(dev->power.last_busy, ktime_get_mono_fast_ns());
}
static inline bool pm_runtime_is_irq_safe(struct device *dev)
#define MMF_HUGE_ZERO_PAGE 23 /* mm has ever used the global huge zero page */
#define MMF_DISABLE_THP 24 /* disable THP for all VMAs */
#define MMF_OOM_VICTIM 25 /* mm is the oom victim */
+#define MMF_OOM_REAP_QUEUED 26 /* mm was queued for oom_reaper */
#define MMF_DISABLE_THP_MASK (1 << MMF_DISABLE_THP)
#define MMF_INIT_MASK (MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK |\
struct scatterlist sg_aead_out[2];
char aad_space[TLS_AAD_SPACE_SIZE];
+ u8 iv_data[TLS_CIPHER_AES_GCM_128_IV_SIZE +
+ TLS_CIPHER_AES_GCM_128_SALT_SIZE];
struct aead_request aead_req;
u8 aead_req_ctx[];
};
const struct uapi_definition *driver_def;
enum rdma_driver_id driver_id;
+
/*
- * Provides synchronization between device unregistration and netlink
- * commands on a device. To be used only by core.
+ * Positive refcount indicates that the device is currently
+ * registered and cannot be unregistered.
*/
refcount_t refcount;
struct completion unreg_completion;
int ib_check_mr_status(struct ib_mr *mr, u32 check_mask,
struct ib_mr_status *mr_status);
+/**
+ * ib_device_try_get: Hold a registration lock
+ * device: The device to lock
+ *
+ * A device under an active registration lock cannot become unregistered. It
+ * is only possible to obtain a registration lock on a device that is fully
+ * registered, otherwise this function returns false.
+ *
+ * The registration lock is only necessary for actions which require the
+ * device to still be registered. Uses that only require the device pointer to
+ * be valid should use get_device(&ibdev->dev) to hold the memory.
+ *
+ */
+static inline bool ib_device_try_get(struct ib_device *dev)
+{
+ return refcount_inc_not_zero(&dev->refcount);
+}
+
+void ib_device_put(struct ib_device *device);
struct net_device *ib_get_net_dev_by_params(struct ib_device *dev, u8 port,
u16 pkey, const union ib_gid *gid,
const struct sockaddr *addr);
__aligned_u64 que_addr;
};
+struct hns_roce_ib_create_srq_resp {
+ __u32 srqn;
+ __u32 reserved;
+};
+
struct hns_roce_ib_create_qp {
__aligned_u64 buf_addr;
__aligned_u64 db_addr;
per default but can be enabled through passing psi=1 on the
kernel commandline during boot.
+ This feature adds some code to the task wakeup and sleep
+ paths of the scheduler. The overhead is too low to affect
+ common scheduling-intense workloads in practice (such as
+ webservers, memcache), but it does show up in artificial
+ scheduler stress tests, such as hackbench.
+
+ If you are paranoid and not sure what the kernel will be
+ used for, say Y.
+
+ Say N if unsure.
+
endmenu # "CPU/Task time and stats accounting"
config CPU_ISOLATION
PIDs controller is designed to stop this from happening.
It should be noted that organisational operations (such as attaching
- to a cgroup hierarchy will *not* be blocked by the PIDs controller),
+ to a cgroup hierarchy) will *not* be blocked by the PIDs controller,
since the PIDs limit only affects a process's ability to fork, not to
attach to a cgroup.
void __user *buffer, size_t *lenp,
loff_t *ppos)
{
- int ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
-
- if (ret || !write)
- return ret;
-
+ int ret;
+ int perf_cpu = sysctl_perf_cpu_time_max_percent;
/*
* If throttling is disabled don't allow the write:
*/
- if (sysctl_perf_cpu_time_max_percent == 100 ||
- sysctl_perf_cpu_time_max_percent == 0)
+ if (write && (perf_cpu == 100 || perf_cpu == 0))
return -EINVAL;
+ ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
+ if (ret || !write)
+ return ret;
+
max_samples_per_tick = DIV_ROUND_UP(sysctl_perf_event_sample_rate, HZ);
perf_sample_period_ns = NSEC_PER_SEC / sysctl_perf_event_sample_rate;
update_perf_cpu_limits();
return NULL;
}
-static struct task_struct *find_child_reaper(struct task_struct *father)
+static struct task_struct *find_child_reaper(struct task_struct *father,
+ struct list_head *dead)
__releases(&tasklist_lock)
__acquires(&tasklist_lock)
{
struct pid_namespace *pid_ns = task_active_pid_ns(father);
struct task_struct *reaper = pid_ns->child_reaper;
+ struct task_struct *p, *n;
if (likely(reaper != father))
return reaper;
panic("Attempted to kill init! exitcode=0x%08x\n",
father->signal->group_exit_code ?: father->exit_code);
}
+
+ list_for_each_entry_safe(p, n, dead, ptrace_entry) {
+ list_del_init(&p->ptrace_entry);
+ release_task(p);
+ }
+
zap_pid_ns_processes(pid_ns);
write_lock_irq(&tasklist_lock);
exit_ptrace(father, dead);
/* Can drop and reacquire tasklist_lock */
- reaper = find_child_reaper(father);
+ reaper = find_child_reaper(father, dead);
if (list_empty(&father->children))
return;
* sampling of the aggregate task states would be.
*/
+#include "../workqueue_internal.h"
#include <linux/sched/loadavg.h>
#include <linux/seq_file.h>
#include <linux/proc_fs.h>
groupc->tasks[t]++;
write_seqcount_end(&groupc->seq);
-
- if (!delayed_work_pending(&group->clock_work))
- schedule_delayed_work(&group->clock_work, PSI_FREQ);
}
static struct psi_group *iterate_groups(struct task_struct *task, void **iter)
{
int cpu = task_cpu(task);
struct psi_group *group;
+ bool wake_clock = true;
void *iter = NULL;
if (!task->pid)
task->psi_flags &= ~clear;
task->psi_flags |= set;
- while ((group = iterate_groups(task, &iter)))
+ /*
+ * Periodic aggregation shuts off if there is a period of no
+ * task changes, so we wake it back up if necessary. However,
+ * don't do this if the task change is the aggregation worker
+ * itself going to sleep, or we'll ping-pong forever.
+ */
+ if (unlikely((clear & TSK_RUNNING) &&
+ (task->flags & PF_WQ_WORKER) &&
+ wq_worker_last_func(task) == psi_update_work))
+ wake_clock = false;
+
+ while ((group = iterate_groups(task, &iter))) {
psi_group_change(group, cpu, clear, set);
+ if (wake_clock && !delayed_work_pending(&group->clock_work))
+ schedule_delayed_work(&group->clock_work, PSI_FREQ);
+ }
}
void psi_memstall_tick(struct task_struct *task, int cpu)
}
/**
+ * wq_worker_last_func - retrieve worker's last work function
+ *
+ * Determine the last function a worker executed. This is called from
+ * the scheduler to get a worker's last known identity.
+ *
+ * CONTEXT:
+ * spin_lock_irq(rq->lock)
+ *
+ * Return:
+ * The last work function %current executed as a worker, NULL if it
+ * hasn't executed any work yet.
+ */
+work_func_t wq_worker_last_func(struct task_struct *task)
+{
+ struct worker *worker = kthread_data(task);
+
+ return worker->last_func;
+}
+
+/**
* worker_set_flags - set worker flags and adjust nr_running accordingly
* @worker: self
* @flags: flags to set
if (unlikely(cpu_intensive))
worker_clr_flags(worker, WORKER_CPU_INTENSIVE);
+ /* tag the worker for identification in schedule() */
+ worker->last_func = worker->current_func;
+
/* we're done with it, release */
hash_del(&worker->hentry);
worker->current_work = NULL;
/* used only by rescuers to point to the target workqueue */
struct workqueue_struct *rescue_wq; /* I: the workqueue to rescue */
+
+ /* used by the scheduler to determine a worker's last known identity */
+ work_func_t last_func;
};
/**
/*
* Scheduler hooks for concurrency managed workqueue. Only to be used from
- * sched/core.c and workqueue.c.
+ * sched/ and workqueue.c.
*/
void wq_worker_waking_up(struct task_struct *task, int cpu);
struct task_struct *wq_worker_sleeping(struct task_struct *task);
+work_func_t wq_worker_last_func(struct task_struct *task);
#endif /* _KERNEL_WORKQUEUE_INTERNAL_H */
config->test_driver = NULL;
kfree_const(config->test_fs);
- config->test_driver = NULL;
+ config->test_fs = NULL;
}
static void kmod_config_free(struct kmod_test_device *test_dev)
break;
}
if (ret & VM_FAULT_RETRY) {
- if (nonblocking)
+ if (nonblocking &&
+ !(fault_flags & FAULT_FLAG_RETRY_NOWAIT))
*nonblocking = 0;
*nr_pages = 0;
/*
UBSAN_SANITIZE_tags.o := n
KCOV_INSTRUMENT := n
+CFLAGS_REMOVE_common.o = -pg
CFLAGS_REMOVE_generic.o = -pg
# Function splitter causes unnecessary splits in __asan_load1/__asan_store1
# see: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=63533
if (fail || tk->addr_valid == 0) {
pr_err("Memory failure: %#lx: forcibly killing %s:%d because of failure to unmap corrupted page\n",
pfn, tk->tsk->comm, tk->tsk->pid);
- force_sig(SIGKILL, tk->tsk);
+ do_send_sig_info(SIGKILL, SEND_SIG_PRIV,
+ tk->tsk, PIDTYPE_PID);
}
/*
bool is_mem_section_removable(unsigned long start_pfn, unsigned long nr_pages)
{
struct page *page = pfn_to_page(start_pfn);
- struct page *end_page = page + nr_pages;
+ unsigned long end_pfn = min(start_pfn + nr_pages, zone_end_pfn(page_zone(page)));
+ struct page *end_page = pfn_to_page(end_pfn);
/* Check the starting page of each pageblock within the range */
for (; page < end_page; page = next_active_pageblock(page)) {
i++;
if (i == MAX_ORDER_NR_PAGES || pfn + i >= end_pfn)
continue;
+ /* Check if we got outside of the zone */
+ if (zone && !zone_spans_pfn(zone, pfn + i))
+ return 0;
page = pfn_to_page(pfn + i);
if (zone && page_zone(page) != zone)
return 0;
static unsigned long scan_movable_pages(unsigned long start, unsigned long end)
{
unsigned long pfn;
- struct page *page;
+
for (pfn = start; pfn < end; pfn++) {
- if (pfn_valid(pfn)) {
- page = pfn_to_page(pfn);
- if (PageLRU(page))
- return pfn;
- if (__PageMovable(page))
- return pfn;
- if (PageHuge(page)) {
- if (hugepage_migration_supported(page_hstate(page)) &&
- page_huge_active(page))
- return pfn;
- else
- pfn = round_up(pfn + 1,
- 1 << compound_order(page)) - 1;
- }
- }
+ struct page *page, *head;
+ unsigned long skip;
+
+ if (!pfn_valid(pfn))
+ continue;
+ page = pfn_to_page(pfn);
+ if (PageLRU(page))
+ return pfn;
+ if (__PageMovable(page))
+ return pfn;
+
+ if (!PageHuge(page))
+ continue;
+ head = compound_head(page);
+ if (hugepage_migration_supported(page_hstate(head)) &&
+ page_huge_active(head))
+ return pfn;
+ skip = (1 << compound_order(head)) - (page - head);
+ pfn += skip - 1;
}
return 0;
}
{
unsigned long pfn;
struct page *page;
- int not_managed = 0;
int ret = 0;
LIST_HEAD(source);
else
ret = isolate_movable_page(page, ISOLATE_UNEVICTABLE);
if (!ret) { /* Success */
- put_page(page);
list_add_tail(&page->lru, &source);
if (!__PageMovable(page))
inc_node_page_state(page, NR_ISOLATED_ANON +
} else {
pr_warn("failed to isolate pfn %lx\n", pfn);
dump_page(page, "isolation failed");
- put_page(page);
- /* Because we don't have big zone->lock. we should
- check this again here. */
- if (page_count(page)) {
- not_managed++;
- ret = -EBUSY;
- break;
- }
}
+ put_page(page);
}
if (!list_empty(&source)) {
- if (not_managed) {
- putback_movable_pages(&source);
- goto out;
- }
-
/* Allocate a new page from the nearest neighbor node */
ret = migrate_pages(&source, new_node_page, NULL, 0,
MIGRATE_SYNC, MR_MEMORY_HOTPLUG);
putback_movable_pages(&source);
}
}
-out:
+
return ret;
}
we assume this for now. .*/
if (!test_pages_in_a_zone(start_pfn, end_pfn, &valid_start,
&valid_end)) {
- mem_hotplug_done();
ret = -EINVAL;
reason = "multizone range";
goto failed_removal;
MIGRATE_MOVABLE,
SKIP_HWPOISON | REPORT_FAILURE);
if (ret) {
- mem_hotplug_done();
reason = "failure to isolate range";
goto failed_removal;
}
/* Simple case, sync compaction */
if (mode != MIGRATE_ASYNC) {
do {
- get_bh(bh);
lock_buffer(bh);
bh = bh->b_this_page;
/* async case, we cannot block on lock_buffer so use trylock_buffer */
do {
- get_bh(bh);
if (!trylock_buffer(bh)) {
/*
* We failed to lock the buffer and cannot stall in
* async migration. Release the taken locks
*/
struct buffer_head *failed_bh = bh;
- put_bh(failed_bh);
bh = head;
while (bh != failed_bh) {
unlock_buffer(bh);
- put_bh(bh);
bh = bh->b_this_page;
}
return false;
bh = head;
do {
unlock_buffer(bh);
- put_bh(bh);
bh = bh->b_this_page;
} while (bh != head);
* If migration is successful, decrease refcount of the newpage
* which will not free the page because new page owner increased
* refcounter. As well, if it is LRU page, add the page to LRU
- * list in here.
+ * list in here. Use the old state of the isolated source page to
+ * determine if we migrated a LRU page. newpage was already unlocked
+ * and possibly modified by its owner - don't rely on the page
+ * state.
*/
if (rc == MIGRATEPAGE_SUCCESS) {
- if (unlikely(__PageMovable(newpage)))
+ if (unlikely(!is_lru))
put_page(newpage);
else
putback_lru_page(newpage);
static void wake_oom_reaper(struct task_struct *tsk)
{
- /* tsk is already queued? */
- if (tsk == oom_reaper_list || tsk->oom_reaper_list)
+ /* mm is already queued? */
+ if (test_and_set_bit(MMF_OOM_REAP_QUEUED, &tsk->signal->oom_mm->flags))
return;
get_task_struct(tsk);
* still freeing memory.
*/
read_lock(&tasklist_lock);
+
+ /*
+ * The task 'p' might have already exited before reaching here. The
+ * put_task_struct() will free task_struct 'p' while the loop still try
+ * to access the field of 'p', so, get an extra reference.
+ */
+ get_task_struct(p);
for_each_thread(p, t) {
list_for_each_entry(child, &t->children, sibling) {
unsigned int child_points;
}
}
}
+ put_task_struct(p);
read_unlock(&tasklist_lock);
/*
xt_compat_lock(NFPROTO_BRIDGE);
- ret = xt_compat_init_offsets(NFPROTO_BRIDGE, tmp.nentries);
- if (ret < 0)
- goto out_unlock;
+ if (tmp.nentries) {
+ ret = xt_compat_init_offsets(NFPROTO_BRIDGE, tmp.nentries);
+ if (ret < 0)
+ goto out_unlock;
+ }
+
ret = compat_copy_entries(entries_tmp, tmp.entries_size, &state);
if (ret < 0)
goto out_unlock;
set_bit(__LINK_STATE_PRESENT, &dev->state);
set_bit(__LINK_STATE_START, &dev->state);
+ /* napi_busy_loop stats accounting wants this */
+ dev_net_set(dev, &init_net);
+
/* Note : We dont allocate pcpu_refcnt for dummy devices,
* because users of this 'device' dont need to change
* its refcount.
#include <net/dn_neigh.h>
#include <net/dn_fib.h>
-#define DN_IFREQ_SIZE (sizeof(struct ifreq) - sizeof(struct sockaddr) + sizeof(struct sockaddr_dn))
+#define DN_IFREQ_SIZE (offsetof(struct ifreq, ifr_ifru) + sizeof(struct sockaddr_dn))
static char dn_rt_all_end_mcast[ETH_ALEN] = {0xAB,0x00,0x00,0x04,0x00,0x00};
static char dn_rt_all_rt_mcast[ETH_ALEN] = {0xAB,0x00,0x00,0x03,0x00,0x00};
return 0;
}
+static int vti_input_ipip(struct sk_buff *skb, int nexthdr, __be32 spi,
+ int encap_type)
+{
+ struct ip_tunnel *tunnel;
+ const struct iphdr *iph = ip_hdr(skb);
+ struct net *net = dev_net(skb->dev);
+ struct ip_tunnel_net *itn = net_generic(net, vti_net_id);
+
+ tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY,
+ iph->saddr, iph->daddr, 0);
+ if (tunnel) {
+ if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb))
+ goto drop;
+
+ XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4 = tunnel;
+
+ skb->dev = tunnel->dev;
+
+ return xfrm_input(skb, nexthdr, spi, encap_type);
+ }
+
+ return -EINVAL;
+drop:
+ kfree_skb(skb);
+ return 0;
+}
+
static int vti_rcv(struct sk_buff *skb)
{
XFRM_SPI_SKB_CB(skb)->family = AF_INET;
return vti_input(skb, ip_hdr(skb)->protocol, 0, 0);
}
+static int vti_rcv_ipip(struct sk_buff *skb)
+{
+ XFRM_SPI_SKB_CB(skb)->family = AF_INET;
+ XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct iphdr, daddr);
+
+ return vti_input_ipip(skb, ip_hdr(skb)->protocol, ip_hdr(skb)->saddr, 0);
+}
+
static int vti_rcv_cb(struct sk_buff *skb, int err)
{
unsigned short family;
.priority = 100,
};
+static struct xfrm_tunnel ipip_handler __read_mostly = {
+ .handler = vti_rcv_ipip,
+ .err_handler = vti4_err,
+ .priority = 0,
+};
+
static int __net_init vti_init_net(struct net *net)
{
int err;
if (err < 0)
goto xfrm_proto_comp_failed;
+ msg = "ipip tunnel";
+ err = xfrm4_tunnel_register(&ipip_handler, AF_INET);
+ if (err < 0) {
+ pr_info("%s: cant't register tunnel\n",__func__);
+ goto xfrm_tunnel_failed;
+ }
+
msg = "netlink interface";
err = rtnl_link_register(&vti_link_ops);
if (err < 0)
rtnl_link_failed:
xfrm4_protocol_deregister(&vti_ipcomp4_protocol, IPPROTO_COMP);
+xfrm_tunnel_failed:
+ xfrm4_tunnel_deregister(&ipip_handler, AF_INET);
xfrm_proto_comp_failed:
xfrm4_protocol_deregister(&vti_ah4_protocol, IPPROTO_AH);
xfrm_proto_ah_failed:
static void clusterip_net_exit(struct net *net)
{
+#ifdef CONFIG_PROC_FS
struct clusterip_net *cn = clusterip_pernet(net);
-#ifdef CONFIG_PROC_FS
mutex_lock(&cn->mutex);
proc_remove(cn->procdir);
cn->procdir = NULL;
continue;
rhltable_remove(&mrt->mfc_hash, &c->mnode, ip6mr_rht_params);
list_del_rcu(&c->list);
+ call_ip6mr_mfc_entry_notifiers(read_pnet(&mrt->net),
+ FIB_EVENT_ENTRY_DEL,
+ (struct mfc6_cache *)c, mrt->id);
mr6_netlink_event(mrt, (struct mfc6_cache *)c, RTM_DELROUTE);
mr_cache_put(c);
}
spin_lock_bh(&mfc_unres_lock);
list_for_each_entry_safe(c, tmp, &mrt->mfc_unres_queue, list) {
list_del(&c->list);
- call_ip6mr_mfc_entry_notifiers(read_pnet(&mrt->net),
- FIB_EVENT_ENTRY_DEL,
- (struct mfc6_cache *)c,
- mrt->id);
mr6_netlink_event(mrt, (struct mfc6_cache *)c,
RTM_DELROUTE);
ip6mr_destroy_unres(mrt, (struct mfc6_cache *)c);
u->udp_timeout);
#ifdef CONFIG_IP_VS_PROTO_TCP
+ if (u->tcp_timeout < 0 || u->tcp_timeout > (INT_MAX / HZ) ||
+ u->tcp_fin_timeout < 0 || u->tcp_fin_timeout > (INT_MAX / HZ)) {
+ return -EINVAL;
+ }
+#endif
+
+#ifdef CONFIG_IP_VS_PROTO_UDP
+ if (u->udp_timeout < 0 || u->udp_timeout > (INT_MAX / HZ))
+ return -EINVAL;
+#endif
+
+#ifdef CONFIG_IP_VS_PROTO_TCP
if (u->tcp_timeout) {
pd = ip_vs_proto_data_get(ipvs, IPPROTO_TCP);
pd->timeout_table[IP_VS_TCP_S_ESTABLISHED]
int ttl_check,
struct nf_osf_hdr_ctx *ctx)
{
+ const __u8 *optpinit = ctx->optp;
unsigned int check_WSS = 0;
int fmatch = FMATCH_WRONG;
int foptsize, optnum;
}
}
+ if (fmatch != FMATCH_OK)
+ ctx->optp = optpinit;
+
return fmatch == FMATCH_OK;
}
#include <linux/netfilter_bridge/ebtables.h>
#include <linux/netfilter_arp/arp_tables.h>
#include <net/netfilter/nf_tables.h>
+#include <net/netns/generic.h>
struct nft_xt {
struct list_head head;
struct nft_expr_ops ops;
- unsigned int refcnt;
+ refcount_t refcnt;
+
+ /* used only when transaction mutex is locked */
+ unsigned int listcnt;
/* Unlike other expressions, ops doesn't have static storage duration.
* nft core assumes they do. We use kfree_rcu so that nft core can
void *info;
};
+struct nft_compat_net {
+ struct list_head nft_target_list;
+ struct list_head nft_match_list;
+};
+
+static unsigned int nft_compat_net_id __read_mostly;
+static struct nft_expr_type nft_match_type;
+static struct nft_expr_type nft_target_type;
+
+static struct nft_compat_net *nft_compat_pernet(struct net *net)
+{
+ return net_generic(net, nft_compat_net_id);
+}
+
static bool nft_xt_put(struct nft_xt *xt)
{
- if (--xt->refcnt == 0) {
- list_del(&xt->head);
+ if (refcount_dec_and_test(&xt->refcnt)) {
+ WARN_ON_ONCE(!list_empty(&xt->head));
kfree_rcu(xt, rcu_head);
return true;
}
return -EINVAL;
nft_xt = container_of(expr->ops, struct nft_xt, ops);
- nft_xt->refcnt++;
+ refcount_inc(&nft_xt->refcnt);
return 0;
}
return ret;
nft_xt = container_of(expr->ops, struct nft_xt, ops);
- nft_xt->refcnt++;
+ refcount_inc(&nft_xt->refcnt);
return 0;
}
__nft_match_destroy(ctx, expr, nft_expr_priv(expr));
}
+static void nft_compat_activate(const struct nft_ctx *ctx,
+ const struct nft_expr *expr,
+ struct list_head *h)
+{
+ struct nft_xt *xt = container_of(expr->ops, struct nft_xt, ops);
+
+ if (xt->listcnt == 0)
+ list_add(&xt->head, h);
+
+ xt->listcnt++;
+}
+
+static void nft_compat_activate_mt(const struct nft_ctx *ctx,
+ const struct nft_expr *expr)
+{
+ struct nft_compat_net *cn = nft_compat_pernet(ctx->net);
+
+ nft_compat_activate(ctx, expr, &cn->nft_match_list);
+}
+
+static void nft_compat_activate_tg(const struct nft_ctx *ctx,
+ const struct nft_expr *expr)
+{
+ struct nft_compat_net *cn = nft_compat_pernet(ctx->net);
+
+ nft_compat_activate(ctx, expr, &cn->nft_target_list);
+}
+
+static void nft_compat_deactivate(const struct nft_ctx *ctx,
+ const struct nft_expr *expr)
+{
+ struct nft_xt *xt = container_of(expr->ops, struct nft_xt, ops);
+
+ if (--xt->listcnt == 0)
+ list_del_init(&xt->head);
+}
+
static void
nft_match_large_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr)
{
.cb = nfnl_nft_compat_cb,
};
-static LIST_HEAD(nft_match_list);
-
-static struct nft_expr_type nft_match_type;
-
static bool nft_match_cmp(const struct xt_match *match,
const char *name, u32 rev, u32 family)
{
nft_match_select_ops(const struct nft_ctx *ctx,
const struct nlattr * const tb[])
{
+ struct nft_compat_net *cn;
struct nft_xt *nft_match;
struct xt_match *match;
unsigned int matchsize;
rev = ntohl(nla_get_be32(tb[NFTA_MATCH_REV]));
family = ctx->family;
+ cn = nft_compat_pernet(ctx->net);
+
/* Re-use the existing match if it's already loaded. */
- list_for_each_entry(nft_match, &nft_match_list, head) {
+ list_for_each_entry(nft_match, &cn->nft_match_list, head) {
struct xt_match *match = nft_match->ops.data;
if (nft_match_cmp(match, mt_name, rev, family))
goto err;
}
- nft_match->refcnt = 0;
+ refcount_set(&nft_match->refcnt, 0);
nft_match->ops.type = &nft_match_type;
nft_match->ops.eval = nft_match_eval;
nft_match->ops.init = nft_match_init;
nft_match->ops.destroy = nft_match_destroy;
+ nft_match->ops.activate = nft_compat_activate_mt;
+ nft_match->ops.deactivate = nft_compat_deactivate;
nft_match->ops.dump = nft_match_dump;
nft_match->ops.validate = nft_match_validate;
nft_match->ops.data = match;
nft_match->ops.size = matchsize;
- list_add(&nft_match->head, &nft_match_list);
+ nft_match->listcnt = 1;
+ list_add(&nft_match->head, &cn->nft_match_list);
return &nft_match->ops;
err:
.owner = THIS_MODULE,
};
-static LIST_HEAD(nft_target_list);
-
-static struct nft_expr_type nft_target_type;
-
static bool nft_target_cmp(const struct xt_target *tg,
const char *name, u32 rev, u32 family)
{
nft_target_select_ops(const struct nft_ctx *ctx,
const struct nlattr * const tb[])
{
+ struct nft_compat_net *cn;
struct nft_xt *nft_target;
struct xt_target *target;
char *tg_name;
strcmp(tg_name, "standard") == 0)
return ERR_PTR(-EINVAL);
+ cn = nft_compat_pernet(ctx->net);
/* Re-use the existing target if it's already loaded. */
- list_for_each_entry(nft_target, &nft_target_list, head) {
+ list_for_each_entry(nft_target, &cn->nft_target_list, head) {
struct xt_target *target = nft_target->ops.data;
if (!target->target)
goto err;
}
- nft_target->refcnt = 0;
+ refcount_set(&nft_target->refcnt, 0);
nft_target->ops.type = &nft_target_type;
nft_target->ops.size = NFT_EXPR_SIZE(XT_ALIGN(target->targetsize));
nft_target->ops.init = nft_target_init;
nft_target->ops.destroy = nft_target_destroy;
+ nft_target->ops.activate = nft_compat_activate_tg;
+ nft_target->ops.deactivate = nft_compat_deactivate;
nft_target->ops.dump = nft_target_dump;
nft_target->ops.validate = nft_target_validate;
nft_target->ops.data = target;
else
nft_target->ops.eval = nft_target_eval_xt;
- list_add(&nft_target->head, &nft_target_list);
+ nft_target->listcnt = 1;
+ list_add(&nft_target->head, &cn->nft_target_list);
return &nft_target->ops;
err:
.owner = THIS_MODULE,
};
+static int __net_init nft_compat_init_net(struct net *net)
+{
+ struct nft_compat_net *cn = nft_compat_pernet(net);
+
+ INIT_LIST_HEAD(&cn->nft_target_list);
+ INIT_LIST_HEAD(&cn->nft_match_list);
+
+ return 0;
+}
+
+static void __net_exit nft_compat_exit_net(struct net *net)
+{
+ struct nft_compat_net *cn = nft_compat_pernet(net);
+ struct nft_xt *xt, *next;
+
+ if (list_empty(&cn->nft_match_list) &&
+ list_empty(&cn->nft_target_list))
+ return;
+
+ /* If there was an error that caused nft_xt expr to not be initialized
+ * fully and noone else requested the same expression later, the lists
+ * contain 0-refcount entries that still hold module reference.
+ *
+ * Clean them here.
+ */
+ mutex_lock(&net->nft.commit_mutex);
+ list_for_each_entry_safe(xt, next, &cn->nft_target_list, head) {
+ struct xt_target *target = xt->ops.data;
+
+ list_del_init(&xt->head);
+
+ if (refcount_read(&xt->refcnt))
+ continue;
+ module_put(target->me);
+ kfree(xt);
+ }
+
+ list_for_each_entry_safe(xt, next, &cn->nft_match_list, head) {
+ struct xt_match *match = xt->ops.data;
+
+ list_del_init(&xt->head);
+
+ if (refcount_read(&xt->refcnt))
+ continue;
+ module_put(match->me);
+ kfree(xt);
+ }
+ mutex_unlock(&net->nft.commit_mutex);
+}
+
+static struct pernet_operations nft_compat_net_ops = {
+ .init = nft_compat_init_net,
+ .exit = nft_compat_exit_net,
+ .id = &nft_compat_net_id,
+ .size = sizeof(struct nft_compat_net),
+};
+
static int __init nft_compat_module_init(void)
{
int ret;
+ ret = register_pernet_subsys(&nft_compat_net_ops);
+ if (ret < 0)
+ goto err_target;
+
ret = nft_register_expr(&nft_match_type);
if (ret < 0)
- return ret;
+ goto err_pernet;
ret = nft_register_expr(&nft_target_type);
if (ret < 0)
}
return ret;
-
err_target:
nft_unregister_expr(&nft_target_type);
err_match:
nft_unregister_expr(&nft_match_type);
+err_pernet:
+ unregister_pernet_subsys(&nft_compat_net_ops);
return ret;
}
static void __exit nft_compat_module_exit(void)
{
- struct nft_xt *xt, *next;
-
- /* list should be empty here, it can be non-empty only in case there
- * was an error that caused nft_xt expr to not be initialized fully
- * and noone else requested the same expression later.
- *
- * In this case, the lists contain 0-refcount entries that still
- * hold module reference.
- */
- list_for_each_entry_safe(xt, next, &nft_target_list, head) {
- struct xt_target *target = xt->ops.data;
-
- if (WARN_ON_ONCE(xt->refcnt))
- continue;
- module_put(target->me);
- kfree(xt);
- }
-
- list_for_each_entry_safe(xt, next, &nft_match_list, head) {
- struct xt_match *match = xt->ops.data;
-
- if (WARN_ON_ONCE(xt->refcnt))
- continue;
- module_put(match->me);
- kfree(xt);
- }
nfnetlink_subsys_unregister(&nfnl_compat_subsys);
nft_unregister_expr(&nft_target_type);
nft_unregister_expr(&nft_match_type);
+ unregister_pernet_subsys(&nft_compat_net_ops);
}
MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_NFT_COMPAT);
{
struct nr_sock *nr = nr_sk(sk);
- mod_timer(&nr->t1timer, jiffies + nr->t1);
+ sk_reset_timer(sk, &nr->t1timer, jiffies + nr->t1);
}
void nr_start_t2timer(struct sock *sk)
{
struct nr_sock *nr = nr_sk(sk);
- mod_timer(&nr->t2timer, jiffies + nr->t2);
+ sk_reset_timer(sk, &nr->t2timer, jiffies + nr->t2);
}
void nr_start_t4timer(struct sock *sk)
{
struct nr_sock *nr = nr_sk(sk);
- mod_timer(&nr->t4timer, jiffies + nr->t4);
+ sk_reset_timer(sk, &nr->t4timer, jiffies + nr->t4);
}
void nr_start_idletimer(struct sock *sk)
struct nr_sock *nr = nr_sk(sk);
if (nr->idle > 0)
- mod_timer(&nr->idletimer, jiffies + nr->idle);
+ sk_reset_timer(sk, &nr->idletimer, jiffies + nr->idle);
}
void nr_start_heartbeat(struct sock *sk)
{
- mod_timer(&sk->sk_timer, jiffies + 5 * HZ);
+ sk_reset_timer(sk, &sk->sk_timer, jiffies + 5 * HZ);
}
void nr_stop_t1timer(struct sock *sk)
{
- del_timer(&nr_sk(sk)->t1timer);
+ sk_stop_timer(sk, &nr_sk(sk)->t1timer);
}
void nr_stop_t2timer(struct sock *sk)
{
- del_timer(&nr_sk(sk)->t2timer);
+ sk_stop_timer(sk, &nr_sk(sk)->t2timer);
}
void nr_stop_t4timer(struct sock *sk)
{
- del_timer(&nr_sk(sk)->t4timer);
+ sk_stop_timer(sk, &nr_sk(sk)->t4timer);
}
void nr_stop_idletimer(struct sock *sk)
{
- del_timer(&nr_sk(sk)->idletimer);
+ sk_stop_timer(sk, &nr_sk(sk)->idletimer);
}
void nr_stop_heartbeat(struct sock *sk)
{
- del_timer(&sk->sk_timer);
+ sk_stop_timer(sk, &sk->sk_timer);
}
int nr_t1timer_running(struct sock *sk)
/*
* Route a frame to an appropriate AX.25 connection.
+ * A NULL ax25_cb indicates an internally generated frame.
*/
int rose_route_frame(struct sk_buff *skb, ax25_cb *ax25)
{
if (skb->len < ROSE_MIN_LEN)
return res;
+
+ if (!ax25)
+ return rose_loopback_queue(skb, NULL);
+
frametype = skb->data[2];
lci = ((skb->data[0] << 8) & 0xF00) + ((skb->data[1] << 0) & 0x0FF);
if (frametype == ROSE_CALL_REQUEST &&
struct scatterlist *sge = sk_msg_elem(msg_en, start);
int rc;
+ memcpy(rec->iv_data, tls_ctx->tx.iv, sizeof(rec->iv_data));
+
sge->offset += tls_ctx->tx.prepend_size;
sge->length -= tls_ctx->tx.prepend_size;
aead_request_set_ad(aead_req, TLS_AAD_SPACE_SIZE);
aead_request_set_crypt(aead_req, rec->sg_aead_in,
rec->sg_aead_out,
- data_len, tls_ctx->tx.iv);
+ data_len, rec->iv_data);
aead_request_set_callback(aead_req, CRYPTO_TFM_REQ_MAY_BACKLOG,
tls_encrypt_done, sk);
if (atomic_read(&ctx->encrypt_pending))
crypto_wait_req(-EINPROGRESS, &ctx->async_wait);
+ release_sock(sk);
cancel_delayed_work_sync(&ctx->tx_work.work);
+ lock_sock(sk);
/* Tx whatever records we can transmit and abandon the rest */
tls_tx_records(sk, -1);
mutex_unlock(&hash_resize_mutex);
}
-static void xfrm_hash_reset_inexact_table(struct net *net)
-{
- struct xfrm_pol_inexact_bin *b;
-
- lockdep_assert_held(&net->xfrm.xfrm_policy_lock);
-
- list_for_each_entry(b, &net->xfrm.inexact_bins, inexact_bins)
- INIT_HLIST_HEAD(&b->hhead);
-}
-
/* Make sure *pol can be inserted into fastbin.
* Useful to check that later insert requests will be sucessful
* (provided xfrm_policy_lock is held throughout).
u16 family)
{
unsigned int matched_s, matched_d;
- struct hlist_node *newpos = NULL;
struct xfrm_policy *policy, *p;
matched_s = 0;
matched_d = 0;
list_for_each_entry_reverse(policy, &net->xfrm.policy_all, walk.all) {
+ struct hlist_node *newpos = NULL;
bool matches_s, matches_d;
if (!policy->bydst_reinsert)
policy->bydst_reinsert = false;
hlist_for_each_entry(p, &n->hhead, bydst) {
- if (policy->priority >= p->priority)
+ if (policy->priority > p->priority)
+ newpos = &p->bydst;
+ else if (policy->priority == p->priority &&
+ policy->pos > p->pos)
newpos = &p->bydst;
else
break;
}
if (newpos)
- hlist_add_behind(&policy->bydst, newpos);
+ hlist_add_behind_rcu(&policy->bydst, newpos);
else
- hlist_add_head(&policy->bydst, &n->hhead);
+ hlist_add_head_rcu(&policy->bydst, &n->hhead);
/* paranoia checks follow.
* Check that the reinserted policy matches at least
struct rb_root *new,
u16 family)
{
- struct rb_node **p, *parent = NULL;
struct xfrm_pol_inexact_node *node;
+ struct rb_node **p, *parent;
/* we should not have another subtree here */
WARN_ON_ONCE(!RB_EMPTY_ROOT(&n->root));
-
+restart:
+ parent = NULL;
p = &new->rb_node;
while (*p) {
u8 prefixlen;
} else {
struct xfrm_policy *tmp;
- hlist_for_each_entry(tmp, &node->hhead, bydst)
- tmp->bydst_reinsert = true;
- hlist_for_each_entry(tmp, &n->hhead, bydst)
+ hlist_for_each_entry(tmp, &n->hhead, bydst) {
tmp->bydst_reinsert = true;
+ hlist_del_rcu(&tmp->bydst);
+ }
- INIT_HLIST_HEAD(&node->hhead);
xfrm_policy_inexact_list_reinsert(net, node, family);
if (node->prefixlen == n->prefixlen) {
kfree_rcu(n, rcu);
n = node;
n->prefixlen = prefixlen;
- *p = new->rb_node;
- parent = NULL;
+ goto restart;
}
}
family);
}
- hlist_for_each_entry(tmp, &v->hhead, bydst)
- tmp->bydst_reinsert = true;
- hlist_for_each_entry(tmp, &n->hhead, bydst)
+ hlist_for_each_entry(tmp, &v->hhead, bydst) {
tmp->bydst_reinsert = true;
+ hlist_del_rcu(&tmp->bydst);
+ }
- INIT_HLIST_HEAD(&n->hhead);
xfrm_policy_inexact_list_reinsert(net, n, family);
}
} while (read_seqretry(&net->xfrm.policy_hthresh.lock, seq));
spin_lock_bh(&net->xfrm.xfrm_policy_lock);
+ write_seqcount_begin(&xfrm_policy_hash_generation);
/* make sure that we can insert the indirect policies again before
* we start with destructive action.
}
/* reset the bydst and inexact table in all directions */
- xfrm_hash_reset_inexact_table(net);
-
for (dir = 0; dir < XFRM_POLICY_MAX; dir++) {
- INIT_HLIST_HEAD(&net->xfrm.policy_inexact[dir]);
+ struct hlist_node *n;
+
+ hlist_for_each_entry_safe(policy, n,
+ &net->xfrm.policy_inexact[dir],
+ bydst_inexact_list)
+ hlist_del_init(&policy->bydst_inexact_list);
+
hmask = net->xfrm.policy_bydst[dir].hmask;
odst = net->xfrm.policy_bydst[dir].table;
for (i = hmask; i >= 0; i--)
newpos = NULL;
chain = policy_hash_bysel(net, &policy->selector,
policy->family, dir);
+
+ hlist_del_rcu(&policy->bydst);
+
if (!chain) {
void *p = xfrm_policy_inexact_insert(policy, dir, 0);
out_unlock:
__xfrm_policy_inexact_flush(net);
+ write_seqcount_end(&xfrm_policy_hash_generation);
spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
mutex_unlock(&hash_resize_mutex);
dst_copy_metrics(dst1, dst);
if (xfrm[i]->props.mode != XFRM_MODE_TRANSPORT) {
- __u32 mark = xfrm_smark_get(fl->flowi_mark, xfrm[i]);
+ __u32 mark = 0;
+
+ if (xfrm[i]->props.smark.v || xfrm[i]->props.smark.m)
+ mark = xfrm_smark_get(fl->flowi_mark, xfrm[i]);
family = xfrm[i]->props.family;
dst = xfrm_dst_lookup(xfrm[i], tos, fl->flowi_oif,
if (!ut[i].family)
ut[i].family = family;
- if ((ut[i].mode == XFRM_MODE_TRANSPORT) &&
- (ut[i].family != prev_family))
- return -EINVAL;
-
+ switch (ut[i].mode) {
+ case XFRM_MODE_TUNNEL:
+ case XFRM_MODE_BEET:
+ break;
+ default:
+ if (ut[i].family != prev_family)
+ return -EINVAL;
+ break;
+ }
if (ut[i].mode >= XFRM_MODE_MAX)
return -EINVAL;
new = aa_label_merge(label, target, GFP_KERNEL);
if (IS_ERR_OR_NULL(new)) {
info = "failed to build target label";
- error = PTR_ERR(new);
+ if (!new)
+ error = -ENOMEM;
+ else
+ error = PTR_ERR(new);
new = NULL;
perms.allow = 0;
goto audit;
return apparmor_ip_postroute(priv, skb, state);
}
+#if IS_ENABLED(CONFIG_IPV6)
static unsigned int apparmor_ipv6_postroute(void *priv,
struct sk_buff *skb,
const struct nf_hook_state *state)
{
return apparmor_ip_postroute(priv, skb, state);
}
+#endif
static const struct nf_hook_ops apparmor_nf_ops[] = {
{
return 0;
}
+/* allow waiting for a capture stream that hasn't been started */
+#if IS_ENABLED(CONFIG_SND_PCM_OSS)
+#define wait_capture_start(substream) ((substream)->oss.oss)
+#else
+#define wait_capture_start(substream) false
+#endif
+
/* the common loop for read/write data */
snd_pcm_sframes_t __snd_pcm_lib_xfer(struct snd_pcm_substream *substream,
void *data, bool interleaved,
err = snd_pcm_start(substream);
if (err < 0)
goto _end_unlock;
- } else {
+ } else if (!wait_capture_start(substream)) {
/* nothing to do */
err = 0;
goto _end_unlock;
int codec_variant; /* flag for other variants */
unsigned int has_alc5505_dsp:1;
unsigned int no_depop_delay:1;
+ unsigned int done_hp_init:1;
/* for PLL fix */
hda_nid_t pll_nid;
snd_hda_shutup_pins(codec);
}
+static void alc294_hp_init(struct hda_codec *codec)
+{
+ struct alc_spec *spec = codec->spec;
+ hda_nid_t hp_pin = spec->gen.autocfg.hp_pins[0];
+ int i, val;
+
+ if (!hp_pin)
+ return;
+
+ snd_hda_codec_write(codec, hp_pin, 0,
+ AC_VERB_SET_AMP_GAIN_MUTE, AMP_OUT_MUTE);
+
+ msleep(100);
+
+ snd_hda_codec_write(codec, hp_pin, 0,
+ AC_VERB_SET_PIN_WIDGET_CONTROL, 0x0);
+
+ alc_update_coef_idx(codec, 0x6f, 0x000f, 0);/* Set HP depop to manual mode */
+ alc_update_coefex_idx(codec, 0x58, 0x00, 0x8000, 0x8000); /* HP depop procedure start */
+
+ /* Wait for depop procedure finish */
+ val = alc_read_coefex_idx(codec, 0x58, 0x01);
+ for (i = 0; i < 20 && val & 0x0080; i++) {
+ msleep(50);
+ val = alc_read_coefex_idx(codec, 0x58, 0x01);
+ }
+ /* Set HP depop to auto mode */
+ alc_update_coef_idx(codec, 0x6f, 0x000f, 0x000b);
+ msleep(50);
+}
+
+static void alc294_init(struct hda_codec *codec)
+{
+ struct alc_spec *spec = codec->spec;
+
+ if (!spec->done_hp_init) {
+ alc294_hp_init(codec);
+ spec->done_hp_init = true;
+ }
+ alc_default_init(codec);
+}
+
static void alc5505_coef_set(struct hda_codec *codec, unsigned int index_reg,
unsigned int val)
{
alc_update_coef_idx(codec, 0x4, 0, 1<<11);
}
-static void alc294_hp_init(struct hda_codec *codec)
-{
- struct alc_spec *spec = codec->spec;
- hda_nid_t hp_pin = spec->gen.autocfg.hp_pins[0];
- int i, val;
-
- if (!hp_pin)
- return;
-
- snd_hda_codec_write(codec, hp_pin, 0,
- AC_VERB_SET_AMP_GAIN_MUTE, AMP_OUT_MUTE);
-
- msleep(100);
-
- snd_hda_codec_write(codec, hp_pin, 0,
- AC_VERB_SET_PIN_WIDGET_CONTROL, 0x0);
-
- alc_update_coef_idx(codec, 0x6f, 0x000f, 0);/* Set HP depop to manual mode */
- alc_update_coefex_idx(codec, 0x58, 0x00, 0x8000, 0x8000); /* HP depop procedure start */
-
- /* Wait for depop procedure finish */
- val = alc_read_coefex_idx(codec, 0x58, 0x01);
- for (i = 0; i < 20 && val & 0x0080; i++) {
- msleep(50);
- val = alc_read_coefex_idx(codec, 0x58, 0x01);
- }
- /* Set HP depop to auto mode */
- alc_update_coef_idx(codec, 0x6f, 0x000f, 0x000b);
- msleep(50);
-}
-
/*
*/
static int patch_alc269(struct hda_codec *codec)
spec->codec_variant = ALC269_TYPE_ALC294;
spec->gen.mixer_nid = 0; /* ALC2x4 does not have any loopback mixer path */
alc_update_coef_idx(codec, 0x6b, 0x0018, (1<<4) | (1<<3)); /* UAJ MIC Vref control by verb */
- alc294_hp_init(codec);
+ spec->init_hook = alc294_init;
break;
case 0x10ec0300:
spec->codec_variant = ALC269_TYPE_ALC300;
spec->codec_variant = ALC269_TYPE_ALC700;
spec->gen.mixer_nid = 0; /* ALC700 does not have any loopback mixer path */
alc_update_coef_idx(codec, 0x4a, 1 << 15, 0); /* Combo jack auto trigger control */
- alc294_hp_init(codec);
+ spec->init_hook = alc294_init;
break;
}
return SNDRV_PCM_FMTBIT_DSD_U32_BE;
break;
+ case USB_ID(0x10cb, 0x0103): /* The Bit Opus #3; with fp->dsd_raw */
case USB_ID(0x152a, 0x85de): /* SMSL D1 DAC */
case USB_ID(0x16d0, 0x09dd): /* Encore mDSD */
case USB_ID(0x0d8c, 0x0316): /* Hegel HD12 DSD */
.force_header = false,
};
struct perf_evsel *ev2;
- static bool init;
u64 val;
- if (!init) {
- perf_stat__init_shadow_stats();
- init = true;
- }
if (!evsel->stats)
perf_evlist__alloc_stats(script->session->evlist, false);
if (evsel_script(evsel->leader)->gnum++ == 0)
return;
}
- if (PRINT_FIELD(TRACE)) {
+ if (PRINT_FIELD(TRACE) && sample->raw_data) {
event_format__fprintf(evsel->tp_format, sample->cpu,
sample->raw_data, sample->raw_size, fp);
}
signal(SIGINT, sig_handler);
+ perf_stat__init_shadow_stats();
+
/* override event processing functions */
if (script->show_task_events) {
script->tool.comm = process_comm_event;
return ret;
}
-static int disasm__cmp(struct annotation_line *a, struct annotation_line *b)
+static double disasm__cmp(struct annotation_line *a, struct annotation_line *b,
+ int percent_type)
{
int i;
for (i = 0; i < a->data_nr; i++) {
- if (a->data[i].percent == b->data[i].percent)
+ if (a->data[i].percent[percent_type] == b->data[i].percent[percent_type])
continue;
- return a->data[i].percent < b->data[i].percent;
+ return a->data[i].percent[percent_type] -
+ b->data[i].percent[percent_type];
}
return 0;
}
-static void disasm_rb_tree__insert(struct rb_root *root, struct annotation_line *al)
+static void disasm_rb_tree__insert(struct annotate_browser *browser,
+ struct annotation_line *al)
{
+ struct rb_root *root = &browser->entries;
struct rb_node **p = &root->rb_node;
struct rb_node *parent = NULL;
struct annotation_line *l;
parent = *p;
l = rb_entry(parent, struct annotation_line, rb_node);
- if (disasm__cmp(al, l))
+ if (disasm__cmp(al, l, browser->opts->percent_type) < 0)
p = &(*p)->rb_left;
else
p = &(*p)->rb_right;
RB_CLEAR_NODE(&pos->al.rb_node);
continue;
}
- disasm_rb_tree__insert(&browser->entries, &pos->al);
+ disasm_rb_tree__insert(browser, &pos->al);
}
pthread_mutex_unlock(¬es->lock);
if (!cpu_list)
return cpu_map__read_all_cpu_map();
- if (!isdigit(*cpu_list))
+ /*
+ * must handle the case of empty cpumap to cover
+ * TOPOLOGY header for NUMA nodes with no CPU
+ * ( e.g., because of CPU hotplug)
+ */
+ if (!isdigit(*cpu_list) && *cpu_list != '\0')
goto out;
while (isdigit(*cpu_list)) {
if (nr_cpus > 0)
cpus = cpu_map__trim_new(nr_cpus, tmp_cpus);
- else
+ else if (*cpu_list != '\0')
cpus = cpu_map__default_new();
+ else
+ cpus = cpu_map__dummy_new();
invalid:
free(tmp_cpus);
out:
* Current buffer might not have all the events allocated
* yet, we need to free only allocated ones ...
*/
- list_del(&oe->buffer->list);
- ordered_events_buffer__free(oe->buffer, oe->buffer_idx, oe);
+ if (oe->buffer) {
+ list_del(&oe->buffer->list);
+ ordered_events_buffer__free(oe->buffer, oe->buffer_idx, oe);
+ }
/* ... and continue with the rest */
list_for_each_entry_safe(buffer, tmp, &oe->to_free, list) {
vars[var] = sub("-mcet", "", vars[var])
if not clang_has_option("-fcf-protection"):
vars[var] = sub("-fcf-protection", "", vars[var])
+ if not clang_has_option("-fstack-clash-protection"):
+ vars[var] = sub("-fstack-clash-protection", "", vars[var])
from distutils.core import setup, Extension
exit $ksft_skip
fi
+ present_cpus=`cat $SYSFS/devices/system/cpu/present`
+ present_max=${present_cpus##*-}
+ echo "present_cpus = $present_cpus present_max = $present_max"
+
echo -e "\t Cpus in online state: $online_cpus"
offline_cpus=`cat $SYSFS/devices/system/cpu/offline`
online_max=0
offline_cpus=0
offline_max=0
+present_cpus=0
+present_max=0
while getopts e:ahp: opt; do
case $opt in
online_cpu_expect_success $online_max
if [[ $offline_cpus -gt 0 ]]; then
- echo -e "\t offline to online to offline: cpu $offline_max"
- online_cpu_expect_success $offline_max
- offline_cpu_expect_success $offline_max
+ echo -e "\t offline to online to offline: cpu $present_max"
+ online_cpu_expect_success $present_max
+ offline_cpu_expect_success $present_max
+ online_cpu $present_max
fi
exit 0
else
# SPDX-License-Identifier: GPL-2.0
TEST_PROGS := ir_loopback.sh
TEST_GEN_PROGS_EXTENDED := ir_loopback
+APIDIR := ../../../include/uapi
+CFLAGS += -Wall -O2 -I$(APIDIR)
include ../lib.mk
KSFT_KHDR_INSTALL := 1
include ../lib.mk
-$(OUTPUT)/reuseport_bpf_numa: LDFLAGS += -lnuma
+$(OUTPUT)/reuseport_bpf_numa: LDLIBS += -lnuma
$(OUTPUT)/tcp_mmap: LDFLAGS += -lpthread
$(OUTPUT)/tcp_inq: LDFLAGS += -lpthread
SPI1=0x1
SPI2=0x2
+do_esp_policy() {
+ local ns=$1
+ local me=$2
+ local remote=$3
+ local lnet=$4
+ local rnet=$5
+
+ # to encrypt packets as they go out (includes forwarded packets that need encapsulation)
+ ip -net $ns xfrm policy add src $lnet dst $rnet dir out tmpl src $me dst $remote proto esp mode tunnel priority 100 action allow
+ # to fwd decrypted packets after esp processing:
+ ip -net $ns xfrm policy add src $rnet dst $lnet dir fwd tmpl src $remote dst $me proto esp mode tunnel priority 100 action allow
+}
+
do_esp() {
local ns=$1
local me=$2
ip -net $ns xfrm state add src $remote dst $me proto esp spi $spi_in enc aes $KEY_AES auth sha1 $KEY_SHA mode tunnel sel src $rnet dst $lnet
ip -net $ns xfrm state add src $me dst $remote proto esp spi $spi_out enc aes $KEY_AES auth sha1 $KEY_SHA mode tunnel sel src $lnet dst $rnet
- # to encrypt packets as they go out (includes forwarded packets that need encapsulation)
- ip -net $ns xfrm policy add src $lnet dst $rnet dir out tmpl src $me dst $remote proto esp mode tunnel priority 100 action allow
- # to fwd decrypted packets after esp processing:
- ip -net $ns xfrm policy add src $rnet dst $lnet dir fwd tmpl src $remote dst $me proto esp mode tunnel priority 100 action allow
+ do_esp_policy $ns $me $remote $lnet $rnet
+}
+
+# add policies with different netmasks, to make sure kernel carries
+# the policies contained within new netmask over when search tree is
+# re-built.
+# peer netns that are supposed to be encapsulated via esp have addresses
+# in the 10.0.1.0/24 and 10.0.2.0/24 subnets, respectively.
+#
+# Adding a policy for '10.0.1.0/23' will make it necessary to
+# alter the prefix of 10.0.1.0 subnet.
+# In case new prefix overlaps with existing node, the node and all
+# policies it carries need to be merged with the existing one(s).
+#
+# Do that here.
+do_overlap()
+{
+ local ns=$1
+
+ # adds new nodes to tree (neither network exists yet in policy database).
+ ip -net $ns xfrm policy add src 10.1.0.0/24 dst 10.0.0.0/24 dir fwd priority 200 action block
+
+ # adds a new node in the 10.0.0.0/24 tree (dst node exists).
+ ip -net $ns xfrm policy add src 10.2.0.0/24 dst 10.0.0.0/24 dir fwd priority 200 action block
+
+ # adds a 10.2.0.0/23 node, but for different dst.
+ ip -net $ns xfrm policy add src 10.2.0.0/23 dst 10.0.1.0/24 dir fwd priority 200 action block
+
+ # dst now overlaps with the 10.0.1.0/24 ESP policy in fwd.
+ # kernel must 'promote' existing one (10.0.0.0/24) to 10.0.0.0/23.
+ # But 10.0.0.0/23 also includes existing 10.0.1.0/24, so that node
+ # also has to be merged too, including source-sorted subtrees.
+ # old:
+ # 10.0.0.0/24 (node 1 in dst tree of the bin)
+ # 10.1.0.0/24 (node in src tree of dst node 1)
+ # 10.2.0.0/24 (node in src tree of dst node 1)
+ # 10.0.1.0/24 (node 2 in dst tree of the bin)
+ # 10.0.2.0/24 (node in src tree of dst node 2)
+ # 10.2.0.0/24 (node in src tree of dst node 2)
+ #
+ # The next 'policy add' adds dst '10.0.0.0/23', which means
+ # that dst node 1 and dst node 2 have to be merged including
+ # the sub-tree. As no duplicates are allowed, policies in
+ # the two '10.0.2.0/24' are also merged.
+ #
+ # after the 'add', internal search tree should look like this:
+ # 10.0.0.0/23 (node in dst tree of bin)
+ # 10.0.2.0/24 (node in src tree of dst node)
+ # 10.1.0.0/24 (node in src tree of dst node)
+ # 10.2.0.0/24 (node in src tree of dst node)
+ #
+ # 10.0.0.0/24 and 10.0.1.0/24 nodes have been merged as 10.0.0.0/23.
+ ip -net $ns xfrm policy add src 10.1.0.0/24 dst 10.0.0.0/23 dir fwd priority 200 action block
}
do_esp_policy_get_check() {
return $lret
}
+check_exceptions()
+{
+ logpostfix="$1"
+ local lret=0
+
+ # ping to .254 should be excluded from the tunnel (exception is in place).
+ check_xfrm 0 254
+ if [ $? -ne 0 ]; then
+ echo "FAIL: expected ping to .254 to fail ($logpostfix)"
+ lret=1
+ else
+ echo "PASS: ping to .254 bypassed ipsec tunnel ($logpostfix)"
+ fi
+
+ # ping to .253 should use use ipsec due to direct policy exception.
+ check_xfrm 1 253
+ if [ $? -ne 0 ]; then
+ echo "FAIL: expected ping to .253 to use ipsec tunnel ($logpostfix)"
+ lret=1
+ else
+ echo "PASS: direct policy matches ($logpostfix)"
+ fi
+
+ # ping to .2 should use ipsec.
+ check_xfrm 1 2
+ if [ $? -ne 0 ]; then
+ echo "FAIL: expected ping to .2 to use ipsec tunnel ($logpostfix)"
+ lret=1
+ else
+ echo "PASS: policy matches ($logpostfix)"
+ fi
+
+ return $lret
+}
+
#check for needed privileges
if [ "$(id -u)" -ne 0 ];then
echo "SKIP: Need root privileges"
do_exception ns3 dead:3::1 dead:3::10 dead:2::fd dead:2:f0::/96
do_exception ns4 dead:3::10 dead:3::1 dead:1::fd dead:1:f0::/96
-# ping to .254 should now be excluded from the tunnel
-check_xfrm 0 254
+check_exceptions "exceptions"
if [ $? -ne 0 ]; then
- echo "FAIL: expected ping to .254 to fail"
ret=1
-else
- echo "PASS: ping to .254 bypassed ipsec tunnel"
fi
-# ping to .253 should use use ipsec due to direct policy exception.
-check_xfrm 1 253
-if [ $? -ne 0 ]; then
- echo "FAIL: expected ping to .253 to use ipsec tunnel"
- ret=1
-else
- echo "PASS: direct policy matches"
-fi
+# insert block policies with adjacent/overlapping netmasks
+do_overlap ns3
-# ping to .2 should use ipsec.
-check_xfrm 1 2
+check_exceptions "exceptions and block policies"
if [ $? -ne 0 ]; then
- echo "FAIL: expected ping to .2 to use ipsec tunnel"
ret=1
-else
- echo "PASS: policy matches"
fi
+for n in ns3 ns4;do
+ ip -net $n xfrm policy set hthresh4 28 24 hthresh6 126 125
+ sleep $((RANDOM%5))
+done
+
+check_exceptions "exceptions and block policies after hresh changes"
+
+# full flush of policy db, check everything gets freed incl. internal meta data
+ip -net ns3 xfrm policy flush
+
+do_esp_policy ns3 10.0.3.1 10.0.3.10 10.0.1.0/24 10.0.2.0/24
+do_exception ns3 10.0.3.1 10.0.3.10 10.0.2.253 10.0.2.240/28
+
+# move inexact policies to hash table
+ip -net ns3 xfrm policy set hthresh4 16 16
+
+sleep $((RANDOM%5))
+check_exceptions "exceptions and block policies after hthresh change in ns3"
+
+# restore original hthresh settings -- move policies back to tables
+for n in ns3 ns4;do
+ ip -net $n xfrm policy set hthresh4 32 32 hthresh6 128 128
+ sleep $((RANDOM%5))
+done
+check_exceptions "exceptions and block policies after hresh change to normal"
+
for i in 1 2 3 4;do ip netns del ns$i;done
exit $ret
/proc-uptime-002
/read
/self
+/setns-dcache
/thread-self
TEST_GEN_PROGS += proc-uptime-002
TEST_GEN_PROGS += read
TEST_GEN_PROGS += self
+TEST_GEN_PROGS += setns-dcache
TEST_GEN_PROGS += thread-self
include ../lib.mk
--- /dev/null
+/*
+ * Copyright © 2019 Alexey Dobriyan <adobriyan@gmail.com>
+ *
+ * Permission to use, copy, modify, and distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+ * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
+ * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ */
+/*
+ * Test that setns(CLONE_NEWNET) points to new /proc/net content even
+ * if old one is in dcache.
+ *
+ * FIXME /proc/net/unix is under CONFIG_UNIX which can be disabled.
+ */
+#undef NDEBUG
+#include <assert.h>
+#include <errno.h>
+#include <sched.h>
+#include <signal.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+#include <sys/socket.h>
+
+static pid_t pid = -1;
+
+static void f(void)
+{
+ if (pid > 0) {
+ kill(pid, SIGTERM);
+ }
+}
+
+int main(void)
+{
+ int fd[2];
+ char _ = 0;
+ int nsfd;
+
+ atexit(f);
+
+ /* Check for priviledges and syscall availability straight away. */
+ if (unshare(CLONE_NEWNET) == -1) {
+ if (errno == ENOSYS || errno == EPERM) {
+ return 4;
+ }
+ return 1;
+ }
+ /* Distinguisher between two otherwise empty net namespaces. */
+ if (socket(AF_UNIX, SOCK_STREAM, 0) == -1) {
+ return 1;
+ }
+
+ if (pipe(fd) == -1) {
+ return 1;
+ }
+
+ pid = fork();
+ if (pid == -1) {
+ return 1;
+ }
+
+ if (pid == 0) {
+ if (unshare(CLONE_NEWNET) == -1) {
+ return 1;
+ }
+
+ if (write(fd[1], &_, 1) != 1) {
+ return 1;
+ }
+
+ pause();
+
+ return 0;
+ }
+
+ if (read(fd[0], &_, 1) != 1) {
+ return 1;
+ }
+
+ {
+ char buf[64];
+ snprintf(buf, sizeof(buf), "/proc/%u/ns/net", pid);
+ nsfd = open(buf, O_RDONLY);
+ if (nsfd == -1) {
+ return 1;
+ }
+ }
+
+ /* Reliably pin dentry into dcache. */
+ (void)open("/proc/net/unix", O_RDONLY);
+
+ if (setns(nsfd, CLONE_NEWNET) == -1) {
+ return 1;
+ }
+
+ kill(pid, SIGTERM);
+ pid = 0;
+
+ {
+ char buf[4096];
+ ssize_t rv;
+ int fd;
+
+ fd = open("/proc/net/unix", O_RDONLY);
+ if (fd == -1) {
+ return 1;
+ }
+
+#define S "Num RefCount Protocol Flags Type St Inode Path\n"
+ rv = read(fd, buf, sizeof(buf));
+
+ assert(rv == strlen(S));
+ assert(memcmp(buf, S, strlen(S)) == 0);
+ }
+
+ return 0;
+}
#ifdef SYSCALL_NUM_RET_SHARE_REG
# define EXPECT_SYSCALL_RETURN(val, action) EXPECT_EQ(-1, action)
#else
-# define EXPECT_SYSCALL_RETURN(val, action) EXPECT_EQ(val, action)
+# define EXPECT_SYSCALL_RETURN(val, action) \
+ do { \
+ errno = 0; \
+ if (val < 0) { \
+ EXPECT_EQ(-1, action); \
+ EXPECT_EQ(-(val), errno); \
+ } else { \
+ EXPECT_EQ(val, action); \
+ } \
+ } while (0)
#endif
/* Use PTRACE_GETREGS and PTRACE_SETREGS when available. This is useful for
/* Architecture-specific syscall changing routine. */
void change_syscall(struct __test_metadata *_metadata,
- pid_t tracee, int syscall)
+ pid_t tracee, int syscall, int result)
{
int ret;
ARCH_REGS regs;
#ifdef SYSCALL_NUM_RET_SHARE_REG
TH_LOG("Can't modify syscall return on this architecture");
#else
- regs.SYSCALL_RET = EPERM;
+ regs.SYSCALL_RET = result;
#endif
#ifdef HAVE_GETREGS
case 0x1002:
/* change getpid to getppid. */
EXPECT_EQ(__NR_getpid, get_syscall(_metadata, tracee));
- change_syscall(_metadata, tracee, __NR_getppid);
+ change_syscall(_metadata, tracee, __NR_getppid, 0);
break;
case 0x1003:
- /* skip gettid. */
+ /* skip gettid with valid return code. */
EXPECT_EQ(__NR_gettid, get_syscall(_metadata, tracee));
- change_syscall(_metadata, tracee, -1);
+ change_syscall(_metadata, tracee, -1, 45000);
break;
case 0x1004:
+ /* skip openat with error. */
+ EXPECT_EQ(__NR_openat, get_syscall(_metadata, tracee));
+ change_syscall(_metadata, tracee, -1, -ESRCH);
+ break;
+ case 0x1005:
/* do nothing (allow getppid) */
EXPECT_EQ(__NR_getppid, get_syscall(_metadata, tracee));
break;
nr = get_syscall(_metadata, tracee);
if (nr == __NR_getpid)
- change_syscall(_metadata, tracee, __NR_getppid);
+ change_syscall(_metadata, tracee, __NR_getppid, 0);
+ if (nr == __NR_gettid)
+ change_syscall(_metadata, tracee, -1, 45000);
if (nr == __NR_openat)
- change_syscall(_metadata, tracee, -1);
+ change_syscall(_metadata, tracee, -1, -ESRCH);
}
FIXTURE_DATA(TRACE_syscall) {
BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_TRACE | 0x1002),
BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_gettid, 0, 1),
BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_TRACE | 0x1003),
- BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_getppid, 0, 1),
+ BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_openat, 0, 1),
BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_TRACE | 0x1004),
+ BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_getppid, 0, 1),
+ BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_TRACE | 0x1005),
BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),
};
EXPECT_NE(self->mypid, syscall(__NR_getpid));
}
-TEST_F(TRACE_syscall, ptrace_syscall_dropped)
+TEST_F(TRACE_syscall, ptrace_syscall_errno)
+{
+ /* Swap SECCOMP_RET_TRACE tracer for PTRACE_SYSCALL tracer. */
+ teardown_trace_fixture(_metadata, self->tracer);
+ self->tracer = setup_trace_fixture(_metadata, tracer_ptrace, NULL,
+ true);
+
+ /* Tracer should skip the open syscall, resulting in ESRCH. */
+ EXPECT_SYSCALL_RETURN(-ESRCH, syscall(__NR_openat));
+}
+
+TEST_F(TRACE_syscall, ptrace_syscall_faked)
{
/* Swap SECCOMP_RET_TRACE tracer for PTRACE_SYSCALL tracer. */
teardown_trace_fixture(_metadata, self->tracer);
self->tracer = setup_trace_fixture(_metadata, tracer_ptrace, NULL,
true);
- /* Tracer should skip the open syscall, resulting in EPERM. */
- EXPECT_SYSCALL_RETURN(EPERM, syscall(__NR_openat));
+ /* Tracer should skip the gettid syscall, resulting fake pid. */
+ EXPECT_SYSCALL_RETURN(45000, syscall(__NR_gettid));
}
TEST_F(TRACE_syscall, syscall_allowed)
EXPECT_NE(self->mypid, syscall(__NR_getpid));
}
-TEST_F(TRACE_syscall, syscall_dropped)
+TEST_F(TRACE_syscall, syscall_errno)
+{
+ long ret;
+
+ ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
+ ASSERT_EQ(0, ret);
+
+ ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->prog, 0, 0);
+ ASSERT_EQ(0, ret);
+
+ /* openat has been skipped and an errno return. */
+ EXPECT_SYSCALL_RETURN(-ESRCH, syscall(__NR_openat));
+}
+
+TEST_F(TRACE_syscall, syscall_faked)
{
long ret;
ASSERT_EQ(0, ret);
/* gettid has been skipped and an altered return value stored. */
- EXPECT_SYSCALL_RETURN(EPERM, syscall(__NR_gettid));
- EXPECT_NE(self->mytid, syscall(__NR_gettid));
+ EXPECT_SYSCALL_RETURN(45000, syscall(__NR_gettid));
}
TEST_F(TRACE_syscall, skip_after_RET_TRACE)
# SPDX-License-Identifier: GPL-2.0
CFLAGS += -O3 -Wl,-no-as-needed -Wall
-LDFLAGS += -lrt -lpthread -lm
+LDLIBS += -lrt -lpthread -lm
# these are all "safe" tests that don't modify
# system time or require escalated privileges
OSDN Git Service
