config ARCH_TASK_STRUCT_ALLOCATOR
bool
-# Select if arch has its private alloc_thread_info() function
-config ARCH_THREAD_INFO_ALLOCATOR
+# Select if arch has its private alloc_thread_stack() function
+config ARCH_THREAD_STACK_ALLOCATOR
bool
# Select if arch wants to size task_struct dynamically via arch_task_struct_size:
Image: vmlinux
$(Q)$(MAKE) $(build)=$(boot) $(boot)/$@
-Image.%: vmlinux
+Image.%: Image
$(Q)$(MAKE) $(build)=$(boot) $(boot)/$@
zinstall install:
cpu_park_loop();
}
+/*
+ * If a secondary CPU enters the kernel but fails to come online,
+ * (e.g. due to mismatched features), and cannot exit the kernel,
+ * we increment cpus_stuck_in_kernel and leave the CPU in a
+ * quiesecent loop within the kernel text. The memory containing
+ * this loop must not be re-used for anything else as the 'stuck'
+ * core is executing it.
+ *
+ * This function is used to inhibit features like kexec and hibernate.
+ */
+bool cpus_are_stuck_in_kernel(void);
+
#endif /* ifndef __ASSEMBLY__ */
#endif /* ifndef __ASM_SMP_H */
#include <asm/pgtable.h>
#include <asm/pgtable-hwdef.h>
#include <asm/sections.h>
+#include <asm/smp.h>
#include <asm/suspend.h>
#include <asm/virt.h>
unsigned long flags;
struct sleep_stack_data state;
+ if (cpus_are_stuck_in_kernel()) {
+ pr_err("Can't hibernate: no mechanism to offline secondary CPUs.\n");
+ return -EBUSY;
+ }
+
local_dbg_save(flags);
if (__cpu_suspend_enter(&state)) {
{
return -EINVAL;
}
+
+static bool have_cpu_die(void)
+{
+#ifdef CONFIG_HOTPLUG_CPU
+ int any_cpu = raw_smp_processor_id();
+
+ if (cpu_ops[any_cpu]->cpu_die)
+ return true;
+#endif
+ return false;
+}
+
+bool cpus_are_stuck_in_kernel(void)
+{
+ bool smp_spin_tables = (num_possible_cpus() > 1 && !have_cpu_die());
+
+ return !!cpus_stuck_in_kernel || smp_spin_tables;
+}
&asid_generation);
flush_context(cpu);
- /* We have at least 1 ASID per CPU, so this will always succeed */
+ /* We have more ASIDs than CPUs, so this will always succeed */
asid = find_next_zero_bit(asid_map, NUM_USER_ASIDS, 1);
set_asid:
static int asids_init(void)
{
asid_bits = get_cpu_asid_bits();
- /* If we end up with more CPUs than ASIDs, expect things to crash */
- WARN_ON(NUM_USER_ASIDS < num_possible_cpus());
+ /*
+ * Expect allocation after rollover to fail if we don't have at least
+ * one more ASID than CPUs. ASID #0 is reserved for init_mm.
+ */
+ WARN_ON(NUM_USER_ASIDS - 1 <= num_possible_cpus());
atomic64_set(&asid_generation, ASID_FIRST_VERSION);
asid_map = kzalloc(BITS_TO_LONGS(NUM_USER_ASIDS) * sizeof(*asid_map),
GFP_KERNEL);
{
struct page *page = pte_page(pte);
- /* no flushing needed for anonymous pages */
- if (!page_mapping(page))
- return;
-
if (!test_and_set_bit(PG_dcache_clean, &page->flags))
sync_icache_aliases(page_address(page),
PAGE_SIZE << compound_order(page));
select GENERIC_SMP_IDLE_THREAD
select ARCH_INIT_TASK
select ARCH_TASK_STRUCT_ALLOCATOR
- select ARCH_THREAD_INFO_ALLOCATOR
+ select ARCH_THREAD_STACK_ALLOCATOR
select ARCH_CLOCKSOURCE_DATA
select GENERIC_TIME_VSYSCALL_OLD
select SYSCTL_ARCH_UNALIGN_NO_WARN
#ifndef ASM_OFFSETS_C
/* how to get the thread information struct from C */
#define current_thread_info() ((struct thread_info *) ((char *) current + IA64_TASK_SIZE))
-#define alloc_thread_info_node(tsk, node) \
- ((struct thread_info *) ((char *) (tsk) + IA64_TASK_SIZE))
+#define alloc_thread_stack_node(tsk, node) \
+ ((unsigned long *) ((char *) (tsk) + IA64_TASK_SIZE))
#define task_thread_info(tsk) ((struct thread_info *) ((char *) (tsk) + IA64_TASK_SIZE))
#else
#define current_thread_info() ((struct thread_info *) 0)
-#define alloc_thread_info_node(tsk, node) ((struct thread_info *) 0)
+#define alloc_thread_stack_node(tsk, node) ((unsigned long *) 0)
#define task_thread_info(tsk) ((struct thread_info *) 0)
#endif
-#define free_thread_info(ti) /* nothing */
+#define free_thread_stack(ti) /* nothing */
#define task_stack_page(tsk) ((void *)(tsk))
#define __HAVE_THREAD_FUNCTIONS
* handled. This is done by having a special ".data..init_task" section...
*/
#define init_thread_info init_task_mem.s.thread_info
+#define init_stack init_task_mem.stack
union {
struct {
}
#ifndef CONFIG_KGDB
-void arch_release_thread_info(struct thread_info *ti);
+void arch_release_thread_stack(unsigned long *stack);
#endif
#define get_thread_info(ti) get_task_struct((ti)->task)
#define put_thread_info(ti) put_task_struct((ti)->task)
* single-step state is cleared. At this point the breakpoints should have
* been removed by __switch_to().
*/
-void arch_release_thread_info(struct thread_info *ti)
+void arch_release_thread_stack(unsigned long *stack)
{
+ struct thread_info *ti = (void *)stack;
if (kgdb_sstep_thread == ti) {
kgdb_sstep_thread = NULL;
#ifndef __ASSEMBLY__
-void arch_release_thread_info(struct thread_info *info);
+void arch_release_thread_stack(unsigned long *stack);
/* How to get the thread information struct from C. */
register unsigned long stack_pointer __asm__("sp");
/*
* Release a thread_info structure
*/
-void arch_release_thread_info(struct thread_info *info)
+void arch_release_thread_stack(unsigned long *stack)
{
+ struct thread_info *info = (void *)stack;
struct single_step_state *step_state = info->step_state;
if (step_state) {
#define RELATIVECALL_OPCODE 0xe8
#define RELATIVE_ADDR_SIZE 4
#define MAX_STACK_SIZE 64
-#define MIN_STACK_SIZE(ADDR) \
- (((MAX_STACK_SIZE) < (((unsigned long)current_thread_info()) + \
- THREAD_SIZE - (unsigned long)(ADDR))) \
- ? (MAX_STACK_SIZE) \
- : (((unsigned long)current_thread_info()) + \
- THREAD_SIZE - (unsigned long)(ADDR)))
+#define CUR_STACK_SIZE(ADDR) \
+ (current_top_of_stack() - (unsigned long)(ADDR))
+#define MIN_STACK_SIZE(ADDR) \
+ (MAX_STACK_SIZE < CUR_STACK_SIZE(ADDR) ? \
+ MAX_STACK_SIZE : CUR_STACK_SIZE(ADDR))
#define flush_insn_slot(p) do { } while (0)
static inline int valid_stack_ptr(struct task_struct *task,
void *p, unsigned int size, void *end)
{
- void *t = task_thread_info(task);
+ void *t = task_stack_page(task);
if (end) {
if (p < end && p >= (end-THREAD_SIZE))
return 1;
void do_softirq_own_stack(void)
{
- struct thread_info *curstk;
struct irq_stack *irqstk;
u32 *isp, *prev_esp;
- curstk = current_stack();
irqstk = __this_cpu_read(softirq_stack);
/* build the stack frame on the softirq stack */
/* NOTE: The loop is more greedy than the cleanup_highmap variant.
* We include the PMD passed in on _both_ boundaries. */
- for (; vaddr <= vaddr_end && (pmd < (level2_kernel_pgt + PAGE_SIZE));
+ for (; vaddr <= vaddr_end && (pmd < (level2_kernel_pgt + PTRS_PER_PMD));
pmd++, vaddr += PMD_SIZE) {
if (pmd_none(*pmd))
continue;
#endif
}
-#ifdef CONFIG_X86_32
-static pte_t __init mask_rw_pte(pte_t *ptep, pte_t pte)
-{
- /* If there's an existing pte, then don't allow _PAGE_RW to be set */
- if (pte_val_ma(*ptep) & _PAGE_PRESENT)
- pte = __pte_ma(((pte_val_ma(*ptep) & _PAGE_RW) | ~_PAGE_RW) &
- pte_val_ma(pte));
-
- return pte;
-}
-#else /* CONFIG_X86_64 */
-static pte_t __init mask_rw_pte(pte_t *ptep, pte_t pte)
-{
- unsigned long pfn;
-
- if (xen_feature(XENFEAT_writable_page_tables) ||
- xen_feature(XENFEAT_auto_translated_physmap) ||
- xen_start_info->mfn_list >= __START_KERNEL_map)
- return pte;
-
- /*
- * Pages belonging to the initial p2m list mapped outside the default
- * address range must be mapped read-only. This region contains the
- * page tables for mapping the p2m list, too, and page tables MUST be
- * mapped read-only.
- */
- pfn = pte_pfn(pte);
- if (pfn >= xen_start_info->first_p2m_pfn &&
- pfn < xen_start_info->first_p2m_pfn + xen_start_info->nr_p2m_frames)
- pte = __pte_ma(pte_val_ma(pte) & ~_PAGE_RW);
-
- return pte;
-}
-#endif /* CONFIG_X86_64 */
-
/*
* Init-time set_pte while constructing initial pagetables, which
* doesn't allow RO page table pages to be remapped RW.
* so always write the PTE directly and rely on Xen trapping and
* emulating any updates as necessary.
*/
-static void __init xen_set_pte_init(pte_t *ptep, pte_t pte)
+__visible pte_t xen_make_pte_init(pteval_t pte)
{
- if (pte_mfn(pte) != INVALID_P2M_ENTRY)
- pte = mask_rw_pte(ptep, pte);
- else
- pte = __pte_ma(0);
+#ifdef CONFIG_X86_64
+ unsigned long pfn;
+
+ /*
+ * Pages belonging to the initial p2m list mapped outside the default
+ * address range must be mapped read-only. This region contains the
+ * page tables for mapping the p2m list, too, and page tables MUST be
+ * mapped read-only.
+ */
+ pfn = (pte & PTE_PFN_MASK) >> PAGE_SHIFT;
+ if (xen_start_info->mfn_list < __START_KERNEL_map &&
+ pfn >= xen_start_info->first_p2m_pfn &&
+ pfn < xen_start_info->first_p2m_pfn + xen_start_info->nr_p2m_frames)
+ pte &= ~_PAGE_RW;
+#endif
+ pte = pte_pfn_to_mfn(pte);
+ return native_make_pte(pte);
+}
+PV_CALLEE_SAVE_REGS_THUNK(xen_make_pte_init);
+static void __init xen_set_pte_init(pte_t *ptep, pte_t pte)
+{
+#ifdef CONFIG_X86_32
+ /* If there's an existing pte, then don't allow _PAGE_RW to be set */
+ if (pte_mfn(pte) != INVALID_P2M_ENTRY
+ && pte_val_ma(*ptep) & _PAGE_PRESENT)
+ pte = __pte_ma(((pte_val_ma(*ptep) & _PAGE_RW) | ~_PAGE_RW) &
+ pte_val_ma(pte));
+#endif
native_set_pte(ptep, pte);
}
pv_mmu_ops.alloc_pud = xen_alloc_pud;
pv_mmu_ops.release_pud = xen_release_pud;
#endif
+ pv_mmu_ops.make_pte = PV_CALLEE_SAVE(xen_make_pte);
#ifdef CONFIG_X86_64
pv_mmu_ops.write_cr3 = &xen_write_cr3;
.pte_val = PV_CALLEE_SAVE(xen_pte_val),
.pgd_val = PV_CALLEE_SAVE(xen_pgd_val),
- .make_pte = PV_CALLEE_SAVE(xen_make_pte),
+ .make_pte = PV_CALLEE_SAVE(xen_make_pte_init),
.make_pgd = PV_CALLEE_SAVE(xen_make_pgd),
#ifdef CONFIG_X86_PAE
/* Add the table to the namespace */
+ acpi_ex_exit_interpreter();
status = acpi_ns_load_table(table_index, parent_node);
+ acpi_ex_enter_interpreter();
if (ACPI_FAILURE(status)) {
acpi_ut_remove_reference(obj_desc);
*ddb_handle = NULL;
#include "acparser.h"
#include "acdispat.h"
#include "actables.h"
+#include "acinterp.h"
#define _COMPONENT ACPI_NAMESPACE
ACPI_MODULE_NAME("nsparse")
ACPI_FUNCTION_TRACE(ns_parse_table);
+ acpi_ex_enter_interpreter();
+
/*
* AML Parse, pass 1
*
status = acpi_ns_one_complete_parse(ACPI_IMODE_LOAD_PASS1,
table_index, start_node);
if (ACPI_FAILURE(status)) {
- return_ACPI_STATUS(status);
+ goto error_exit;
}
/*
status = acpi_ns_one_complete_parse(ACPI_IMODE_LOAD_PASS2,
table_index, start_node);
if (ACPI_FAILURE(status)) {
- return_ACPI_STATUS(status);
+ goto error_exit;
}
+error_exit:
+ acpi_ex_exit_interpreter();
return_ACPI_STATUS(status);
}
doorbell.space_id = reg_resource->space_id;
doorbell.bit_width = reg_resource->bit_width;
doorbell.bit_offset = reg_resource->bit_offset;
- doorbell.access_width = 64;
+ doorbell.access_width = 4;
doorbell.address = reg_resource->address;
pr_debug("probe: doorbell: space_id is %d, bit_width is %d, "
devfreq_notify_transition(devfreq, &freqs, DEVFREQ_PRECHANGE);
err = devfreq->profile->target(devfreq->dev.parent, &freq, flags);
- if (err)
+ if (err) {
+ freqs.new = cur_freq;
+ devfreq_notify_transition(devfreq, &freqs, DEVFREQ_POSTCHANGE);
return err;
+ }
freqs.new = freq;
devfreq_notify_transition(devfreq, &freqs, DEVFREQ_POSTCHANGE);
devfreq->profile = profile;
strncpy(devfreq->governor_name, governor_name, DEVFREQ_NAME_LEN);
devfreq->previous_freq = profile->initial_freq;
+ devfreq->last_status.current_frequency = profile->initial_freq;
devfreq->data = data;
devfreq->nb.notifier_call = devfreq_notifier_call;
mutex_lock(&devfreq->lock);
}
- devfreq->trans_table = devm_kzalloc(dev, sizeof(unsigned int) *
- devfreq->profile->max_state *
- devfreq->profile->max_state,
- GFP_KERNEL);
- devfreq->time_in_state = devm_kzalloc(dev, sizeof(unsigned long) *
- devfreq->profile->max_state,
- GFP_KERNEL);
- devfreq->last_stat_updated = jiffies;
-
dev_set_name(&devfreq->dev, "%s", dev_name(dev));
err = device_register(&devfreq->dev);
if (err) {
- put_device(&devfreq->dev);
mutex_unlock(&devfreq->lock);
goto err_out;
}
+ devfreq->trans_table = devm_kzalloc(&devfreq->dev, sizeof(unsigned int) *
+ devfreq->profile->max_state *
+ devfreq->profile->max_state,
+ GFP_KERNEL);
+ devfreq->time_in_state = devm_kzalloc(&devfreq->dev, sizeof(unsigned long) *
+ devfreq->profile->max_state,
+ GFP_KERNEL);
+ devfreq->last_stat_updated = jiffies;
+
srcu_init_notifier_head(&devfreq->transition_notifier_list);
mutex_unlock(&devfreq->lock);
err_init:
list_del(&devfreq->node);
device_unregister(&devfreq->dev);
- kfree(devfreq);
err_out:
return ERR_PTR(err);
}
return -EINVAL;
device_unregister(&devfreq->dev);
- put_device(&devfreq->dev);
return 0;
}
/* Maps the memory mapped IO to control nocp register */
res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
- if (IS_ERR(res))
- return PTR_ERR(res);
-
base = devm_ioremap_resource(dev, res);
if (IS_ERR(base))
return PTR_ERR(base);
goto inval;
} else if (uref->usage_index >= field->report_count)
goto inval;
-
- else if ((cmd == HIDIOCGUSAGES || cmd == HIDIOCSUSAGES) &&
- (uref_multi->num_values > HID_MAX_MULTI_USAGES ||
- uref->usage_index + uref_multi->num_values > field->report_count))
- goto inval;
}
+ if ((cmd == HIDIOCGUSAGES || cmd == HIDIOCSUSAGES) &&
+ (uref_multi->num_values > HID_MAX_MULTI_USAGES ||
+ uref->usage_index + uref_multi->num_values > field->report_count))
+ goto inval;
+
switch (cmd) {
case HIDIOCGUSAGE:
uref->value = field->value[uref->usage_index];
/*
* Read the fan type.
*/
-static int i8k_get_fan_type(int fan)
+static int _i8k_get_fan_type(int fan)
{
struct smm_regs regs = { .eax = I8K_SMM_GET_FAN_TYPE, };
return i8k_smm(®s) ? : regs.eax & 0xff;
}
+static int i8k_get_fan_type(int fan)
+{
+ /* I8K_SMM_GET_FAN_TYPE SMM call is expensive, so cache values */
+ static int types[2] = { INT_MIN, INT_MIN };
+
+ if (types[fan] == INT_MIN)
+ types[fan] = _i8k_get_fan_type(fan);
+
+ return types[fan];
+}
+
/*
* Read the fan nominal rpm for specific fan speed.
*/
if (err >= 0)
i8k_hwmon_flags |= I8K_HWMON_HAVE_TEMP4;
- /* First fan attributes, if fan type is OK */
- err = i8k_get_fan_type(0);
+ /* First fan attributes, if fan status or type is OK */
+ err = i8k_get_fan_status(0);
+ if (err < 0)
+ err = i8k_get_fan_type(0);
if (err >= 0)
i8k_hwmon_flags |= I8K_HWMON_HAVE_FAN1;
- /* Second fan attributes, if fan type is OK */
- err = i8k_get_fan_type(1);
+ /* Second fan attributes, if fan status or type is OK */
+ err = i8k_get_fan_status(1);
+ if (err < 0)
+ err = i8k_get_fan_type(1);
if (err >= 0)
i8k_hwmon_flags |= I8K_HWMON_HAVE_FAN2;
for (ix = 0; ix < table->sz; ix++)
if (table->data_vec[ix].attr.ndev == ndev)
- if (!del_gid(ib_dev, port, table, ix, false))
+ if (!del_gid(ib_dev, port, table, ix,
+ !!(table->data_vec[ix].props &
+ GID_TABLE_ENTRY_DEFAULT)))
deleted = true;
write_unlock_irq(&table->rwlock);
complete(&id_priv->comp);
}
-static int cma_disable_callback(struct rdma_id_private *id_priv,
- enum rdma_cm_state state)
-{
- mutex_lock(&id_priv->handler_mutex);
- if (id_priv->state != state) {
- mutex_unlock(&id_priv->handler_mutex);
- return -EINVAL;
- }
- return 0;
-}
-
struct rdma_cm_id *rdma_create_id(struct net *net,
rdma_cm_event_handler event_handler,
void *context, enum rdma_port_space ps,
struct rdma_cm_event event;
int ret = 0;
+ mutex_lock(&id_priv->handler_mutex);
if ((ib_event->event != IB_CM_TIMEWAIT_EXIT &&
- cma_disable_callback(id_priv, RDMA_CM_CONNECT)) ||
+ id_priv->state != RDMA_CM_CONNECT) ||
(ib_event->event == IB_CM_TIMEWAIT_EXIT &&
- cma_disable_callback(id_priv, RDMA_CM_DISCONNECT)))
- return 0;
+ id_priv->state != RDMA_CM_DISCONNECT))
+ goto out;
memset(&event, 0, sizeof event);
switch (ib_event->event) {
static int cma_req_handler(struct ib_cm_id *cm_id, struct ib_cm_event *ib_event)
{
- struct rdma_id_private *listen_id, *conn_id;
+ struct rdma_id_private *listen_id, *conn_id = NULL;
struct rdma_cm_event event;
struct net_device *net_dev;
int offset, ret;
goto net_dev_put;
}
- if (cma_disable_callback(listen_id, RDMA_CM_LISTEN)) {
+ mutex_lock(&listen_id->handler_mutex);
+ if (listen_id->state != RDMA_CM_LISTEN) {
ret = -ECONNABORTED;
- goto net_dev_put;
+ goto err1;
}
memset(&event, 0, sizeof event);
struct sockaddr *laddr = (struct sockaddr *)&iw_event->local_addr;
struct sockaddr *raddr = (struct sockaddr *)&iw_event->remote_addr;
- if (cma_disable_callback(id_priv, RDMA_CM_CONNECT))
- return 0;
+ mutex_lock(&id_priv->handler_mutex);
+ if (id_priv->state != RDMA_CM_CONNECT)
+ goto out;
memset(&event, 0, sizeof event);
switch (iw_event->event) {
return ret;
}
+out:
mutex_unlock(&id_priv->handler_mutex);
return ret;
}
struct rdma_cm_id *new_cm_id;
struct rdma_id_private *listen_id, *conn_id;
struct rdma_cm_event event;
- int ret;
+ int ret = -ECONNABORTED;
struct sockaddr *laddr = (struct sockaddr *)&iw_event->local_addr;
struct sockaddr *raddr = (struct sockaddr *)&iw_event->remote_addr;
listen_id = cm_id->context;
- if (cma_disable_callback(listen_id, RDMA_CM_LISTEN))
- return -ECONNABORTED;
+
+ mutex_lock(&listen_id->handler_mutex);
+ if (listen_id->state != RDMA_CM_LISTEN)
+ goto out;
/* Create a new RDMA id for the new IW CM ID */
new_cm_id = rdma_create_id(listen_id->id.route.addr.dev_addr.net,
struct ib_cm_sidr_rep_event_param *rep = &ib_event->param.sidr_rep_rcvd;
int ret = 0;
- if (cma_disable_callback(id_priv, RDMA_CM_CONNECT))
- return 0;
+ mutex_lock(&id_priv->handler_mutex);
+ if (id_priv->state != RDMA_CM_CONNECT)
+ goto out;
memset(&event, 0, sizeof event);
switch (ib_event->event) {
struct rdma_id_private *id_priv;
struct cma_multicast *mc = multicast->context;
struct rdma_cm_event event;
- int ret;
+ int ret = 0;
id_priv = mc->id_priv;
- if (cma_disable_callback(id_priv, RDMA_CM_ADDR_BOUND) &&
- cma_disable_callback(id_priv, RDMA_CM_ADDR_RESOLVED))
- return 0;
+ mutex_lock(&id_priv->handler_mutex);
+ if (id_priv->state != RDMA_CM_ADDR_BOUND &&
+ id_priv->state != RDMA_CM_ADDR_RESOLVED)
+ goto out;
if (!status)
status = cma_set_qkey(id_priv, be32_to_cpu(multicast->rec.qkey));
return 0;
}
+out:
mutex_unlock(&id_priv->handler_mutex);
return 0;
}
gid_type = id_priv->cma_dev->default_gid_type[id_priv->id.port_num -
rdma_start_port(id_priv->cma_dev->device)];
if (addr->sa_family == AF_INET) {
- if (gid_type == IB_GID_TYPE_ROCE_UDP_ENCAP)
+ if (gid_type == IB_GID_TYPE_ROCE_UDP_ENCAP) {
+ mc->multicast.ib->rec.hop_limit = IPV6_DEFAULT_HOPLIMIT;
err = cma_igmp_send(ndev, &mc->multicast.ib->rec.mgid,
true);
- if (!err) {
- mc->igmp_joined = true;
- mc->multicast.ib->rec.hop_limit = IPV6_DEFAULT_HOPLIMIT;
+ if (!err)
+ mc->igmp_joined = true;
}
} else {
if (gid_type == IB_GID_TYPE_ROCE_UDP_ENCAP)
struct ib_srq *srq = NULL;
struct ib_qp *qp;
char *buf;
- struct ib_qp_init_attr attr;
+ struct ib_qp_init_attr attr = {};
struct ib_uverbs_ex_create_qp_resp resp;
int ret;
ah_attr->grh.dgid = sgid;
if (!rdma_cap_eth_ah(device, port_num)) {
- ret = ib_find_cached_gid_by_port(device, &dgid,
- IB_GID_TYPE_IB,
- port_num, NULL,
- &gid_index);
- if (ret)
- return ret;
+ if (dgid.global.interface_id != cpu_to_be64(IB_SA_WELL_KNOWN_GUID)) {
+ ret = ib_find_cached_gid_by_port(device, &dgid,
+ IB_GID_TYPE_IB,
+ port_num, NULL,
+ &gid_index);
+ if (ret)
+ return ret;
+ } else {
+ gid_index = 0;
+ }
}
ah_attr->grh.sgid_index = (u8) gid_index;
static void dc_start(struct hfi1_devdata *);
static int qos_rmt_entries(struct hfi1_devdata *dd, unsigned int *mp,
unsigned int *np);
-static void remove_full_mgmt_pkey(struct hfi1_pportdata *ppd);
+static void clear_full_mgmt_pkey(struct hfi1_pportdata *ppd);
/*
* Error interrupt table entry. This is used as input to the interrupt
}
reset_neighbor_info(ppd);
- if (ppd->mgmt_allowed)
- remove_full_mgmt_pkey(ppd);
/* disable the port */
clear_rcvctrl(ppd->dd, RCV_CTRL_RCV_PORT_ENABLE_SMASK);
__func__, ppd->pkeys[2], FULL_MGMT_P_KEY);
ppd->pkeys[2] = FULL_MGMT_P_KEY;
(void)hfi1_set_ib_cfg(ppd, HFI1_IB_CFG_PKEYS, 0);
+ hfi1_event_pkey_change(ppd->dd, ppd->port);
}
-static void remove_full_mgmt_pkey(struct hfi1_pportdata *ppd)
+static void clear_full_mgmt_pkey(struct hfi1_pportdata *ppd)
{
- ppd->pkeys[2] = 0;
- (void)hfi1_set_ib_cfg(ppd, HFI1_IB_CFG_PKEYS, 0);
+ if (ppd->pkeys[2] != 0) {
+ ppd->pkeys[2] = 0;
+ (void)hfi1_set_ib_cfg(ppd, HFI1_IB_CFG_PKEYS, 0);
+ hfi1_event_pkey_change(ppd->dd, ppd->port);
+ }
}
/*
return 0;
}
+ /*
+ * FULL_MGMT_P_KEY is cleared from the pkey table, so that the
+ * pkey table can be configured properly if the HFI unit is connected
+ * to switch port with MgmtAllowed=NO
+ */
+ clear_full_mgmt_pkey(ppd);
+
return set_link_state(ppd, HLS_DN_POLL);
}
u64 len1 = 0, len2 = (((dd->vld[15].mtu + max_hb) >> 2)
& SEND_LEN_CHECK1_LEN_VL15_MASK) <<
SEND_LEN_CHECK1_LEN_VL15_SHIFT;
- int i;
+ int i, j;
u32 thres;
for (i = 0; i < ppd->vls_supported; i++) {
sc_mtu_to_threshold(dd->vld[i].sc,
dd->vld[i].mtu,
dd->rcd[0]->rcvhdrqentsize));
- sc_set_cr_threshold(dd->vld[i].sc, thres);
+ for (j = 0; j < INIT_SC_PER_VL; j++)
+ sc_set_cr_threshold(
+ pio_select_send_context_vl(dd, j, i),
+ thres);
}
thres = min(sc_percent_to_threshold(dd->vld[15].sc, 50),
sc_mtu_to_threshold(dd->vld[15].sc,
switch (cmd) {
case HFI1_IOCTL_ASSIGN_CTXT:
+ if (uctxt)
+ return -EINVAL;
+
if (copy_from_user(&uinfo,
(struct hfi1_user_info __user *)arg,
sizeof(uinfo)))
static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
{
int ret = 0, j, pidx, initfail;
- struct hfi1_devdata *dd = NULL;
+ struct hfi1_devdata *dd = ERR_PTR(-EINVAL);
struct hfi1_pportdata *ppd;
/* First, lock the non-writable module parameters */
memset(data, 0, size);
}
+void hfi1_event_pkey_change(struct hfi1_devdata *dd, u8 port)
+{
+ struct ib_event event;
+
+ event.event = IB_EVENT_PKEY_CHANGE;
+ event.device = &dd->verbs_dev.rdi.ibdev;
+ event.element.port_num = port;
+ ib_dispatch_event(&event);
+}
+
static void send_trap(struct hfi1_ibport *ibp, void *data, unsigned len)
{
struct ib_mad_send_buf *send_buf;
}
if (changed) {
- struct ib_event event;
-
(void)hfi1_set_ib_cfg(ppd, HFI1_IB_CFG_PKEYS, 0);
-
- event.event = IB_EVENT_PKEY_CHANGE;
- event.device = &dd->verbs_dev.rdi.ibdev;
- event.element.port_num = port;
- ib_dispatch_event(&event);
+ hfi1_event_pkey_change(dd, port);
}
+
return 0;
}
COUNTER_MASK(1, 3) | \
COUNTER_MASK(1, 4))
+void hfi1_event_pkey_change(struct hfi1_devdata *dd, u8 port);
+
#endif /* _HFI1_MAD_H */
/* counter is reset if occupancy count changes */
if (reg != reg_prev)
loop = 0;
- if (loop > 500) {
+ if (loop > 50000) {
/* timed out - bounce the link */
dd_dev_err(dd,
"%s: context %u(%u) timeout waiting for packets to egress, remaining count %u, bouncing link\n",
pio_map_free(m);
}
+/*
+ * Set credit return threshold for the kernel send context
+ */
+static void set_threshold(struct hfi1_devdata *dd, int scontext, int i)
+{
+ u32 thres;
+
+ thres = min(sc_percent_to_threshold(dd->kernel_send_context[scontext],
+ 50),
+ sc_mtu_to_threshold(dd->kernel_send_context[scontext],
+ dd->vld[i].mtu,
+ dd->rcd[0]->rcvhdrqentsize));
+ sc_set_cr_threshold(dd->kernel_send_context[scontext], thres);
+}
+
/*
* pio_map_init - called when #vls change
* @dd: hfi1_devdata
if (!newmap->map[i])
goto bail;
newmap->map[i]->mask = (1 << ilog2(sz)) - 1;
- /* assign send contexts */
+ /*
+ * assign send contexts and
+ * adjust credit return threshold
+ */
for (j = 0; j < sz; j++) {
- if (dd->kernel_send_context[scontext])
+ if (dd->kernel_send_context[scontext]) {
newmap->map[i]->ksc[j] =
dd->kernel_send_context[scontext];
+ set_threshold(dd, scontext, i);
+ }
if (++scontext >= first_scontext +
vl_scontexts[i])
/* wrap back to first send context */
if (ppd->qsfp_info.cache_valid) {
if (QSFP_IS_CU(cache[QSFP_MOD_TECH_OFFS]))
- sprintf(lenstr, "%dM ", cache[QSFP_MOD_LEN_OFFS]);
+ snprintf(lenstr, sizeof(lenstr), "%dM ",
+ cache[QSFP_MOD_LEN_OFFS]);
power_byte = cache[QSFP_MOD_PWR_OFFS];
sofar += scnprintf(buf + sofar, len - sofar, "PWR:%.3sW\n",
struct verbs_txreq *__get_txreq(struct hfi1_ibdev *dev,
struct rvt_qp *qp)
+ __must_hold(&qp->s_lock)
{
struct verbs_txreq *tx = ERR_PTR(-EBUSY);
- unsigned long flags;
- spin_lock_irqsave(&qp->s_lock, flags);
write_seqlock(&dev->iowait_lock);
if (ib_rvt_state_ops[qp->state] & RVT_PROCESS_RECV_OK) {
struct hfi1_qp_priv *priv;
}
out:
write_sequnlock(&dev->iowait_lock);
- spin_unlock_irqrestore(&qp->s_lock, flags);
return tx;
}
static inline struct verbs_txreq *get_txreq(struct hfi1_ibdev *dev,
struct rvt_qp *qp)
+ __must_hold(&qp->slock)
{
struct verbs_txreq *tx;
struct hfi1_qp_priv *priv = qp->priv;
#define IW_HMC_OBJ_TYPE_NUM ARRAY_SIZE(iw_hmc_obj_types)
#define IW_CFG_FPM_QP_COUNT 32768
+#define I40IW_MAX_PAGES_PER_FMR 512
+#define I40IW_MIN_PAGES_PER_FMR 1
#define I40IW_MTU_TO_MSS 40
#define I40IW_DEFAULT_MSS 1460
props->max_qp_init_rd_atom = props->max_qp_rd_atom;
props->atomic_cap = IB_ATOMIC_NONE;
props->max_map_per_fmr = 1;
+ props->max_fast_reg_page_list_len = I40IW_MAX_PAGES_PER_FMR;
return 0;
}
mutex_lock(&iwdev->pbl_mutex);
status = i40iw_get_pble(&iwdev->sc_dev, iwdev->pble_rsrc, palloc, iwmr->page_cnt);
mutex_unlock(&iwdev->pbl_mutex);
- if (!status)
+ if (status)
goto err1;
if (palloc->level != I40IW_LEVEL_1)
struct i40iw_sc_dev *dev = &iwqp->iwdev->sc_dev;
struct i40iw_fast_reg_stag_info info;
+ memset(&info, 0, sizeof(info));
info.access_rights = I40IW_ACCESS_FLAGS_LOCALREAD;
info.access_rights |= i40iw_get_user_access(flags);
info.stag_key = reg_wr(ib_wr)->key & 0xff;
info.addr_type = I40IW_ADDR_TYPE_VA_BASED;
info.va = (void *)(uintptr_t)iwmr->ibmr.iova;
info.total_len = iwmr->ibmr.length;
+ info.reg_addr_pa = *(u64 *)palloc->level1.addr;
info.first_pm_pbl_index = palloc->level1.idx;
info.local_fence = ib_wr->send_flags & IB_SEND_FENCE;
info.signaled = ib_wr->send_flags & IB_SEND_SIGNALED;
+ if (iwmr->npages > I40IW_MIN_PAGES_PER_FMR)
+ info.chunk_size = 1;
+
if (page_shift == 21)
info.page_size = 1; /* 2M page */
{
struct i40iw_cq *iwcq;
struct i40iw_cq_uk *ukcq;
- enum i40iw_completion_notify cq_notify = IW_CQ_COMPL_SOLICITED;
+ unsigned long flags;
+ enum i40iw_completion_notify cq_notify = IW_CQ_COMPL_EVENT;
iwcq = (struct i40iw_cq *)ibcq;
ukcq = &iwcq->sc_cq.cq_uk;
- if (notify_flags == IB_CQ_NEXT_COMP)
- cq_notify = IW_CQ_COMPL_EVENT;
+ if (notify_flags == IB_CQ_SOLICITED)
+ cq_notify = IW_CQ_COMPL_SOLICITED;
+ spin_lock_irqsave(&iwcq->lock, flags);
ukcq->ops.iw_cq_request_notification(ukcq, cq_notify);
+ spin_unlock_irqrestore(&iwcq->lock, flags);
return 0;
}
ah->av.ib.port_pd = cpu_to_be32(to_mpd(pd)->pdn | (ah_attr->port_num << 24));
ah->av.ib.g_slid = ah_attr->src_path_bits;
+ ah->av.ib.sl_tclass_flowlabel = cpu_to_be32(ah_attr->sl << 28);
if (ah_attr->ah_flags & IB_AH_GRH) {
ah->av.ib.g_slid |= 0x80;
ah->av.ib.gid_index = ah_attr->grh.sgid_index;
!(1 << ah->av.ib.stat_rate & dev->caps.stat_rate_support))
--ah->av.ib.stat_rate;
}
- ah->av.ib.sl_tclass_flowlabel = cpu_to_be32(ah_attr->sl << 28);
return &ah->ibah;
}
tun_tx_ix = (++tun_qp->tx_ix_head) & (MLX4_NUM_TUNNEL_BUFS - 1);
spin_unlock(&tun_qp->tx_lock);
if (ret)
- goto out;
+ goto end;
tun_mad = (struct mlx4_rcv_tunnel_mad *) (tun_qp->tx_ring[tun_tx_ix].buf.addr);
if (tun_qp->tx_ring[tun_tx_ix].ah)
wr.wr.send_flags = IB_SEND_SIGNALED;
ret = ib_post_send(src_qp, &wr.wr, &bad_wr);
-out:
- if (ret)
- ib_destroy_ah(ah);
+ if (!ret)
+ return 0;
+ out:
+ spin_lock(&tun_qp->tx_lock);
+ tun_qp->tx_ix_tail++;
+ spin_unlock(&tun_qp->tx_lock);
+ tun_qp->tx_ring[tun_tx_ix].ah = NULL;
+end:
+ ib_destroy_ah(ah);
return ret;
}
ret = ib_post_send(send_qp, &wr.wr, &bad_wr);
+ if (!ret)
+ return 0;
+
+ spin_lock(&sqp->tx_lock);
+ sqp->tx_ix_tail++;
+ spin_unlock(&sqp->tx_lock);
+ sqp->tx_ring[wire_tx_ix].ah = NULL;
out:
- if (ret)
- ib_destroy_ah(ah);
+ ib_destroy_ah(ah);
return ret;
}
struct mlx4_dev *dev = (to_mdev(qp->device))->dev;
int is_bonded = mlx4_is_bonded(dev);
+ if (flow_attr->port < 1 || flow_attr->port > qp->device->phys_port_cnt)
+ return ERR_PTR(-EINVAL);
+
if ((flow_attr->flags & IB_FLOW_ATTR_FLAGS_DONT_TRAP) &&
(flow_attr->type != IB_FLOW_ATTR_NORMAL))
return ERR_PTR(-EOPNOTSUPP);
u32 max_pages;
struct mlx4_mr mmr;
struct ib_umem *umem;
- void *pages_alloc;
+ size_t page_map_size;
};
struct mlx4_ib_mw {
struct mlx4_ib_mr *mr,
int max_pages)
{
- int size = max_pages * sizeof(u64);
- int add_size;
int ret;
- add_size = max_t(int, MLX4_MR_PAGES_ALIGN - ARCH_KMALLOC_MINALIGN, 0);
+ /* Ensure that size is aligned to DMA cacheline
+ * requirements.
+ * max_pages is limited to MLX4_MAX_FAST_REG_PAGES
+ * so page_map_size will never cross PAGE_SIZE.
+ */
+ mr->page_map_size = roundup(max_pages * sizeof(u64),
+ MLX4_MR_PAGES_ALIGN);
- mr->pages_alloc = kzalloc(size + add_size, GFP_KERNEL);
- if (!mr->pages_alloc)
+ /* Prevent cross page boundary allocation. */
+ mr->pages = (__be64 *)get_zeroed_page(GFP_KERNEL);
+ if (!mr->pages)
return -ENOMEM;
- mr->pages = PTR_ALIGN(mr->pages_alloc, MLX4_MR_PAGES_ALIGN);
-
mr->page_map = dma_map_single(device->dma_device, mr->pages,
- size, DMA_TO_DEVICE);
+ mr->page_map_size, DMA_TO_DEVICE);
if (dma_mapping_error(device->dma_device, mr->page_map)) {
ret = -ENOMEM;
}
return 0;
-err:
- kfree(mr->pages_alloc);
+err:
+ free_page((unsigned long)mr->pages);
return ret;
}
{
if (mr->pages) {
struct ib_device *device = mr->ibmr.device;
- int size = mr->max_pages * sizeof(u64);
dma_unmap_single(device->dma_device, mr->page_map,
- size, DMA_TO_DEVICE);
- kfree(mr->pages_alloc);
+ mr->page_map_size, DMA_TO_DEVICE);
+ free_page((unsigned long)mr->pages);
mr->pages = NULL;
}
}
mr->npages = 0;
ib_dma_sync_single_for_cpu(ibmr->device, mr->page_map,
- sizeof(u64) * mr->max_pages,
- DMA_TO_DEVICE);
+ mr->page_map_size, DMA_TO_DEVICE);
rc = ib_sg_to_pages(ibmr, sg, sg_nents, sg_offset, mlx4_set_page);
ib_dma_sync_single_for_device(ibmr->device, mr->page_map,
- sizeof(u64) * mr->max_pages,
- DMA_TO_DEVICE);
+ mr->page_map_size, DMA_TO_DEVICE);
return rc;
}
sizeof (struct mlx4_wqe_raddr_seg);
case MLX4_IB_QPT_RC:
return sizeof (struct mlx4_wqe_ctrl_seg) +
- sizeof (struct mlx4_wqe_atomic_seg) +
+ sizeof (struct mlx4_wqe_masked_atomic_seg) +
sizeof (struct mlx4_wqe_raddr_seg);
case MLX4_IB_QPT_SMI:
case MLX4_IB_QPT_GSI:
{
err = create_qp_common(to_mdev(pd->device), pd, init_attr,
udata, 0, &qp, gfp);
- if (err)
+ if (err) {
+ kfree(qp);
return ERR_PTR(err);
+ }
qp->ibqp.qp_num = qp->mqp.qpn;
qp->xrcdn = xrcdn;
pma_cnt_ext->port_xmit_data =
cpu_to_be64(MLX5_SUM_CNT(out, transmitted_ib_unicast.octets,
transmitted_ib_multicast.octets) >> 2);
- pma_cnt_ext->port_xmit_data =
+ pma_cnt_ext->port_rcv_data =
cpu_to_be64(MLX5_SUM_CNT(out, received_ib_unicast.octets,
received_ib_multicast.octets) >> 2);
pma_cnt_ext->port_xmit_packets =
return MLX5_FENCE_MODE_SMALL_AND_FENCE;
else
return fence;
-
- } else {
- return 0;
+ } else if (unlikely(wr->send_flags & IB_SEND_FENCE)) {
+ return MLX5_FENCE_MODE_FENCE;
}
+
+ return 0;
}
static int begin_wqe(struct mlx5_ib_qp *qp, void **seg,
switch (cmd.type) {
case QIB_CMD_ASSIGN_CTXT:
+ if (rcd) {
+ ret = -EINVAL;
+ goto bail;
+ }
+
ret = qib_assign_ctxt(fp, &cmd.cmd.user_info);
if (ret)
goto bail;
/* wrap to first map page, invert bit 0 */
offset = qpt->incr | ((offset & 1) ^ 1);
}
- /* there can be no bits at shift and below */
- WARN_ON(offset & (rdi->dparms.qos_shift - 1));
+ /* there can be no set bits in low-order QoS bits */
+ WARN_ON(offset & (BIT(rdi->dparms.qos_shift) - 1));
qpn = mk_qpn(qpt, map, offset);
}
qp->s_ssn = 1;
qp->s_lsn = 0;
qp->s_mig_state = IB_MIG_MIGRATED;
- if (qp->s_ack_queue)
- memset(
- qp->s_ack_queue,
- 0,
- rvt_max_atomic(rdi) *
- sizeof(*qp->s_ack_queue));
qp->r_head_ack_queue = 0;
qp->s_tail_ack_queue = 0;
qp->s_num_rd_atomic = 0;
* initialization that is needed.
*/
priv = rdi->driver_f.qp_priv_alloc(rdi, qp, gfp);
- if (!priv)
+ if (IS_ERR(priv)) {
+ ret = priv;
goto bail_qp;
+ }
qp->priv = priv;
qp->timeout_jiffies =
usecs_to_jiffies((4096UL * (1UL << qp->timeout)) /
!rdi->driver_f.quiesce_qp ||
!rdi->driver_f.notify_error_qp ||
!rdi->driver_f.mtu_from_qp ||
- !rdi->driver_f.mtu_to_path_mtu ||
- !rdi->driver_f.shut_down_port ||
- !rdi->driver_f.cap_mask_chg)
+ !rdi->driver_f.mtu_to_path_mtu)
return -EINVAL;
break;
*/
qp_init->cap.max_send_wr = srp_sq_size / 2;
qp_init->cap.max_rdma_ctxs = srp_sq_size / 2;
- qp_init->cap.max_send_sge = max(sdev->device->attrs.max_sge_rd,
- sdev->device->attrs.max_sge);
+ qp_init->cap.max_send_sge = SRPT_DEF_SG_PER_WQE;
qp_init->port_num = ch->sport->port;
ch->qp = ib_create_qp(sdev->pd, qp_init);
SRP_LOGIN_RSP_MULTICHAN_MAINTAINED = 0x2,
SRPT_DEF_SG_TABLESIZE = 128,
+ SRPT_DEF_SG_PER_WQE = 16,
MIN_SRPT_SQ_SIZE = 16,
DEF_SRPT_SQ_SIZE = 4096,
static void balloon_process(struct work_struct *work);
static DECLARE_DELAYED_WORK(balloon_worker, balloon_process);
-static void release_memory_resource(struct resource *resource);
-
/* When ballooning out (allocating memory to return to Xen) we don't really
want the kernel to try too hard since that can trigger the oom killer. */
#define GFP_BALLOON \
}
#ifdef CONFIG_XEN_BALLOON_MEMORY_HOTPLUG
+static void release_memory_resource(struct resource *resource)
+{
+ if (!resource)
+ return;
+
+ /*
+ * No need to reset region to identity mapped since we now
+ * know that no I/O can be in this region
+ */
+ release_resource(resource);
+ kfree(resource);
+}
+
static struct resource *additional_memory_resource(phys_addr_t size)
{
struct resource *res;
return res;
}
-static void release_memory_resource(struct resource *resource)
-{
- if (!resource)
- return;
-
- /*
- * No need to reset region to identity mapped since we now
- * know that no I/O can be in this region
- */
- release_resource(resource);
- kfree(resource);
-}
-
static enum bp_state reserve_additional_memory(void)
{
long credit;
field_start = OFFSET(cfg_entry);
field_end = OFFSET(cfg_entry) + field->size;
- if ((req_start >= field_start && req_start < field_end)
- || (req_end > field_start && req_end <= field_end)) {
+ if (req_end > field_start && field_end > req_start) {
err = conf_space_read(dev, cfg_entry, field_start,
&tmp_val);
if (err)
field_start = OFFSET(cfg_entry);
field_end = OFFSET(cfg_entry) + field->size;
- if ((req_start >= field_start && req_start < field_end)
- || (req_end > field_start && req_end <= field_end)) {
+ if (req_end > field_start && field_end > req_start) {
tmp_val = 0;
err = xen_pcibk_config_read(dev, field_start,
/* A write to obtain the length must happen as a 32-bit write.
* This does not (yet) support writing individual bytes
*/
- if (value == ~PCI_ROM_ADDRESS_ENABLE)
+ if ((value | ~PCI_ROM_ADDRESS_MASK) == ~0U)
bar->which = 1;
else {
u32 tmpval;
(PCI_BASE_ADDRESS_SPACE_MEMORY |
PCI_BASE_ADDRESS_MEM_TYPE_64))) {
bar_info->val = res[pos - 1].start >> 32;
- bar_info->len_val = res[pos - 1].end >> 32;
+ bar_info->len_val = -resource_size(&res[pos - 1]) >> 32;
return;
}
}
+ if (!res[pos].flags ||
+ (res[pos].flags & (IORESOURCE_DISABLED | IORESOURCE_UNSET |
+ IORESOURCE_BUSY)))
+ return;
+
bar_info->val = res[pos].start |
(res[pos].flags & PCI_REGION_FLAG_MASK);
- bar_info->len_val = resource_size(&res[pos]);
+ bar_info->len_val = -resource_size(&res[pos]) |
+ (res[pos].flags & PCI_REGION_FLAG_MASK);
}
static void *bar_init(struct pci_dev *dev, int offset)
{
- struct pci_bar_info *bar = kmalloc(sizeof(*bar), GFP_KERNEL);
+ struct pci_bar_info *bar = kzalloc(sizeof(*bar), GFP_KERNEL);
if (!bar)
return ERR_PTR(-ENOMEM);
read_dev_bar(dev, bar, offset, ~0);
- bar->which = 0;
return bar;
}
static void *rom_init(struct pci_dev *dev, int offset)
{
- struct pci_bar_info *bar = kmalloc(sizeof(*bar), GFP_KERNEL);
+ struct pci_bar_info *bar = kzalloc(sizeof(*bar), GFP_KERNEL);
if (!bar)
return ERR_PTR(-ENOMEM);
read_dev_bar(dev, bar, offset, ~PCI_ROM_ADDRESS_ENABLE);
- bar->which = 0;
return bar;
}
goto out;
inode = d_inode(fh->fh_dentry);
- if (!IS_POSIXACL(inode) || !inode->i_op->set_acl) {
- error = -EOPNOTSUPP;
- goto out_errno;
- }
error = fh_want_write(fh);
if (error)
goto out_errno;
- error = inode->i_op->set_acl(inode, argp->acl_access, ACL_TYPE_ACCESS);
+ fh_lock(fh);
+
+ error = set_posix_acl(inode, ACL_TYPE_ACCESS, argp->acl_access);
if (error)
- goto out_drop_write;
- error = inode->i_op->set_acl(inode, argp->acl_default,
- ACL_TYPE_DEFAULT);
+ goto out_drop_lock;
+ error = set_posix_acl(inode, ACL_TYPE_DEFAULT, argp->acl_default);
if (error)
- goto out_drop_write;
+ goto out_drop_lock;
+
+ fh_unlock(fh);
fh_drop_write(fh);
posix_acl_release(argp->acl_access);
posix_acl_release(argp->acl_default);
return nfserr;
-out_drop_write:
+out_drop_lock:
+ fh_unlock(fh);
fh_drop_write(fh);
out_errno:
nfserr = nfserrno(error);
goto out;
inode = d_inode(fh->fh_dentry);
- if (!IS_POSIXACL(inode) || !inode->i_op->set_acl) {
- error = -EOPNOTSUPP;
- goto out_errno;
- }
error = fh_want_write(fh);
if (error)
goto out_errno;
- error = inode->i_op->set_acl(inode, argp->acl_access, ACL_TYPE_ACCESS);
+ fh_lock(fh);
+
+ error = set_posix_acl(inode, ACL_TYPE_ACCESS, argp->acl_access);
if (error)
- goto out_drop_write;
- error = inode->i_op->set_acl(inode, argp->acl_default,
- ACL_TYPE_DEFAULT);
+ goto out_drop_lock;
+ error = set_posix_acl(inode, ACL_TYPE_DEFAULT, argp->acl_default);
-out_drop_write:
+out_drop_lock:
+ fh_unlock(fh);
fh_drop_write(fh);
out_errno:
nfserr = nfserrno(error);
dentry = fhp->fh_dentry;
inode = d_inode(dentry);
- if (!inode->i_op->set_acl || !IS_POSIXACL(inode))
- return nfserr_attrnotsupp;
-
if (S_ISDIR(inode->i_mode))
flags = NFS4_ACL_DIR;
if (host_error < 0)
goto out_nfserr;
- host_error = inode->i_op->set_acl(inode, pacl, ACL_TYPE_ACCESS);
+ fh_lock(fhp);
+
+ host_error = set_posix_acl(inode, ACL_TYPE_ACCESS, pacl);
if (host_error < 0)
- goto out_release;
+ goto out_drop_lock;
if (S_ISDIR(inode->i_mode)) {
- host_error = inode->i_op->set_acl(inode, dpacl,
- ACL_TYPE_DEFAULT);
+ host_error = set_posix_acl(inode, ACL_TYPE_DEFAULT, dpacl);
}
-out_release:
+out_drop_lock:
+ fh_unlock(fhp);
+
posix_acl_release(pacl);
posix_acl_release(dpacl);
out_nfserr:
return error;
}
-static int
-posix_acl_xattr_set(const struct xattr_handler *handler,
- struct dentry *unused, struct inode *inode,
- const char *name, const void *value,
- size_t size, int flags)
+int
+set_posix_acl(struct inode *inode, int type, struct posix_acl *acl)
{
- struct posix_acl *acl = NULL;
- int ret;
-
if (!IS_POSIXACL(inode))
return -EOPNOTSUPP;
if (!inode->i_op->set_acl)
return -EOPNOTSUPP;
- if (handler->flags == ACL_TYPE_DEFAULT && !S_ISDIR(inode->i_mode))
- return value ? -EACCES : 0;
+ if (type == ACL_TYPE_DEFAULT && !S_ISDIR(inode->i_mode))
+ return acl ? -EACCES : 0;
if (!inode_owner_or_capable(inode))
return -EPERM;
+ if (acl) {
+ int ret = posix_acl_valid(acl);
+ if (ret)
+ return ret;
+ }
+ return inode->i_op->set_acl(inode, acl, type);
+}
+EXPORT_SYMBOL(set_posix_acl);
+
+static int
+posix_acl_xattr_set(const struct xattr_handler *handler,
+ struct dentry *unused, struct inode *inode,
+ const char *name, const void *value,
+ size_t size, int flags)
+{
+ struct posix_acl *acl = NULL;
+ int ret;
+
if (value) {
acl = posix_acl_from_xattr(&init_user_ns, value, size);
if (IS_ERR(acl))
return PTR_ERR(acl);
-
- if (acl) {
- ret = posix_acl_valid(acl);
- if (ret)
- goto out;
- }
}
-
- ret = inode->i_op->set_acl(inode, acl, handler->flags);
-out:
+ ret = set_posix_acl(inode, handler->flags, acl);
posix_acl_release(acl);
return ret;
}
#define INIT_TASK(tsk) \
{ \
.state = 0, \
- .stack = &init_thread_info, \
+ .stack = init_stack, \
.usage = ATOMIC_INIT(2), \
.flags = PF_KTHREAD, \
.prio = MAX_PRIO-20, \
enum {
MLX5_FENCE_MODE_NONE = 0 << 5,
MLX5_FENCE_MODE_INITIATOR_SMALL = 1 << 5,
+ MLX5_FENCE_MODE_FENCE = 2 << 5,
MLX5_FENCE_MODE_STRONG_ORDERING = 3 << 5,
MLX5_FENCE_MODE_SMALL_AND_FENCE = 4 << 5,
};
return (obj >= stack) && (obj < (stack + THREAD_SIZE));
}
-extern void thread_info_cache_init(void);
+extern void thread_stack_cache_init(void);
#ifdef CONFIG_DEBUG_STACK_USAGE
static inline unsigned long stack_not_used(struct task_struct *p)
/*
* Allocate a private queue pair data structure for driver specific
- * information which is opaque to rdmavt.
+ * information which is opaque to rdmavt. Errors are returned via
+ * ERR_PTR(err). The driver is free to return NULL or a valid
+ * pointer.
*/
void * (*qp_priv_alloc)(struct rvt_dev_info *rdi, struct rvt_qp *qp,
gfp_t gfp);
}
# if THREAD_SIZE >= PAGE_SIZE
-void __init __weak thread_info_cache_init(void)
+void __init __weak thread_stack_cache_init(void)
{
}
#endif
/* Should be run before the first non-init thread is created */
init_espfix_bsp();
#endif
- thread_info_cache_init();
+ thread_stack_cache_init();
cred_init();
fork_init();
proc_caches_init();
}
#endif
-void __weak arch_release_thread_info(struct thread_info *ti)
+void __weak arch_release_thread_stack(unsigned long *stack)
{
}
-#ifndef CONFIG_ARCH_THREAD_INFO_ALLOCATOR
+#ifndef CONFIG_ARCH_THREAD_STACK_ALLOCATOR
/*
* Allocate pages if THREAD_SIZE is >= PAGE_SIZE, otherwise use a
* kmemcache based allocator.
*/
# if THREAD_SIZE >= PAGE_SIZE
-static struct thread_info *alloc_thread_info_node(struct task_struct *tsk,
+static unsigned long *alloc_thread_stack_node(struct task_struct *tsk,
int node)
{
struct page *page = alloc_kmem_pages_node(node, THREADINFO_GFP,
return page ? page_address(page) : NULL;
}
-static inline void free_thread_info(struct thread_info *ti)
+static inline void free_thread_stack(unsigned long *stack)
{
- struct page *page = virt_to_page(ti);
+ struct page *page = virt_to_page(stack);
memcg_kmem_update_page_stat(page, MEMCG_KERNEL_STACK,
-(1 << THREAD_SIZE_ORDER));
__free_kmem_pages(page, THREAD_SIZE_ORDER);
}
# else
-static struct kmem_cache *thread_info_cache;
+static struct kmem_cache *thread_stack_cache;
-static struct thread_info *alloc_thread_info_node(struct task_struct *tsk,
+static struct thread_info *alloc_thread_stack_node(struct task_struct *tsk,
int node)
{
- return kmem_cache_alloc_node(thread_info_cache, THREADINFO_GFP, node);
+ return kmem_cache_alloc_node(thread_stack_cache, THREADINFO_GFP, node);
}
-static void free_thread_info(struct thread_info *ti)
+static void free_stack(unsigned long *stack)
{
- kmem_cache_free(thread_info_cache, ti);
+ kmem_cache_free(thread_stack_cache, stack);
}
-void thread_info_cache_init(void)
+void thread_stack_cache_init(void)
{
- thread_info_cache = kmem_cache_create("thread_info", THREAD_SIZE,
+ thread_stack_cache = kmem_cache_create("thread_stack", THREAD_SIZE,
THREAD_SIZE, 0, NULL);
- BUG_ON(thread_info_cache == NULL);
+ BUG_ON(thread_stack_cache == NULL);
}
# endif
#endif
/* SLAB cache for mm_struct structures (tsk->mm) */
static struct kmem_cache *mm_cachep;
-static void account_kernel_stack(struct thread_info *ti, int account)
+static void account_kernel_stack(unsigned long *stack, int account)
{
- struct zone *zone = page_zone(virt_to_page(ti));
+ struct zone *zone = page_zone(virt_to_page(stack));
mod_zone_page_state(zone, NR_KERNEL_STACK, account);
}
void free_task(struct task_struct *tsk)
{
account_kernel_stack(tsk->stack, -1);
- arch_release_thread_info(tsk->stack);
- free_thread_info(tsk->stack);
+ arch_release_thread_stack(tsk->stack);
+ free_thread_stack(tsk->stack);
rt_mutex_debug_task_free(tsk);
ftrace_graph_exit_task(tsk);
put_seccomp_filter(tsk);
static struct task_struct *dup_task_struct(struct task_struct *orig, int node)
{
struct task_struct *tsk;
- struct thread_info *ti;
+ unsigned long *stack;
int err;
if (node == NUMA_NO_NODE)
if (!tsk)
return NULL;
- ti = alloc_thread_info_node(tsk, node);
- if (!ti)
+ stack = alloc_thread_stack_node(tsk, node);
+ if (!stack)
goto free_tsk;
err = arch_dup_task_struct(tsk, orig);
if (err)
- goto free_ti;
+ goto free_stack;
- tsk->stack = ti;
+ tsk->stack = stack;
#ifdef CONFIG_SECCOMP
/*
* We must handle setting up seccomp filters once we're under
tsk->task_frag.page = NULL;
tsk->wake_q.next = NULL;
- account_kernel_stack(ti, 1);
+ account_kernel_stack(stack, 1);
kcov_task_init(tsk);
return tsk;
-free_ti:
- free_thread_info(ti);
+free_stack:
+ free_thread_stack(stack);
free_tsk:
free_task_struct(tsk);
return NULL;
projects / cascardo / linux.git / commitdiff