F: drivers/media/tuners/mxl5007t.*
MYRICOM MYRI-10G 10GbE DRIVER (MYRI10GE)
-M: Andrew Gallatin <gallatin@myri.com>
+M: Hyong-Youb Kim <hykim@myri.com>
L: netdev@vger.kernel.org
-W: http://www.myri.com/scs/download-Myri10GE.html
+W: https://www.myricom.com/support/downloads/myri10ge.html
S: Supported
F: drivers/net/ethernet/myricom/myri10ge/
help
Architecture has the first two arguments of clone(2) swapped.
+config CLONE_BACKWARDS3
+ bool
+ help
+ Architecture has tls passed as the 3rd argument of clone(2),
+ not the 5th one.
+
config ODD_RT_SIGACTION
bool
help
struct mm_struct *mm;
unsigned int fullmm;
struct vm_area_struct *vma;
+ unsigned long start, end;
unsigned long range_start;
unsigned long range_end;
unsigned int nr;
}
static inline void
-tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned int fullmm)
+tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long start, unsigned long end)
{
tlb->mm = mm;
- tlb->fullmm = fullmm;
+ tlb->fullmm = !(start | (end+1));
+ tlb->start = start;
+ tlb->end = end;
tlb->vma = NULL;
tlb->max = ARRAY_SIZE(tlb->local);
tlb->pages = tlb->local;
static int
armpmu_map_hw_event(const unsigned (*event_map)[PERF_COUNT_HW_MAX], u64 config)
{
- int mapping = (*event_map)[config];
+ int mapping;
+
+ if (config >= PERF_COUNT_HW_MAX)
+ return -ENOENT;
+
+ mapping = (*event_map)[config];
return mapping == HW_OP_UNSUPPORTED ? -ENOENT : mapping;
}
struct mm_struct *mm;
unsigned int fullmm;
struct vm_area_struct *vma;
+ unsigned long start, end;
unsigned long range_start;
unsigned long range_end;
unsigned int nr;
}
static inline void
-tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned int fullmm)
+tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long start, unsigned long end)
{
tlb->mm = mm;
- tlb->fullmm = fullmm;
+ tlb->fullmm = !(start | (end+1));
+ tlb->start = start;
+ tlb->end = end;
tlb->vma = NULL;
tlb->max = ARRAY_SIZE(tlb->local);
tlb->pages = tlb->local;
endmenu
source "init/Kconfig"
+source "kernel/Kconfig.freezer"
source "drivers/Kconfig"
source "fs/Kconfig"
* unmapping a portion of the virtual address space, these hooks are called according to
* the following template:
*
- * tlb <- tlb_gather_mmu(mm, full_mm_flush); // start unmap for address space MM
+ * tlb <- tlb_gather_mmu(mm, start, end); // start unmap for address space MM
* {
* for each vma that needs a shootdown do {
* tlb_start_vma(tlb, vma);
unsigned int max;
unsigned char fullmm; /* non-zero means full mm flush */
unsigned char need_flush; /* really unmapped some PTEs? */
+ unsigned long start, end;
unsigned long start_addr;
unsigned long end_addr;
struct page **pages;
static inline void
-tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned int full_mm_flush)
+tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long start, unsigned long end)
{
tlb->mm = mm;
tlb->max = ARRAY_SIZE(tlb->local);
tlb->pages = tlb->local;
tlb->nr = 0;
- tlb->fullmm = full_mm_flush;
+ tlb->fullmm = !(start | (end+1));
+ tlb->start = start;
+ tlb->end = end;
tlb->start_addr = ~0UL;
}
select GENERIC_CLOCKEVENTS
select GENERIC_IDLE_POLL_SETUP
select MODULES_USE_ELF_RELA
- select CLONE_BACKWARDS
+ select CLONE_BACKWARDS3
config SWAP
def_bool n
source "init/Kconfig"
+source "kernel/Kconfig.freezer"
menu "Processor type and features"
struct mm_struct *mm;
struct mmu_table_batch *batch;
unsigned int fullmm;
+ unsigned long start, unsigned long end;
};
struct mmu_table_batch {
static inline void tlb_gather_mmu(struct mmu_gather *tlb,
struct mm_struct *mm,
- unsigned int full_mm_flush)
+ unsigned long start,
+ unsigned long end)
{
tlb->mm = mm;
- tlb->fullmm = full_mm_flush;
+ tlb->start = start;
+ tlb->end = end;
+ tlb->fullmm = !(start | (end+1));
tlb->batch = NULL;
if (tlb->fullmm)
__tlb_flush_mm(mm);
source "init/Kconfig"
+source "kernel/Kconfig.freezer"
+
config MMU
def_bool y
}
static inline void
-tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned int full_mm_flush)
+tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long start, unsigned long end)
{
tlb->mm = mm;
- tlb->fullmm = full_mm_flush;
+ tlb->start = start;
+ tlb->end = end;
+ tlb->fullmm = !(start | (end+1));
init_tlb_gather(tlb);
}
}
static inline void
-tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned int full_mm_flush)
+tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long start, unsigned long end)
{
tlb->mm = mm;
- tlb->fullmm = full_mm_flush;
+ tlb->start = start;
+ tlb->end = end;
+ tlb->fullmm = !(start | (end+1));
init_tlb_gather(tlb);
}
#define native_pmdp_get_and_clear(xp) native_local_pmdp_get_and_clear(xp)
#endif
+#ifdef CONFIG_MEM_SOFT_DIRTY
+
+/*
+ * Bits _PAGE_BIT_PRESENT, _PAGE_BIT_FILE, _PAGE_BIT_SOFT_DIRTY and
+ * _PAGE_BIT_PROTNONE are taken, split up the 28 bits of offset
+ * into this range.
+ */
+#define PTE_FILE_MAX_BITS 28
+#define PTE_FILE_SHIFT1 (_PAGE_BIT_PRESENT + 1)
+#define PTE_FILE_SHIFT2 (_PAGE_BIT_FILE + 1)
+#define PTE_FILE_SHIFT3 (_PAGE_BIT_PROTNONE + 1)
+#define PTE_FILE_SHIFT4 (_PAGE_BIT_SOFT_DIRTY + 1)
+#define PTE_FILE_BITS1 (PTE_FILE_SHIFT2 - PTE_FILE_SHIFT1 - 1)
+#define PTE_FILE_BITS2 (PTE_FILE_SHIFT3 - PTE_FILE_SHIFT2 - 1)
+#define PTE_FILE_BITS3 (PTE_FILE_SHIFT4 - PTE_FILE_SHIFT3 - 1)
+
+#define pte_to_pgoff(pte) \
+ ((((pte).pte_low >> (PTE_FILE_SHIFT1)) \
+ & ((1U << PTE_FILE_BITS1) - 1))) \
+ + ((((pte).pte_low >> (PTE_FILE_SHIFT2)) \
+ & ((1U << PTE_FILE_BITS2) - 1)) \
+ << (PTE_FILE_BITS1)) \
+ + ((((pte).pte_low >> (PTE_FILE_SHIFT3)) \
+ & ((1U << PTE_FILE_BITS3) - 1)) \
+ << (PTE_FILE_BITS1 + PTE_FILE_BITS2)) \
+ + ((((pte).pte_low >> (PTE_FILE_SHIFT4))) \
+ << (PTE_FILE_BITS1 + PTE_FILE_BITS2 + PTE_FILE_BITS3))
+
+#define pgoff_to_pte(off) \
+ ((pte_t) { .pte_low = \
+ ((((off)) & ((1U << PTE_FILE_BITS1) - 1)) << PTE_FILE_SHIFT1) \
+ + ((((off) >> PTE_FILE_BITS1) \
+ & ((1U << PTE_FILE_BITS2) - 1)) \
+ << PTE_FILE_SHIFT2) \
+ + ((((off) >> (PTE_FILE_BITS1 + PTE_FILE_BITS2)) \
+ & ((1U << PTE_FILE_BITS3) - 1)) \
+ << PTE_FILE_SHIFT3) \
+ + ((((off) >> \
+ (PTE_FILE_BITS1 + PTE_FILE_BITS2 + PTE_FILE_BITS3))) \
+ << PTE_FILE_SHIFT4) \
+ + _PAGE_FILE })
+
+#else /* CONFIG_MEM_SOFT_DIRTY */
+
/*
* Bits _PAGE_BIT_PRESENT, _PAGE_BIT_FILE and _PAGE_BIT_PROTNONE are taken,
- * split up the 29 bits of offset into this range:
+ * split up the 29 bits of offset into this range.
*/
#define PTE_FILE_MAX_BITS 29
#define PTE_FILE_SHIFT1 (_PAGE_BIT_PRESENT + 1)
<< PTE_FILE_SHIFT3) \
+ _PAGE_FILE })
+#endif /* CONFIG_MEM_SOFT_DIRTY */
+
/* Encode and de-code a swap entry */
#if _PAGE_BIT_FILE < _PAGE_BIT_PROTNONE
#define SWP_TYPE_BITS (_PAGE_BIT_FILE - _PAGE_BIT_PRESENT - 1)
/*
* Bits 0, 6 and 7 are taken in the low part of the pte,
* put the 32 bits of offset into the high part.
+ *
+ * For soft-dirty tracking 11 bit is taken from
+ * the low part of pte as well.
*/
#define pte_to_pgoff(pte) ((pte).pte_high)
#define pgoff_to_pte(off) \
return pmd_set_flags(pmd, _PAGE_SOFT_DIRTY);
}
+static inline pte_t pte_swp_mksoft_dirty(pte_t pte)
+{
+ return pte_set_flags(pte, _PAGE_SWP_SOFT_DIRTY);
+}
+
+static inline int pte_swp_soft_dirty(pte_t pte)
+{
+ return pte_flags(pte) & _PAGE_SWP_SOFT_DIRTY;
+}
+
+static inline pte_t pte_swp_clear_soft_dirty(pte_t pte)
+{
+ return pte_clear_flags(pte, _PAGE_SWP_SOFT_DIRTY);
+}
+
+static inline pte_t pte_file_clear_soft_dirty(pte_t pte)
+{
+ return pte_clear_flags(pte, _PAGE_SOFT_DIRTY);
+}
+
+static inline pte_t pte_file_mksoft_dirty(pte_t pte)
+{
+ return pte_set_flags(pte, _PAGE_SOFT_DIRTY);
+}
+
+static inline int pte_file_soft_dirty(pte_t pte)
+{
+ return pte_flags(pte) & _PAGE_SOFT_DIRTY;
+}
+
/*
* Mask out unsupported bits in a present pgprot. Non-present pgprots
* can use those bits for other purposes, so leave them be.
* they do not conflict with each other.
*/
+#define _PAGE_BIT_SOFT_DIRTY _PAGE_BIT_HIDDEN
+
#ifdef CONFIG_MEM_SOFT_DIRTY
-#define _PAGE_SOFT_DIRTY (_AT(pteval_t, 1) << _PAGE_BIT_HIDDEN)
+#define _PAGE_SOFT_DIRTY (_AT(pteval_t, 1) << _PAGE_BIT_SOFT_DIRTY)
#else
#define _PAGE_SOFT_DIRTY (_AT(pteval_t, 0))
#endif
+/*
+ * Tracking soft dirty bit when a page goes to a swap is tricky.
+ * We need a bit which can be stored in pte _and_ not conflict
+ * with swap entry format. On x86 bits 6 and 7 are *not* involved
+ * into swap entry computation, but bit 6 is used for nonlinear
+ * file mapping, so we borrow bit 7 for soft dirty tracking.
+ */
+#ifdef CONFIG_MEM_SOFT_DIRTY
+#define _PAGE_SWP_SOFT_DIRTY _PAGE_PSE
+#else
+#define _PAGE_SWP_SOFT_DIRTY (_AT(pteval_t, 0))
+#endif
+
#if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE)
#define _PAGE_NX (_AT(pteval_t, 1) << _PAGE_BIT_NX)
#else
#define arch_read_relax(lock) cpu_relax()
#define arch_write_relax(lock) cpu_relax()
-/* The {read|write|spin}_lock() on x86 are full memory barriers. */
-static inline void smp_mb__after_lock(void) { }
-#define ARCH_HAS_SMP_MB_AFTER_LOCK
-
#endif /* _ASM_X86_SPINLOCK_H */
case 70:
case 71:
case 63:
+ case 69:
x86_pmu.late_ack = true;
memcpy(hw_cache_event_ids, snb_hw_cache_event_ids, sizeof(hw_cache_event_ids));
memcpy(hw_cache_extra_regs, snb_hw_cache_extra_regs, sizeof(hw_cache_extra_regs));
static struct uncore_event_desc snbep_uncore_qpi_events[] = {
INTEL_UNCORE_EVENT_DESC(clockticks, "event=0x14"),
INTEL_UNCORE_EVENT_DESC(txl_flits_active, "event=0x00,umask=0x06"),
- INTEL_UNCORE_EVENT_DESC(drs_data, "event=0x02,umask=0x08"),
- INTEL_UNCORE_EVENT_DESC(ncb_data, "event=0x03,umask=0x04"),
+ INTEL_UNCORE_EVENT_DESC(drs_data, "event=0x102,umask=0x08"),
+ INTEL_UNCORE_EVENT_DESC(ncb_data, "event=0x103,umask=0x04"),
{ /* end: all zeroes */ },
};
*begin = new_begin;
}
} else {
- *begin = TASK_UNMAPPED_BASE;
+ *begin = mmap_legacy_base();
*end = TASK_SIZE;
}
}
* Bottom-up (legacy) layout on X86_32 did not support randomization, X86_64
* does, but not when emulating X86_32
*/
-static unsigned long mmap_legacy_base(void)
+unsigned long mmap_legacy_base(void)
{
if (mmap_is_ia32())
return TASK_UNMAPPED_BASE;
int i;
bio_for_each_segment(bv, bio, i) {
- page = bv->bv_page;
/* Non-zero page count for non-head members of
- * compound pages is no longer allowed by the kernel,
- * but this has never been seen here.
+ * compound pages is no longer allowed by the kernel.
*/
- if (unlikely(PageCompound(page)))
- if (compound_trans_head(page) != page) {
- pr_crit("page tail used for block I/O\n");
- BUG();
- }
+ page = compound_trans_head(bv->bv_page);
atomic_inc(&page->_count);
}
}
bio_pagedec(struct bio *bio)
{
struct bio_vec *bv;
+ struct page *page;
int i;
- bio_for_each_segment(bv, bio, i)
- atomic_dec(&bv->bv_page->_count);
+ bio_for_each_segment(bv, bio, i) {
+ page = compound_trans_head(bv->bv_page);
+ atomic_dec(&page->_count);
+ }
}
static void
* The bonding ndo_neigh_setup is called at init time beofre any
* slave exists. So we must declare proxy setup function which will
* be used at run time to resolve the actual slave neigh param setup.
+ *
+ * It's also called by master devices (such as vlans) to setup their
+ * underlying devices. In that case - do nothing, we're already set up from
+ * our init.
*/
static int bond_neigh_setup(struct net_device *dev,
struct neigh_parms *parms)
{
- parms->neigh_setup = bond_neigh_init;
+ /* modify only our neigh_parms */
+ if (parms->dev == dev)
+ parms->neigh_setup = bond_neigh_init;
return 0;
}
if ((mc->ptr + rec_len) > mc->end)
goto decode_failed;
- memcpy(cf->data, mc->ptr, rec_len);
+ memcpy(cf->data, mc->ptr, cf->can_dlc);
mc->ptr += rec_len;
}
struct arc_emac_priv *priv = netdev_priv(ndev);
unsigned int work_done;
- for (work_done = 0; work_done <= budget; work_done++) {
+ for (work_done = 0; work_done < budget; work_done++) {
unsigned int *last_rx_bd = &priv->last_rx_bd;
struct net_device_stats *stats = &priv->stats;
struct buffer_state *rx_buff = &priv->rx_buff[*last_rx_bd];
#define BC_SUPPORTS_DCBX_MSG_NON_PMF (1 << 21)
#define IS_VF_FLAG (1 << 22)
#define INTERRUPTS_ENABLED_FLAG (1 << 23)
+#define BC_SUPPORTS_RMMOD_CMD (1 << 24)
#define BP_NOMCP(bp) ((bp)->flags & NO_MCP_FLAG)
int fp_array_size;
u32 dump_preset_idx;
+ bool stats_started;
+ struct semaphore stats_sema;
};
/* Tx queues may be less or equal to Rx queues */
BNX2X_PCI_LINK_SPEED_5000 = 5000,
BNX2X_PCI_LINK_SPEED_8000 = 8000
};
+
+void bnx2x_set_local_cmng(struct bnx2x *bp);
#endif /* bnx2x.h */
bnx2x_pfc_set_pfc(bp);
bnx2x_dcbx_update_ets_params(bp);
+
+ /* ets may affect cmng configuration: reinit it in hw */
+ bnx2x_set_local_cmng(bp);
+
bnx2x_dcbx_resume_hw_tx(bp);
return;
#define DRV_MSG_CODE_EEE_RESULTS_ACK 0xda000000
+ #define DRV_MSG_CODE_RMMOD 0xdb000000
+ #define REQ_BC_VER_4_RMMOD_CMD 0x0007080f
+
#define DRV_MSG_CODE_SET_MF_BW 0xe0000000
#define REQ_BC_VER_4_SET_MF_BW 0x00060202
#define DRV_MSG_CODE_SET_MF_BW_ACK 0xe1000000
#define FW_MSG_CODE_EEE_RESULS_ACK 0xda100000
+ #define FW_MSG_CODE_RMMOD_ACK 0xdb100000
+
#define FW_MSG_CODE_SET_MF_BW_SENT 0xe0000000
#define FW_MSG_CODE_SET_MF_BW_DONE 0xe1000000
input.port_rate = bp->link_vars.line_speed;
- if (cmng_type == CMNG_FNS_MINMAX) {
+ if (cmng_type == CMNG_FNS_MINMAX && input.port_rate) {
int vn;
/* read mf conf from shmem */
}
}
+/* init cmng mode in HW according to local configuration */
+void bnx2x_set_local_cmng(struct bnx2x *bp)
+{
+ int cmng_fns = bnx2x_get_cmng_fns_mode(bp);
+
+ if (cmng_fns != CMNG_FNS_NONE) {
+ bnx2x_cmng_fns_init(bp, false, cmng_fns);
+ storm_memset_cmng(bp, &bp->cmng, BP_PORT(bp));
+ } else {
+ /* rate shaping and fairness are disabled */
+ DP(NETIF_MSG_IFUP,
+ "single function mode without fairness\n");
+ }
+}
+
/* This function is called upon link interrupt */
static void bnx2x_link_attn(struct bnx2x *bp)
{
bnx2x_stats_handle(bp, STATS_EVENT_LINK_UP);
}
- if (bp->link_vars.link_up && bp->link_vars.line_speed) {
- int cmng_fns = bnx2x_get_cmng_fns_mode(bp);
-
- if (cmng_fns != CMNG_FNS_NONE) {
- bnx2x_cmng_fns_init(bp, false, cmng_fns);
- storm_memset_cmng(bp, &bp->cmng, BP_PORT(bp));
- } else
- /* rate shaping and fairness are disabled */
- DP(NETIF_MSG_IFUP,
- "single function mode without fairness\n");
- }
+ if (bp->link_vars.link_up && bp->link_vars.line_speed)
+ bnx2x_set_local_cmng(bp);
__bnx2x_link_report(bp);
bp->flags |= (val >= REQ_BC_VER_4_DCBX_ADMIN_MSG_NON_PMF) ?
BC_SUPPORTS_DCBX_MSG_NON_PMF : 0;
+
+ bp->flags |= (val >= REQ_BC_VER_4_RMMOD_CMD) ?
+ BC_SUPPORTS_RMMOD_CMD : 0;
+
boot_mode = SHMEM_RD(bp,
dev_info.port_feature_config[BP_PORT(bp)].mba_config) &
PORT_FEATURE_MBA_BOOT_AGENT_TYPE_MASK;
mutex_init(&bp->port.phy_mutex);
mutex_init(&bp->fw_mb_mutex);
spin_lock_init(&bp->stats_lock);
+ sema_init(&bp->stats_sema, 1);
INIT_DELAYED_WORK(&bp->sp_task, bnx2x_sp_task);
INIT_DELAYED_WORK(&bp->sp_rtnl_task, bnx2x_sp_rtnl_task);
bnx2x_dcbnl_update_applist(bp, true);
#endif
+ if (IS_PF(bp) &&
+ !BP_NOMCP(bp) &&
+ (bp->flags & BC_SUPPORTS_RMMOD_CMD))
+ bnx2x_fw_command(bp, DRV_MSG_CODE_RMMOD, 0);
+
/* Close the interface - either directly or implicitly */
if (remove_netdev) {
unregister_netdev(dev);
} else {
rtnl_lock();
- if (netif_running(dev))
- bnx2x_close(dev);
+ dev_close(dev);
rtnl_unlock();
}
alloc_mem_err:
BNX2X_PCI_FREE(bp->vf2pf_mbox, bp->vf2pf_mbox_mapping,
sizeof(struct bnx2x_vf_mbx_msg));
- BNX2X_PCI_FREE(bp->vf2pf_mbox, bp->vf2pf_mbox_mapping,
+ BNX2X_PCI_FREE(bp->vf2pf_mbox, bp->pf2vf_bulletin_mapping,
sizeof(union pf_vf_bulletin));
return -ENOMEM;
}
* Statistics service functions
*/
-static void bnx2x_stats_pmf_update(struct bnx2x *bp)
+/* should be called under stats_sema */
+static void __bnx2x_stats_pmf_update(struct bnx2x *bp)
{
struct dmae_command *dmae;
u32 opcode;
*stats_comp = 0;
}
-static void bnx2x_stats_start(struct bnx2x *bp)
+/* should be called under stats_sema */
+static void __bnx2x_stats_start(struct bnx2x *bp)
{
/* vfs travel through here as part of the statistics FSM, but no action
* is required
bnx2x_hw_stats_post(bp);
bnx2x_storm_stats_post(bp);
+
+ bp->stats_started = true;
+}
+
+static void bnx2x_stats_start(struct bnx2x *bp)
+{
+ if (down_timeout(&bp->stats_sema, HZ/10))
+ BNX2X_ERR("Unable to acquire stats lock\n");
+ __bnx2x_stats_start(bp);
+ up(&bp->stats_sema);
}
static void bnx2x_stats_pmf_start(struct bnx2x *bp)
{
+ if (down_timeout(&bp->stats_sema, HZ/10))
+ BNX2X_ERR("Unable to acquire stats lock\n");
bnx2x_stats_comp(bp);
- bnx2x_stats_pmf_update(bp);
- bnx2x_stats_start(bp);
+ __bnx2x_stats_pmf_update(bp);
+ __bnx2x_stats_start(bp);
+ up(&bp->stats_sema);
+}
+
+static void bnx2x_stats_pmf_update(struct bnx2x *bp)
+{
+ if (down_timeout(&bp->stats_sema, HZ/10))
+ BNX2X_ERR("Unable to acquire stats lock\n");
+ __bnx2x_stats_pmf_update(bp);
+ up(&bp->stats_sema);
}
static void bnx2x_stats_restart(struct bnx2x *bp)
*/
if (IS_VF(bp))
return;
+ if (down_timeout(&bp->stats_sema, HZ/10))
+ BNX2X_ERR("Unable to acquire stats lock\n");
bnx2x_stats_comp(bp);
- bnx2x_stats_start(bp);
+ __bnx2x_stats_start(bp);
+ up(&bp->stats_sema);
}
static void bnx2x_bmac_stats_update(struct bnx2x *bp)
/* Make sure we use the value of the counter
* used for sending the last stats ramrod.
*/
- spin_lock_bh(&bp->stats_lock);
cur_stats_counter = bp->stats_counter - 1;
- spin_unlock_bh(&bp->stats_lock);
/* are storm stats valid? */
if (le16_to_cpu(counters->xstats_counter) != cur_stats_counter) {
{
u32 *stats_comp = bnx2x_sp(bp, stats_comp);
- if (bnx2x_edebug_stats_stopped(bp))
+ /* we run update from timer context, so give up
+ * if somebody is in the middle of transition
+ */
+ if (down_trylock(&bp->stats_sema))
return;
+ if (bnx2x_edebug_stats_stopped(bp) || !bp->stats_started)
+ goto out;
+
if (IS_PF(bp)) {
if (*stats_comp != DMAE_COMP_VAL)
- return;
+ goto out;
if (bp->port.pmf)
bnx2x_hw_stats_update(bp);
BNX2X_ERR("storm stats were not updated for 3 times\n");
bnx2x_panic();
}
- return;
+ goto out;
}
} else {
/* vf doesn't collect HW statistics, and doesn't get completions
/* vf is done */
if (IS_VF(bp))
- return;
+ goto out;
if (netif_msg_timer(bp)) {
struct bnx2x_eth_stats *estats = &bp->eth_stats;
bnx2x_hw_stats_post(bp);
bnx2x_storm_stats_post(bp);
+
+out:
+ up(&bp->stats_sema);
}
static void bnx2x_port_stats_stop(struct bnx2x *bp)
{
int update = 0;
+ if (down_timeout(&bp->stats_sema, HZ/10))
+ BNX2X_ERR("Unable to acquire stats lock\n");
+
+ bp->stats_started = false;
+
bnx2x_stats_comp(bp);
if (bp->port.pmf)
bnx2x_hw_stats_post(bp);
bnx2x_stats_comp(bp);
}
+
+ up(&bp->stats_sema);
}
static void bnx2x_stats_do_nothing(struct bnx2x *bp)
void bnx2x_stats_handle(struct bnx2x *bp, enum bnx2x_stats_event event)
{
enum bnx2x_stats_state state;
+ void (*action)(struct bnx2x *bp);
if (unlikely(bp->panic))
return;
spin_lock_bh(&bp->stats_lock);
state = bp->stats_state;
bp->stats_state = bnx2x_stats_stm[state][event].next_state;
+ action = bnx2x_stats_stm[state][event].action;
spin_unlock_bh(&bp->stats_lock);
- bnx2x_stats_stm[state][event].action(bp);
+ action(bp);
if ((event != STATS_EVENT_UPDATE) || netif_msg_timer(bp))
DP(BNX2X_MSG_STATS, "state %d -> event %d -> state %d\n",
done:
if (state == pci_channel_io_perm_failure) {
- tg3_napi_enable(tp);
- dev_close(netdev);
+ if (netdev) {
+ tg3_napi_enable(tp);
+ dev_close(netdev);
+ }
err = PCI_ERS_RESULT_DISCONNECT;
} else {
pci_disable_device(pdev);
rtnl_lock();
if (pci_enable_device(pdev)) {
- netdev_err(netdev, "Cannot re-enable PCI device after reset.\n");
+ dev_err(&pdev->dev,
+ "Cannot re-enable PCI device after reset.\n");
goto done;
}
pci_restore_state(pdev);
pci_save_state(pdev);
- if (!netif_running(netdev)) {
+ if (!netdev || !netif_running(netdev)) {
rc = PCI_ERS_RESULT_RECOVERED;
goto done;
}
rc = PCI_ERS_RESULT_RECOVERED;
done:
- if (rc != PCI_ERS_RESULT_RECOVERED && netif_running(netdev)) {
+ if (rc != PCI_ERS_RESULT_RECOVERED && netdev && netif_running(netdev)) {
tg3_napi_enable(tp);
dev_close(netdev);
}
q->pg_chunk.offset = 0;
mapping = pci_map_page(adapter->pdev, q->pg_chunk.page,
0, q->alloc_size, PCI_DMA_FROMDEVICE);
- if (unlikely(pci_dma_mapping_error(adapter->pdev, mapping))) {
- __free_pages(q->pg_chunk.page, order);
- q->pg_chunk.page = NULL;
- return -EIO;
- }
q->pg_chunk.mapping = mapping;
}
sd->pg_chunk = q->pg_chunk;
return flits_to_desc(flits);
}
-
-/* map_skb - map a packet main body and its page fragments
- * @pdev: the PCI device
- * @skb: the packet
- * @addr: placeholder to save the mapped addresses
- *
- * map the main body of an sk_buff and its page fragments, if any.
- */
-static int map_skb(struct pci_dev *pdev, const struct sk_buff *skb,
- dma_addr_t *addr)
-{
- const skb_frag_t *fp, *end;
- const struct skb_shared_info *si;
-
- *addr = pci_map_single(pdev, skb->data, skb_headlen(skb),
- PCI_DMA_TODEVICE);
- if (pci_dma_mapping_error(pdev, *addr))
- goto out_err;
-
- si = skb_shinfo(skb);
- end = &si->frags[si->nr_frags];
-
- for (fp = si->frags; fp < end; fp++) {
- *++addr = skb_frag_dma_map(&pdev->dev, fp, 0, skb_frag_size(fp),
- DMA_TO_DEVICE);
- if (pci_dma_mapping_error(pdev, *addr))
- goto unwind;
- }
- return 0;
-
-unwind:
- while (fp-- > si->frags)
- dma_unmap_page(&pdev->dev, *--addr, skb_frag_size(fp),
- DMA_TO_DEVICE);
-
- pci_unmap_single(pdev, addr[-1], skb_headlen(skb), PCI_DMA_TODEVICE);
-out_err:
- return -ENOMEM;
-}
-
/**
- * write_sgl - populate a scatter/gather list for a packet
+ * make_sgl - populate a scatter/gather list for a packet
* @skb: the packet
* @sgp: the SGL to populate
* @start: start address of skb main body data to include in the SGL
* @len: length of skb main body data to include in the SGL
- * @addr: the list of the mapped addresses
+ * @pdev: the PCI device
*
- * Copies the scatter/gather list for the buffers that make up a packet
+ * Generates a scatter/gather list for the buffers that make up a packet
* and returns the SGL size in 8-byte words. The caller must size the SGL
* appropriately.
*/
-static inline unsigned int write_sgl(const struct sk_buff *skb,
+static inline unsigned int make_sgl(const struct sk_buff *skb,
struct sg_ent *sgp, unsigned char *start,
- unsigned int len, const dma_addr_t *addr)
+ unsigned int len, struct pci_dev *pdev)
{
- unsigned int i, j = 0, k = 0, nfrags;
+ dma_addr_t mapping;
+ unsigned int i, j = 0, nfrags;
if (len) {
+ mapping = pci_map_single(pdev, start, len, PCI_DMA_TODEVICE);
sgp->len[0] = cpu_to_be32(len);
- sgp->addr[j++] = cpu_to_be64(addr[k++]);
+ sgp->addr[0] = cpu_to_be64(mapping);
+ j = 1;
}
nfrags = skb_shinfo(skb)->nr_frags;
for (i = 0; i < nfrags; i++) {
const skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
+ mapping = skb_frag_dma_map(&pdev->dev, frag, 0, skb_frag_size(frag),
+ DMA_TO_DEVICE);
sgp->len[j] = cpu_to_be32(skb_frag_size(frag));
- sgp->addr[j] = cpu_to_be64(addr[k++]);
+ sgp->addr[j] = cpu_to_be64(mapping);
j ^= 1;
if (j == 0)
++sgp;
const struct port_info *pi,
unsigned int pidx, unsigned int gen,
struct sge_txq *q, unsigned int ndesc,
- unsigned int compl, const dma_addr_t *addr)
+ unsigned int compl)
{
unsigned int flits, sgl_flits, cntrl, tso_info;
struct sg_ent *sgp, sgl[MAX_SKB_FRAGS / 2 + 1];
}
sgp = ndesc == 1 ? (struct sg_ent *)&d->flit[flits] : sgl;
- sgl_flits = write_sgl(skb, sgp, skb->data, skb_headlen(skb), addr);
+ sgl_flits = make_sgl(skb, sgp, skb->data, skb_headlen(skb), adap->pdev);
write_wr_hdr_sgl(ndesc, skb, d, pidx, q, sgl, flits, sgl_flits, gen,
htonl(V_WR_OP(FW_WROPCODE_TUNNEL_TX_PKT) | compl),
struct netdev_queue *txq;
struct sge_qset *qs;
struct sge_txq *q;
- dma_addr_t addr[MAX_SKB_FRAGS + 1];
/*
* The chip min packet length is 9 octets but play safe and reject
return NETDEV_TX_BUSY;
}
- if (unlikely(map_skb(adap->pdev, skb, addr) < 0)) {
- dev_kfree_skb(skb);
- return NETDEV_TX_OK;
- }
-
q->in_use += ndesc;
if (unlikely(credits - ndesc < q->stop_thres)) {
t3_stop_tx_queue(txq, qs, q);
if (likely(!skb_shared(skb)))
skb_orphan(skb);
- write_tx_pkt_wr(adap, skb, pi, pidx, gen, q, ndesc, compl, addr);
+ write_tx_pkt_wr(adap, skb, pi, pidx, gen, q, ndesc, compl);
check_ring_tx_db(adap, q);
return NETDEV_TX_OK;
}
*/
static void write_ofld_wr(struct adapter *adap, struct sk_buff *skb,
struct sge_txq *q, unsigned int pidx,
- unsigned int gen, unsigned int ndesc,
- const dma_addr_t *addr)
+ unsigned int gen, unsigned int ndesc)
{
unsigned int sgl_flits, flits;
struct work_request_hdr *from;
flits = skb_transport_offset(skb) / 8;
sgp = ndesc == 1 ? (struct sg_ent *)&d->flit[flits] : sgl;
- sgl_flits = write_sgl(skb, sgp, skb_transport_header(skb),
- skb_tail_pointer(skb) -
- skb_transport_header(skb), addr);
+ sgl_flits = make_sgl(skb, sgp, skb_transport_header(skb),
+ skb->tail - skb->transport_header,
+ adap->pdev);
if (need_skb_unmap()) {
setup_deferred_unmapping(skb, adap->pdev, sgp, sgl_flits);
skb->destructor = deferred_unmap_destructor;
goto again;
}
- if (map_skb(adap->pdev, skb, (dma_addr_t *)skb->head)) {
- spin_unlock(&q->lock);
- return NET_XMIT_SUCCESS;
- }
-
gen = q->gen;
q->in_use += ndesc;
pidx = q->pidx;
}
spin_unlock(&q->lock);
- write_ofld_wr(adap, skb, q, pidx, gen, ndesc, (dma_addr_t *)skb->head);
+ write_ofld_wr(adap, skb, q, pidx, gen, ndesc);
check_ring_tx_db(adap, q);
return NET_XMIT_SUCCESS;
}
struct sge_txq *q = &qs->txq[TXQ_OFLD];
const struct port_info *pi = netdev_priv(qs->netdev);
struct adapter *adap = pi->adapter;
- unsigned int written = 0;
spin_lock(&q->lock);
again: reclaim_completed_tx(adap, q, TX_RECLAIM_CHUNK);
break;
}
- if (map_skb(adap->pdev, skb, (dma_addr_t *)skb->head))
- break;
-
gen = q->gen;
q->in_use += ndesc;
pidx = q->pidx;
q->pidx += ndesc;
- written += ndesc;
if (q->pidx >= q->size) {
q->pidx -= q->size;
q->gen ^= 1;
__skb_unlink(skb, &q->sendq);
spin_unlock(&q->lock);
- write_ofld_wr(adap, skb, q, pidx, gen, ndesc,
- (dma_addr_t *)skb->head);
+ write_ofld_wr(adap, skb, q, pidx, gen, ndesc);
spin_lock(&q->lock);
}
spin_unlock(&q->lock);
set_bit(TXQ_LAST_PKT_DB, &q->flags);
#endif
wmb();
- if (likely(written))
- t3_write_reg(adap, A_SG_KDOORBELL,
- F_SELEGRCNTX | V_EGRCNTX(q->cntxt_id));
+ t3_write_reg(adap, A_SG_KDOORBELL,
+ F_SELEGRCNTX | V_EGRCNTX(q->cntxt_id));
}
/**
adapter->max_event_queues = le16_to_cpu(desc->eq_count);
adapter->if_cap_flags = le32_to_cpu(desc->cap_flags);
+
+ /* Clear flags that driver is not interested in */
+ adapter->if_cap_flags &= BE_IF_CAP_FLAGS_WANT;
}
err:
mutex_unlock(&adapter->mbox_lock);
BE_IF_FLAGS_MULTICAST = 0x1000
};
+#define BE_IF_CAP_FLAGS_WANT (BE_IF_FLAGS_RSS | BE_IF_FLAGS_PROMISCUOUS |\
+ BE_IF_FLAGS_BROADCAST | BE_IF_FLAGS_VLAN_PROMISCUOUS |\
+ BE_IF_FLAGS_VLAN | BE_IF_FLAGS_MCAST_PROMISCUOUS |\
+ BE_IF_FLAGS_PASS_L3L4_ERRORS | BE_IF_FLAGS_MULTICAST |\
+ BE_IF_FLAGS_UNTAGGED)
+
/* An RX interface is an object with one or more MAC addresses and
* filtering capabilities. */
struct be_cmd_req_if_create {
}
/* Allocate and setup a new buffer for receiving */
-static void skge_rx_setup(struct skge_port *skge, struct skge_element *e,
- struct sk_buff *skb, unsigned int bufsize)
+static int skge_rx_setup(struct skge_port *skge, struct skge_element *e,
+ struct sk_buff *skb, unsigned int bufsize)
{
struct skge_rx_desc *rd = e->desc;
- u64 map;
+ dma_addr_t map;
map = pci_map_single(skge->hw->pdev, skb->data, bufsize,
PCI_DMA_FROMDEVICE);
- rd->dma_lo = map;
- rd->dma_hi = map >> 32;
+ if (pci_dma_mapping_error(skge->hw->pdev, map))
+ return -1;
+
+ rd->dma_lo = lower_32_bits(map);
+ rd->dma_hi = upper_32_bits(map);
e->skb = skb;
rd->csum1_start = ETH_HLEN;
rd->csum2_start = ETH_HLEN;
rd->control = BMU_OWN | BMU_STF | BMU_IRQ_EOF | BMU_TCP_CHECK | bufsize;
dma_unmap_addr_set(e, mapaddr, map);
dma_unmap_len_set(e, maplen, bufsize);
+ return 0;
}
/* Resume receiving using existing skb,
return -ENOMEM;
skb_reserve(skb, NET_IP_ALIGN);
- skge_rx_setup(skge, e, skb, skge->rx_buf_size);
+ if (skge_rx_setup(skge, e, skb, skge->rx_buf_size) < 0) {
+ dev_kfree_skb(skb);
+ return -EIO;
+ }
} while ((e = e->next) != ring->start);
ring->to_clean = ring->start;
BUG_ON(skge->dma & 7);
- if ((u64)skge->dma >> 32 != ((u64) skge->dma + skge->mem_size) >> 32) {
+ if (upper_32_bits(skge->dma) != upper_32_bits(skge->dma + skge->mem_size)) {
dev_err(&hw->pdev->dev, "pci_alloc_consistent region crosses 4G boundary\n");
err = -EINVAL;
goto free_pci_mem;
struct skge_tx_desc *td;
int i;
u32 control, len;
- u64 map;
+ dma_addr_t map;
if (skb_padto(skb, ETH_ZLEN))
return NETDEV_TX_OK;
e->skb = skb;
len = skb_headlen(skb);
map = pci_map_single(hw->pdev, skb->data, len, PCI_DMA_TODEVICE);
+ if (pci_dma_mapping_error(hw->pdev, map))
+ goto mapping_error;
+
dma_unmap_addr_set(e, mapaddr, map);
dma_unmap_len_set(e, maplen, len);
- td->dma_lo = map;
- td->dma_hi = map >> 32;
+ td->dma_lo = lower_32_bits(map);
+ td->dma_hi = upper_32_bits(map);
if (skb->ip_summed == CHECKSUM_PARTIAL) {
const int offset = skb_checksum_start_offset(skb);
map = skb_frag_dma_map(&hw->pdev->dev, frag, 0,
skb_frag_size(frag), DMA_TO_DEVICE);
+ if (dma_mapping_error(&hw->pdev->dev, map))
+ goto mapping_unwind;
e = e->next;
e->skb = skb;
tf = e->desc;
BUG_ON(tf->control & BMU_OWN);
- tf->dma_lo = map;
- tf->dma_hi = (u64) map >> 32;
+ tf->dma_lo = lower_32_bits(map);
+ tf->dma_hi = upper_32_bits(map);
dma_unmap_addr_set(e, mapaddr, map);
dma_unmap_len_set(e, maplen, skb_frag_size(frag));
}
return NETDEV_TX_OK;
+
+mapping_unwind:
+ e = skge->tx_ring.to_use;
+ pci_unmap_single(hw->pdev,
+ dma_unmap_addr(e, mapaddr),
+ dma_unmap_len(e, maplen),
+ PCI_DMA_TODEVICE);
+ while (i-- > 0) {
+ e = e->next;
+ pci_unmap_page(hw->pdev,
+ dma_unmap_addr(e, mapaddr),
+ dma_unmap_len(e, maplen),
+ PCI_DMA_TODEVICE);
+ }
+
+mapping_error:
+ if (net_ratelimit())
+ dev_warn(&hw->pdev->dev, "%s: tx mapping error\n", dev->name);
+ dev_kfree_skb(skb);
+ return NETDEV_TX_OK;
}
pci_dma_sync_single_for_cpu(skge->hw->pdev,
dma_unmap_addr(e, mapaddr),
- len, PCI_DMA_FROMDEVICE);
+ dma_unmap_len(e, maplen),
+ PCI_DMA_FROMDEVICE);
skb_copy_from_linear_data(e->skb, skb->data, len);
pci_dma_sync_single_for_device(skge->hw->pdev,
dma_unmap_addr(e, mapaddr),
- len, PCI_DMA_FROMDEVICE);
+ dma_unmap_len(e, maplen),
+ PCI_DMA_FROMDEVICE);
skge_rx_reuse(e, skge->rx_buf_size);
} else {
struct sk_buff *nskb;
if (!nskb)
goto resubmit;
+ if (skge_rx_setup(skge, e, nskb, skge->rx_buf_size) < 0) {
+ dev_kfree_skb(nskb);
+ goto resubmit;
+ }
+
pci_unmap_single(skge->hw->pdev,
dma_unmap_addr(e, mapaddr),
dma_unmap_len(e, maplen),
PCI_DMA_FROMDEVICE);
skb = e->skb;
prefetch(skb->data);
- skge_rx_setup(skge, e, nskb, skge->rx_buf_size);
}
skb_put(skb, len);
#include "mlx5_core.h"
enum {
- CMD_IF_REV = 4,
+ CMD_IF_REV = 5,
};
enum {
case MLX5_EVENT_TYPE_PAGE_REQUEST:
{
u16 func_id = be16_to_cpu(eqe->data.req_pages.func_id);
- s16 npages = be16_to_cpu(eqe->data.req_pages.num_pages);
+ s32 npages = be32_to_cpu(eqe->data.req_pages.num_pages);
mlx5_core_dbg(dev, "page request for func 0x%x, napges %d\n", func_id, npages);
mlx5_core_req_pages_handler(dev, func_id, npages);
caps->log_max_srq = out->hca_cap.log_max_srqs & 0x1f;
caps->local_ca_ack_delay = out->hca_cap.local_ca_ack_delay & 0x1f;
caps->log_max_mcg = out->hca_cap.log_max_mcg;
- caps->max_qp_mcg = be16_to_cpu(out->hca_cap.max_qp_mcg);
+ caps->max_qp_mcg = be32_to_cpu(out->hca_cap.max_qp_mcg) & 0xffffff;
caps->max_ra_res_qp = 1 << (out->hca_cap.log_max_ra_res_qp & 0x3f);
caps->max_ra_req_qp = 1 << (out->hca_cap.log_max_ra_req_qp & 0x3f);
caps->max_srq_wqes = 1 << out->hca_cap.log_max_srq_sz;
};
static DEFINE_SPINLOCK(health_lock);
-
static LIST_HEAD(health_list);
static struct work_struct health_work;
-static health_handler_t reg_handler;
-int mlx5_register_health_report_handler(health_handler_t handler)
-{
- spin_lock_irq(&health_lock);
- if (reg_handler) {
- spin_unlock_irq(&health_lock);
- return -EEXIST;
- }
- reg_handler = handler;
- spin_unlock_irq(&health_lock);
-
- return 0;
-}
-EXPORT_SYMBOL(mlx5_register_health_report_handler);
-
-void mlx5_unregister_health_report_handler(void)
-{
- spin_lock_irq(&health_lock);
- reg_handler = NULL;
- spin_unlock_irq(&health_lock);
-}
-EXPORT_SYMBOL(mlx5_unregister_health_report_handler);
-
static void health_care(struct work_struct *work)
{
struct mlx5_core_health *health, *n;
priv = container_of(health, struct mlx5_priv, health);
dev = container_of(priv, struct mlx5_core_dev, priv);
mlx5_core_warn(dev, "handling bad device here\n");
+ /* nothing yet */
spin_lock_irq(&health_lock);
- if (reg_handler)
- reg_handler(dev->pdev, health->health,
- sizeof(health->health));
-
list_del_init(&health->list);
spin_unlock_irq(&health_lock);
}
MLX5_PAGES_TAKE = 2
};
+enum {
+ MLX5_BOOT_PAGES = 1,
+ MLX5_INIT_PAGES = 2,
+ MLX5_POST_INIT_PAGES = 3
+};
+
struct mlx5_pages_req {
struct mlx5_core_dev *dev;
u32 func_id;
- s16 npages;
+ s32 npages;
struct work_struct work;
};
struct mlx5_query_pages_outbox {
struct mlx5_outbox_hdr hdr;
- __be16 num_boot_pages;
+ __be16 rsvd;
__be16 func_id;
- __be16 init_pages;
- __be16 num_pages;
+ __be32 num_pages;
};
struct mlx5_manage_pages_inbox {
struct mlx5_inbox_hdr hdr;
- __be16 rsvd0;
+ __be16 rsvd;
__be16 func_id;
- __be16 rsvd1;
- __be16 num_entries;
- u8 rsvd2[16];
+ __be32 num_entries;
__be64 pas[0];
};
struct mlx5_manage_pages_outbox {
struct mlx5_outbox_hdr hdr;
- u8 rsvd0[2];
- __be16 num_entries;
- u8 rsvd1[20];
+ __be32 num_entries;
+ u8 rsvd[4];
__be64 pas[0];
};
}
static int mlx5_cmd_query_pages(struct mlx5_core_dev *dev, u16 *func_id,
- s16 *pages, s16 *init_pages, u16 *boot_pages)
+ s32 *npages, int boot)
{
struct mlx5_query_pages_inbox in;
struct mlx5_query_pages_outbox out;
memset(&in, 0, sizeof(in));
memset(&out, 0, sizeof(out));
in.hdr.opcode = cpu_to_be16(MLX5_CMD_OP_QUERY_PAGES);
+ in.hdr.opmod = boot ? cpu_to_be16(MLX5_BOOT_PAGES) : cpu_to_be16(MLX5_INIT_PAGES);
+
err = mlx5_cmd_exec(dev, &in, sizeof(in), &out, sizeof(out));
if (err)
return err;
if (out.hdr.status)
return mlx5_cmd_status_to_err(&out.hdr);
- if (pages)
- *pages = be16_to_cpu(out.num_pages);
-
- if (init_pages)
- *init_pages = be16_to_cpu(out.init_pages);
-
- if (boot_pages)
- *boot_pages = be16_to_cpu(out.num_boot_pages);
-
+ *npages = be32_to_cpu(out.num_pages);
*func_id = be16_to_cpu(out.func_id);
return err;
in->hdr.opcode = cpu_to_be16(MLX5_CMD_OP_MANAGE_PAGES);
in->hdr.opmod = cpu_to_be16(MLX5_PAGES_GIVE);
in->func_id = cpu_to_be16(func_id);
- in->num_entries = cpu_to_be16(npages);
+ in->num_entries = cpu_to_be32(npages);
err = mlx5_cmd_exec(dev, in, inlen, &out, sizeof(out));
mlx5_core_dbg(dev, "err %d\n", err);
if (err) {
in.hdr.opcode = cpu_to_be16(MLX5_CMD_OP_MANAGE_PAGES);
in.hdr.opmod = cpu_to_be16(MLX5_PAGES_TAKE);
in.func_id = cpu_to_be16(func_id);
- in.num_entries = cpu_to_be16(npages);
+ in.num_entries = cpu_to_be32(npages);
mlx5_core_dbg(dev, "npages %d, outlen %d\n", npages, outlen);
err = mlx5_cmd_exec(dev, &in, sizeof(in), out, outlen);
if (err) {
goto out_free;
}
- num_claimed = be16_to_cpu(out->num_entries);
+ num_claimed = be32_to_cpu(out->num_entries);
if (nclaimed)
*nclaimed = num_claimed;
}
void mlx5_core_req_pages_handler(struct mlx5_core_dev *dev, u16 func_id,
- s16 npages)
+ s32 npages)
{
struct mlx5_pages_req *req;
int mlx5_satisfy_startup_pages(struct mlx5_core_dev *dev, int boot)
{
- u16 uninitialized_var(boot_pages);
- s16 uninitialized_var(init_pages);
u16 uninitialized_var(func_id);
+ s32 uninitialized_var(npages);
int err;
- err = mlx5_cmd_query_pages(dev, &func_id, NULL, &init_pages,
- &boot_pages);
+ err = mlx5_cmd_query_pages(dev, &func_id, &npages, boot);
if (err)
return err;
+ mlx5_core_dbg(dev, "requested %d %s pages for func_id 0x%x\n",
+ npages, boot ? "boot" : "init", func_id);
- mlx5_core_dbg(dev, "requested %d init pages and %d boot pages for func_id 0x%x\n",
- init_pages, boot_pages, func_id);
- return give_pages(dev, func_id, boot ? boot_pages : init_pages, 0);
+ return give_pages(dev, func_id, npages, 0);
}
static int optimal_reclaimed_pages(void)
u8 val;
int ret, max_sds_rings = adapter->max_sds_rings;
+ if (test_bit(__QLCNIC_RESETTING, &adapter->state)) {
+ netdev_info(netdev, "Device is resetting\n");
+ return -EBUSY;
+ }
+
if (qlcnic_get_diag_lock(adapter)) {
netdev_info(netdev, "Device in diagnostics mode\n");
return -EBUSY;
return -EIO;
}
- qlcnic_set_drv_version(adapter);
+ if (adapter->portnum == 0)
+ qlcnic_set_drv_version(adapter);
qlcnic_83xx_idc_attach_driver(adapter);
return 0;
if (err)
goto err_out_disable_mbx_intr;
- qlcnic_set_drv_version(adapter);
+ if (adapter->portnum == 0)
+ qlcnic_set_drv_version(adapter);
pci_set_drvdata(pdev, adapter);
adapter->fw_fail_cnt = 0;
adapter->flags &= ~QLCNIC_FW_HANG;
clear_bit(__QLCNIC_RESETTING, &adapter->state);
- qlcnic_set_drv_version(adapter);
+ if (adapter->portnum == 0)
+ qlcnic_set_drv_version(adapter);
if (!qlcnic_clr_drv_state(adapter))
qlcnic_schedule_work(adapter, qlcnic_fw_poll_work,
if (ahw->extra_capability[0] & QLCNIC_FW_CAPABILITY_2_BEACON) {
err = qlcnic_get_beacon_state(adapter, &h_beacon_state);
- if (!err) {
- dev_info(&adapter->pdev->dev,
- "Failed to get current beacon state\n");
+ if (err) {
+ netdev_err(adapter->netdev,
+ "Failed to get current beacon state\n");
} else {
if (h_beacon_state == QLCNIC_BEACON_DISABLE)
ahw->beacon_state = 0;
PCI_DMA_FROMDEVICE);
if (dma_mapping_error(&cp->pdev->dev, new_mapping)) {
dev->stats.rx_dropped++;
+ kfree_skb(new_skb);
goto rx_next;
}
struct stmmac_priv *priv = (struct stmmac_priv *)p;
unsigned int txsize = priv->dma_tx_size;
unsigned int entry = priv->cur_tx % txsize;
- struct dma_desc *desc = priv->dma_tx + entry;
+ struct dma_desc *desc;
unsigned int nopaged_len = skb_headlen(skb);
unsigned int bmax, len;
+ if (priv->extend_desc)
+ desc = (struct dma_desc *)(priv->dma_etx + entry);
+ else
+ desc = priv->dma_tx + entry;
+
if (priv->plat->enh_desc)
bmax = BUF_SIZE_8KiB;
else
STMMAC_RING_MODE);
wmb();
entry = (++priv->cur_tx) % txsize;
- desc = priv->dma_tx + entry;
+
+ if (priv->extend_desc)
+ desc = (struct dma_desc *)(priv->dma_etx + entry);
+ else
+ desc = priv->dma_tx + entry;
desc->des2 = dma_map_single(priv->device, skb->data + bmax,
len, DMA_TO_DEVICE);
skb = __netdev_alloc_skb(priv->dev, priv->dma_buf_sz + NET_IP_ALIGN,
GFP_KERNEL);
- if (unlikely(skb == NULL)) {
+ if (!skb) {
pr_err("%s: Rx init fails; skb is NULL\n", __func__);
- return 1;
+ return -ENOMEM;
}
skb_reserve(skb, NET_IP_ALIGN);
priv->rx_skbuff[i] = skb;
priv->rx_skbuff_dma[i] = dma_map_single(priv->device, skb->data,
priv->dma_buf_sz,
DMA_FROM_DEVICE);
+ if (dma_mapping_error(priv->device, priv->rx_skbuff_dma[i])) {
+ pr_err("%s: DMA mapping error\n", __func__);
+ dev_kfree_skb_any(skb);
+ return -EINVAL;
+ }
p->des2 = priv->rx_skbuff_dma[i];
return 0;
}
+static void stmmac_free_rx_buffers(struct stmmac_priv *priv, int i)
+{
+ if (priv->rx_skbuff[i]) {
+ dma_unmap_single(priv->device, priv->rx_skbuff_dma[i],
+ priv->dma_buf_sz, DMA_FROM_DEVICE);
+ dev_kfree_skb_any(priv->rx_skbuff[i]);
+ }
+ priv->rx_skbuff[i] = NULL;
+}
+
/**
* init_dma_desc_rings - init the RX/TX descriptor rings
* @dev: net device structure
* and allocates the socket buffers. It suppors the chained and ring
* modes.
*/
-static void init_dma_desc_rings(struct net_device *dev)
+static int init_dma_desc_rings(struct net_device *dev)
{
int i;
struct stmmac_priv *priv = netdev_priv(dev);
unsigned int txsize = priv->dma_tx_size;
unsigned int rxsize = priv->dma_rx_size;
unsigned int bfsize = 0;
+ int ret = -ENOMEM;
/* Set the max buffer size according to the DESC mode
* and the MTU. Note that RING mode allows 16KiB bsize.
dma_extended_desc),
&priv->dma_rx_phy,
GFP_KERNEL);
+ if (!priv->dma_erx)
+ goto err_dma;
+
priv->dma_etx = dma_alloc_coherent(priv->device, txsize *
sizeof(struct
dma_extended_desc),
&priv->dma_tx_phy,
GFP_KERNEL);
- if ((!priv->dma_erx) || (!priv->dma_etx))
- return;
+ if (!priv->dma_etx) {
+ dma_free_coherent(priv->device, priv->dma_rx_size *
+ sizeof(struct dma_extended_desc),
+ priv->dma_erx, priv->dma_rx_phy);
+ goto err_dma;
+ }
} else {
priv->dma_rx = dma_alloc_coherent(priv->device, rxsize *
sizeof(struct dma_desc),
&priv->dma_rx_phy,
GFP_KERNEL);
+ if (!priv->dma_rx)
+ goto err_dma;
+
priv->dma_tx = dma_alloc_coherent(priv->device, txsize *
sizeof(struct dma_desc),
&priv->dma_tx_phy,
GFP_KERNEL);
- if ((!priv->dma_rx) || (!priv->dma_tx))
- return;
+ if (!priv->dma_tx) {
+ dma_free_coherent(priv->device, priv->dma_rx_size *
+ sizeof(struct dma_desc),
+ priv->dma_rx, priv->dma_rx_phy);
+ goto err_dma;
+ }
}
priv->rx_skbuff_dma = kmalloc_array(rxsize, sizeof(dma_addr_t),
GFP_KERNEL);
+ if (!priv->rx_skbuff_dma)
+ goto err_rx_skbuff_dma;
+
priv->rx_skbuff = kmalloc_array(rxsize, sizeof(struct sk_buff *),
GFP_KERNEL);
+ if (!priv->rx_skbuff)
+ goto err_rx_skbuff;
+
priv->tx_skbuff_dma = kmalloc_array(txsize, sizeof(dma_addr_t),
GFP_KERNEL);
+ if (!priv->tx_skbuff_dma)
+ goto err_tx_skbuff_dma;
+
priv->tx_skbuff = kmalloc_array(txsize, sizeof(struct sk_buff *),
GFP_KERNEL);
+ if (!priv->tx_skbuff)
+ goto err_tx_skbuff;
+
if (netif_msg_probe(priv)) {
pr_debug("(%s) dma_rx_phy=0x%08x dma_tx_phy=0x%08x\n", __func__,
(u32) priv->dma_rx_phy, (u32) priv->dma_tx_phy);
else
p = priv->dma_rx + i;
- if (stmmac_init_rx_buffers(priv, p, i))
- break;
+ ret = stmmac_init_rx_buffers(priv, p, i);
+ if (ret)
+ goto err_init_rx_buffers;
if (netif_msg_probe(priv))
pr_debug("[%p]\t[%p]\t[%x]\n", priv->rx_skbuff[i],
if (netif_msg_hw(priv))
stmmac_display_rings(priv);
+
+ return 0;
+err_init_rx_buffers:
+ while (--i >= 0)
+ stmmac_free_rx_buffers(priv, i);
+ kfree(priv->tx_skbuff);
+err_tx_skbuff:
+ kfree(priv->tx_skbuff_dma);
+err_tx_skbuff_dma:
+ kfree(priv->rx_skbuff);
+err_rx_skbuff:
+ kfree(priv->rx_skbuff_dma);
+err_rx_skbuff_dma:
+ if (priv->extend_desc) {
+ dma_free_coherent(priv->device, priv->dma_tx_size *
+ sizeof(struct dma_extended_desc),
+ priv->dma_etx, priv->dma_tx_phy);
+ dma_free_coherent(priv->device, priv->dma_rx_size *
+ sizeof(struct dma_extended_desc),
+ priv->dma_erx, priv->dma_rx_phy);
+ } else {
+ dma_free_coherent(priv->device,
+ priv->dma_tx_size * sizeof(struct dma_desc),
+ priv->dma_tx, priv->dma_tx_phy);
+ dma_free_coherent(priv->device,
+ priv->dma_rx_size * sizeof(struct dma_desc),
+ priv->dma_rx, priv->dma_rx_phy);
+ }
+err_dma:
+ return ret;
}
static void dma_free_rx_skbufs(struct stmmac_priv *priv)
{
int i;
- for (i = 0; i < priv->dma_rx_size; i++) {
- if (priv->rx_skbuff[i]) {
- dma_unmap_single(priv->device, priv->rx_skbuff_dma[i],
- priv->dma_buf_sz, DMA_FROM_DEVICE);
- dev_kfree_skb_any(priv->rx_skbuff[i]);
- }
- priv->rx_skbuff[i] = NULL;
- }
+ for (i = 0; i < priv->dma_rx_size; i++)
+ stmmac_free_rx_buffers(priv, i);
}
static void dma_free_tx_skbufs(struct stmmac_priv *priv)
priv->dma_tx_size = STMMAC_ALIGN(dma_txsize);
priv->dma_rx_size = STMMAC_ALIGN(dma_rxsize);
priv->dma_buf_sz = STMMAC_ALIGN(buf_sz);
- init_dma_desc_rings(dev);
+
+ ret = init_dma_desc_rings(dev);
+ if (ret < 0) {
+ pr_err("%s: DMA descriptors initialization failed\n", __func__);
+ goto dma_desc_error;
+ }
/* DMA initialization and SW reset */
ret = stmmac_init_dma_engine(priv);
if (ret < 0) {
- pr_err("%s: DMA initialization failed\n", __func__);
+ pr_err("%s: DMA engine initialization failed\n", __func__);
goto init_error;
}
init_error:
free_dma_desc_resources(priv);
+dma_desc_error:
if (priv->phydev)
phy_disconnect(priv->phydev);
phy_error:
__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vid);
}
- netif_rx(skb);
+ netif_receive_skb(skb);
stats->rx_bytes += pkt_len;
stats->rx_packets++;
return ret;
err_iounmap:
+ netif_napi_del(&vptr->napi);
iounmap(regs);
err_free_dev:
free_netdev(netdev);
struct velocity_info *vptr = netdev_priv(netdev);
unregister_netdev(netdev);
+ netif_napi_del(&vptr->napi);
iounmap(vptr->mac_regs);
free_netdev(netdev);
velocity_nics--;
return -EADDRNOTAVAIL;
}
+ if (data && data[IFLA_MACVLAN_FLAGS] &&
+ nla_get_u16(data[IFLA_MACVLAN_FLAGS]) & ~MACVLAN_FLAG_NOPROMISC)
+ return -EINVAL;
+
if (data && data[IFLA_MACVLAN_MODE]) {
switch (nla_get_u32(data[IFLA_MACVLAN_MODE])) {
case MACVLAN_MODE_PRIVATE:
skb_shinfo(skb)->tx_flags |= SKBTX_DEV_ZEROCOPY;
skb_shinfo(skb)->tx_flags |= SKBTX_SHARED_FRAG;
}
- if (vlan)
+ if (vlan) {
+ local_bh_disable();
macvlan_start_xmit(skb, vlan->dev);
- else
+ local_bh_enable();
+ } else {
kfree_skb(skb);
+ }
rcu_read_unlock();
return total_len;
done:
rcu_read_lock();
vlan = rcu_dereference(q->vlan);
- if (vlan)
+ if (vlan) {
+ preempt_disable();
macvlan_count_rx(vlan, copied - vnet_hdr_len, ret == 0, 0);
+ preempt_enable();
+ }
rcu_read_unlock();
return ret ? ret : copied;
u32 rxhash;
if (!(tun->flags & TUN_NO_PI)) {
- if ((len -= sizeof(pi)) > total_len)
+ if (len < sizeof(pi))
return -EINVAL;
+ len -= sizeof(pi);
if (memcpy_fromiovecend((void *)&pi, iv, 0, sizeof(pi)))
return -EFAULT;
}
if (tun->flags & TUN_VNET_HDR) {
- if ((len -= tun->vnet_hdr_sz) > total_len)
+ if (len < tun->vnet_hdr_sz)
return -EINVAL;
+ len -= tun->vnet_hdr_sz;
if (memcpy_fromiovecend((void *)&gso, iv, offset, sizeof(gso)))
return -EFAULT;
return -ENOTCONN;
if (IN_MULTICAST(ntohl(vxlan->default_dst.remote_ip)) &&
- ! vxlan_group_used(vn, vxlan->default_dst.remote_ip)) {
+ vxlan_group_used(vn, vxlan->default_dst.remote_ip)) {
vxlan_sock_hold(vs);
dev_hold(dev);
queue_work(vxlan_wq, &vxlan->igmp_join);
struct vxlan_net *vn = net_generic(dev_net(dev), vxlan_net_id);
struct vxlan_dev *vxlan = netdev_priv(dev);
- flush_workqueue(vxlan_wq);
-
spin_lock(&vn->sock_lock);
hlist_del_rcu(&vxlan->hlist);
spin_unlock(&vn->sock_lock);
if (!priv->join_status)
goto done;
- if (priv->join_status > CW1200_JOIN_STATUS_IBSS) {
- wiphy_err(priv->hw->wiphy, "Unexpected: join status: %d\n",
- priv->join_status);
- BUG_ON(1);
- }
+ if (priv->join_status == CW1200_JOIN_STATUS_AP)
+ goto done;
cancel_work_sync(&priv->update_filtering_work);
cancel_work_sync(&priv->set_beacon_wakeup_period_work);
* is killed. Hence update the killswitch state here. The
* rfkill handler will care about restarting if needed.
*/
- if (!test_bit(S_ALIVE, &il->status)) {
- if (hw_rf_kill)
- set_bit(S_RFKILL, &il->status);
- else
- clear_bit(S_RFKILL, &il->status);
+ if (hw_rf_kill) {
+ set_bit(S_RFKILL, &il->status);
+ } else {
+ clear_bit(S_RFKILL, &il->status);
wiphy_rfkill_set_hw_state(il->hw->wiphy, hw_rf_kill);
+ il_force_reset(il, true);
}
handled |= CSR_INT_BIT_RF_KILL;
il->active_rate = RATES_MASK;
+ il_power_update_mode(il, true);
+ D_INFO("Updated power mode\n");
+
if (il_is_associated(il)) {
struct il_rxon_cmd *active_rxon =
(struct il_rxon_cmd *)&il->active;
D_INFO("ALIVE processing complete.\n");
wake_up(&il->wait_command_queue);
- il_power_update_mode(il, true);
- D_INFO("Updated power mode\n");
-
return;
restart:
return 0;
}
+EXPORT_SYMBOL(il_force_reset);
int
il_mac_change_interface(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
#include <linux/init.h>
#include <linux/platform_device.h>
#include <linux/interrupt.h>
+#include <linux/delay.h>
#include <linux/rtc.h>
#include <linux/slab.h>
#include <linux/of_device.h>
}
#endif /* CONFIG_STMP3XXX_RTC_WATCHDOG */
-static void stmp3xxx_wait_time(struct stmp3xxx_rtc_data *rtc_data)
+static int stmp3xxx_wait_time(struct stmp3xxx_rtc_data *rtc_data)
{
+ int timeout = 5000; /* 3ms according to i.MX28 Ref Manual */
/*
- * The datasheet doesn't say which way round the
- * NEW_REGS/STALE_REGS bitfields go. In fact it's 0x1=P0,
- * 0x2=P1, .., 0x20=P5, 0x40=ALARM, 0x80=SECONDS
+ * The i.MX28 Applications Processor Reference Manual, Rev. 1, 2010
+ * states:
+ * | The order in which registers are updated is
+ * | Persistent 0, 1, 2, 3, 4, 5, Alarm, Seconds.
+ * | (This list is in bitfield order, from LSB to MSB, as they would
+ * | appear in the STALE_REGS and NEW_REGS bitfields of the HW_RTC_STAT
+ * | register. For example, the Seconds register corresponds to
+ * | STALE_REGS or NEW_REGS containing 0x80.)
*/
- while (readl(rtc_data->io + STMP3XXX_RTC_STAT) &
- (0x80 << STMP3XXX_RTC_STAT_STALE_SHIFT))
- cpu_relax();
+ do {
+ if (!(readl(rtc_data->io + STMP3XXX_RTC_STAT) &
+ (0x80 << STMP3XXX_RTC_STAT_STALE_SHIFT)))
+ return 0;
+ udelay(1);
+ } while (--timeout > 0);
+ return (readl(rtc_data->io + STMP3XXX_RTC_STAT) &
+ (0x80 << STMP3XXX_RTC_STAT_STALE_SHIFT)) ? -ETIME : 0;
}
/* Time read/write */
static int stmp3xxx_rtc_gettime(struct device *dev, struct rtc_time *rtc_tm)
{
+ int ret;
struct stmp3xxx_rtc_data *rtc_data = dev_get_drvdata(dev);
- stmp3xxx_wait_time(rtc_data);
+ ret = stmp3xxx_wait_time(rtc_data);
+ if (ret)
+ return ret;
+
rtc_time_to_tm(readl(rtc_data->io + STMP3XXX_RTC_SECONDS), rtc_tm);
return 0;
}
struct stmp3xxx_rtc_data *rtc_data = dev_get_drvdata(dev);
writel(t, rtc_data->io + STMP3XXX_RTC_SECONDS);
- stmp3xxx_wait_time(rtc_data);
- return 0;
+ return stmp3xxx_wait_time(rtc_data);
}
/* interrupt(s) handler */
server->secmech.md5 = crypto_alloc_shash("md5", 0, 0);
if (IS_ERR(server->secmech.md5)) {
cifs_dbg(VFS, "could not allocate crypto md5\n");
- return PTR_ERR(server->secmech.md5);
+ rc = PTR_ERR(server->secmech.md5);
+ server->secmech.md5 = NULL;
+ return rc;
}
size = sizeof(struct shash_desc) +
crypto_shash_descsize(server->secmech.md5);
server->secmech.sdescmd5 = kmalloc(size, GFP_KERNEL);
if (!server->secmech.sdescmd5) {
- rc = -ENOMEM;
crypto_free_shash(server->secmech.md5);
server->secmech.md5 = NULL;
- return rc;
+ return -ENOMEM;
}
server->secmech.sdescmd5->shash.tfm = server->secmech.md5;
server->secmech.sdescmd5->shash.flags = 0x0;
if (blobptr + attrsize > blobend)
break;
if (type == NTLMSSP_AV_NB_DOMAIN_NAME) {
- if (!attrsize)
+ if (!attrsize || attrsize >= CIFS_MAX_DOMAINNAME_LEN)
break;
if (!ses->domainName) {
ses->domainName =
static int crypto_hmacmd5_alloc(struct TCP_Server_Info *server)
{
+ int rc;
unsigned int size;
/* check if already allocated */
server->secmech.hmacmd5 = crypto_alloc_shash("hmac(md5)", 0, 0);
if (IS_ERR(server->secmech.hmacmd5)) {
cifs_dbg(VFS, "could not allocate crypto hmacmd5\n");
- return PTR_ERR(server->secmech.hmacmd5);
+ rc = PTR_ERR(server->secmech.hmacmd5);
+ server->secmech.hmacmd5 = NULL;
+ return rc;
}
size = sizeof(struct shash_desc) +
goto out_no_root;
}
+ if (cifs_sb_master_tcon(cifs_sb)->nocase)
+ sb->s_d_op = &cifs_ci_dentry_ops;
+ else
+ sb->s_d_op = &cifs_dentry_ops;
+
sb->s_root = d_make_root(inode);
if (!sb->s_root) {
rc = -ENOMEM;
goto out_no_root;
}
- /* do that *after* d_make_root() - we want NULL ->d_op for root here */
- if (cifs_sb_master_tcon(cifs_sb)->nocase)
- sb->s_d_op = &cifs_ci_dentry_ops;
- else
- sb->s_d_op = &cifs_dentry_ops;
-
#ifdef CONFIG_CIFS_NFSD_EXPORT
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM) {
cifs_dbg(FYI, "export ops supported\n");
#define MAX_TREE_SIZE (2 + MAX_SERVER_SIZE + 1 + MAX_SHARE_SIZE + 1)
#define MAX_SERVER_SIZE 15
#define MAX_SHARE_SIZE 80
+#define CIFS_MAX_DOMAINNAME_LEN 256 /* max domain name length */
#define MAX_USERNAME_SIZE 256 /* reasonable maximum for current servers */
#define MAX_PASSWORD_SIZE 512 /* max for windows seems to be 256 wide chars */
void (*generate_signingkey)(struct TCP_Server_Info *server);
int (*calc_signature)(struct smb_rqst *rqst,
struct TCP_Server_Info *server);
+ int (*query_mf_symlink)(const unsigned char *path, char *pbuf,
+ unsigned int *pbytes_read, struct cifs_sb_info *cifs_sb,
+ unsigned int xid);
};
struct smb_version_values {
struct cifs_writedata *cifs_writedata_alloc(unsigned int nr_pages,
work_func_t complete);
void cifs_writedata_release(struct kref *refcount);
-
+int open_query_close_cifs_symlink(const unsigned char *path, char *pbuf,
+ unsigned int *pbytes_read, struct cifs_sb_info *cifs_sb,
+ unsigned int xid);
#endif /* _CIFSPROTO_H */
if (string == NULL)
goto out_nomem;
- if (strnlen(string, 256) == 256) {
+ if (strnlen(string, CIFS_MAX_DOMAINNAME_LEN)
+ == CIFS_MAX_DOMAINNAME_LEN) {
printk(KERN_WARNING "CIFS: domain name too"
" long\n");
goto cifs_parse_mount_err;
#ifdef CONFIG_KEYS
-/* strlen("cifs:a:") + INET6_ADDRSTRLEN + 1 */
-#define CIFSCREDS_DESC_SIZE (7 + INET6_ADDRSTRLEN + 1)
+/* strlen("cifs:a:") + CIFS_MAX_DOMAINNAME_LEN + 1 */
+#define CIFSCREDS_DESC_SIZE (7 + CIFS_MAX_DOMAINNAME_LEN + 1)
/* Populate username and pw fields from keyring if possible */
static int
oflags, &oplock, &cfile->fid.netfid, xid);
if (rc == 0) {
cifs_dbg(FYI, "posix reopen succeeded\n");
+ oparms.reconnect = true;
goto reopen_success;
}
/*
}
int
-CIFSCheckMFSymlink(struct cifs_fattr *fattr,
- const unsigned char *path,
- struct cifs_sb_info *cifs_sb, unsigned int xid)
+open_query_close_cifs_symlink(const unsigned char *path, char *pbuf,
+ unsigned int *pbytes_read, struct cifs_sb_info *cifs_sb,
+ unsigned int xid)
{
int rc;
int oplock = 0;
__u16 netfid = 0;
struct tcon_link *tlink;
- struct cifs_tcon *pTcon;
+ struct cifs_tcon *ptcon;
struct cifs_io_parms io_parms;
- u8 *buf;
- char *pbuf;
- unsigned int bytes_read = 0;
int buf_type = CIFS_NO_BUFFER;
- unsigned int link_len = 0;
FILE_ALL_INFO file_info;
- if (!CIFSCouldBeMFSymlink(fattr))
- /* it's not a symlink */
- return 0;
-
tlink = cifs_sb_tlink(cifs_sb);
if (IS_ERR(tlink))
return PTR_ERR(tlink);
- pTcon = tlink_tcon(tlink);
+ ptcon = tlink_tcon(tlink);
- rc = CIFSSMBOpen(xid, pTcon, path, FILE_OPEN, GENERIC_READ,
+ rc = CIFSSMBOpen(xid, ptcon, path, FILE_OPEN, GENERIC_READ,
CREATE_NOT_DIR, &netfid, &oplock, &file_info,
cifs_sb->local_nls,
cifs_sb->mnt_cifs_flags &
CIFS_MOUNT_MAP_SPECIAL_CHR);
- if (rc != 0)
- goto out;
+ if (rc != 0) {
+ cifs_put_tlink(tlink);
+ return rc;
+ }
if (file_info.EndOfFile != cpu_to_le64(CIFS_MF_SYMLINK_FILE_SIZE)) {
- CIFSSMBClose(xid, pTcon, netfid);
+ CIFSSMBClose(xid, ptcon, netfid);
+ cifs_put_tlink(tlink);
/* it's not a symlink */
- goto out;
+ return rc;
}
- buf = kmalloc(CIFS_MF_SYMLINK_FILE_SIZE, GFP_KERNEL);
- if (!buf) {
- rc = -ENOMEM;
- goto out;
- }
- pbuf = buf;
io_parms.netfid = netfid;
io_parms.pid = current->tgid;
- io_parms.tcon = pTcon;
+ io_parms.tcon = ptcon;
io_parms.offset = 0;
io_parms.length = CIFS_MF_SYMLINK_FILE_SIZE;
- rc = CIFSSMBRead(xid, &io_parms, &bytes_read, &pbuf, &buf_type);
- CIFSSMBClose(xid, pTcon, netfid);
- if (rc != 0) {
- kfree(buf);
+ rc = CIFSSMBRead(xid, &io_parms, pbytes_read, &pbuf, &buf_type);
+ CIFSSMBClose(xid, ptcon, netfid);
+ cifs_put_tlink(tlink);
+ return rc;
+}
+
+
+int
+CIFSCheckMFSymlink(struct cifs_fattr *fattr,
+ const unsigned char *path,
+ struct cifs_sb_info *cifs_sb, unsigned int xid)
+{
+ int rc = 0;
+ u8 *buf = NULL;
+ unsigned int link_len = 0;
+ unsigned int bytes_read = 0;
+ struct cifs_tcon *ptcon;
+
+ if (!CIFSCouldBeMFSymlink(fattr))
+ /* it's not a symlink */
+ return 0;
+
+ buf = kmalloc(CIFS_MF_SYMLINK_FILE_SIZE, GFP_KERNEL);
+ if (!buf) {
+ rc = -ENOMEM;
goto out;
}
+ ptcon = tlink_tcon(cifs_sb_tlink(cifs_sb));
+ if ((ptcon->ses) && (ptcon->ses->server->ops->query_mf_symlink))
+ rc = ptcon->ses->server->ops->query_mf_symlink(path, buf,
+ &bytes_read, cifs_sb, xid);
+ else
+ goto out;
+
+ if (rc != 0)
+ goto out;
+
+ if (bytes_read == 0) /* not a symlink */
+ goto out;
+
rc = CIFSParseMFSymlink(buf, bytes_read, &link_len, NULL);
- kfree(buf);
if (rc == -EINVAL) {
/* it's not a symlink */
rc = 0;
fattr->cf_mode |= S_IFLNK | S_IRWXU | S_IRWXG | S_IRWXO;
fattr->cf_dtype = DT_LNK;
out:
- cifs_put_tlink(tlink);
+ kfree(buf);
return rc;
}
return;
}
+ /*
+ * If we know that the inode will need to be revalidated immediately,
+ * then don't create a new dentry for it. We'll end up doing an on
+ * the wire call either way and this spares us an invalidation.
+ */
+ if (fattr->cf_flags & CIFS_FATTR_NEED_REVAL)
+ return;
+
dentry = d_alloc(parent, name);
if (!dentry)
return;
bytes_ret = 0;
} else
bytes_ret = cifs_strtoUTF16((__le16 *) bcc_ptr, ses->domainName,
- 256, nls_cp);
+ CIFS_MAX_DOMAINNAME_LEN, nls_cp);
bcc_ptr += 2 * bytes_ret;
bcc_ptr += 2; /* account for null terminator */
/* copy domain */
if (ses->domainName != NULL) {
- strncpy(bcc_ptr, ses->domainName, 256);
- bcc_ptr += strnlen(ses->domainName, 256);
+ strncpy(bcc_ptr, ses->domainName, CIFS_MAX_DOMAINNAME_LEN);
+ bcc_ptr += strnlen(ses->domainName, CIFS_MAX_DOMAINNAME_LEN);
} /* else we will send a null domain name
so the server will default to its own domain */
*bcc_ptr = 0;
.mand_lock = cifs_mand_lock,
.mand_unlock_range = cifs_unlock_range,
.push_mand_locks = cifs_push_mandatory_locks,
+ .query_mf_symlink = open_query_close_cifs_symlink,
};
struct smb_version_values smb1_values = {
static int
smb2_crypto_shash_allocate(struct TCP_Server_Info *server)
{
+ int rc;
unsigned int size;
if (server->secmech.sdeschmacsha256 != NULL)
server->secmech.hmacsha256 = crypto_alloc_shash("hmac(sha256)", 0, 0);
if (IS_ERR(server->secmech.hmacsha256)) {
cifs_dbg(VFS, "could not allocate crypto hmacsha256\n");
- return PTR_ERR(server->secmech.hmacsha256);
+ rc = PTR_ERR(server->secmech.hmacsha256);
+ server->secmech.hmacsha256 = NULL;
+ return rc;
}
size = sizeof(struct shash_desc) +
server->secmech.sdeschmacsha256 = NULL;
crypto_free_shash(server->secmech.hmacsha256);
server->secmech.hmacsha256 = NULL;
- return PTR_ERR(server->secmech.cmacaes);
+ rc = PTR_ERR(server->secmech.cmacaes);
+ server->secmech.cmacaes = NULL;
+ return rc;
}
size = sizeof(struct shash_desc) +
return -ENOMEM;
lru_add_drain();
- tlb_gather_mmu(&tlb, mm, 0);
+ tlb_gather_mmu(&tlb, mm, old_start, old_end);
if (new_end > old_start) {
/*
* when the old and new regions overlap clear from new_end.
free_pgd_range(&tlb, old_start, old_end, new_end,
vma->vm_next ? vma->vm_next->vm_start : USER_PGTABLES_CEILING);
}
- tlb_finish_mmu(&tlb, new_end, old_end);
+ tlb_finish_mmu(&tlb, old_start, old_end);
/*
* Shrink the vma to just the new range. Always succeeds.
memswap(ei1->i_data, ei2->i_data, sizeof(ei1->i_data));
memswap(&ei1->i_flags, &ei2->i_flags, sizeof(ei1->i_flags));
memswap(&ei1->i_disksize, &ei2->i_disksize, sizeof(ei1->i_disksize));
- memswap(&ei1->i_es_tree, &ei2->i_es_tree, sizeof(ei1->i_es_tree));
- memswap(&ei1->i_es_lru_nr, &ei2->i_es_lru_nr, sizeof(ei1->i_es_lru_nr));
+ ext4_es_remove_extent(inode1, 0, EXT_MAX_BLOCKS);
+ ext4_es_remove_extent(inode2, 0, EXT_MAX_BLOCKS);
+ ext4_es_lru_del(inode1);
+ ext4_es_lru_del(inode2);
isize = i_size_read(inode1);
i_size_write(inode1, i_size_read(inode2));
{Opt_delalloc, EXT4_MOUNT_DELALLOC,
MOPT_EXT4_ONLY | MOPT_SET | MOPT_EXPLICIT},
{Opt_nodelalloc, EXT4_MOUNT_DELALLOC,
- MOPT_EXT4_ONLY | MOPT_CLEAR | MOPT_EXPLICIT},
+ MOPT_EXT4_ONLY | MOPT_CLEAR},
{Opt_journal_checksum, EXT4_MOUNT_JOURNAL_CHECKSUM,
MOPT_EXT4_ONLY | MOPT_SET},
{Opt_journal_async_commit, (EXT4_MOUNT_JOURNAL_ASYNC_COMMIT |
}
if (test_opt(sb, DIOREAD_NOLOCK)) {
ext4_msg(sb, KERN_ERR, "can't mount with "
- "both data=journal and delalloc");
+ "both data=journal and dioread_nolock");
goto failed_mount;
}
if (test_opt(sb, DELALLOC))
goto restore_opts;
}
+ if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) {
+ if (test_opt2(sb, EXPLICIT_DELALLOC)) {
+ ext4_msg(sb, KERN_ERR, "can't mount with "
+ "both data=journal and delalloc");
+ err = -EINVAL;
+ goto restore_opts;
+ }
+ if (test_opt(sb, DIOREAD_NOLOCK)) {
+ ext4_msg(sb, KERN_ERR, "can't mount with "
+ "both data=journal and dioread_nolock");
+ err = -EINVAL;
+ goto restore_opts;
+ }
+ }
+
if (sbi->s_mount_flags & EXT4_MF_FS_ABORTED)
ext4_abort(sb, "Abort forced by user");
return inode;
}
+/*
+ * Hugetlbfs is not reclaimable; therefore its i_mmap_mutex will never
+ * be taken from reclaim -- unlike regular filesystems. This needs an
+ * annotation because huge_pmd_share() does an allocation under
+ * i_mmap_mutex.
+ */
+struct lock_class_key hugetlbfs_i_mmap_mutex_key;
+
static struct inode *hugetlbfs_get_inode(struct super_block *sb,
struct inode *dir,
umode_t mode, dev_t dev)
struct hugetlbfs_inode_info *info;
inode->i_ino = get_next_ino();
inode_init_owner(inode, dir, mode);
+ lockdep_set_class(&inode->i_mapping->i_mmap_mutex,
+ &hugetlbfs_i_mmap_mutex_key);
inode->i_mapping->a_ops = &hugetlbfs_aops;
inode->i_mapping->backing_dev_info =&hugetlbfs_backing_dev_info;
inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
goto out;
} else if (ret == 1) {
clusters_need = wc->w_clen;
- ret = ocfs2_refcount_cow(inode, filp, di_bh,
+ ret = ocfs2_refcount_cow(inode, di_bh,
wc->w_cpos, wc->w_clen, UINT_MAX);
if (ret) {
mlog_errno(ret);
{
int ret;
struct ocfs2_empty_dir_priv priv = {
- .ctx.actor = ocfs2_empty_dir_filldir
+ .ctx.actor = ocfs2_empty_dir_filldir,
};
- memset(&priv, 0, sizeof(priv));
-
if (ocfs2_dir_indexed(inode)) {
ret = ocfs2_empty_dir_dx(inode, &priv);
if (ret)
if (!(ext_flags & OCFS2_EXT_REFCOUNTED))
goto out;
- return ocfs2_refcount_cow(inode, NULL, fe_bh, cpos, 1, cpos+1);
+ return ocfs2_refcount_cow(inode, fe_bh, cpos, 1, cpos+1);
out:
return status;
zero_clusters = last_cpos - zero_cpos;
if (needs_cow) {
- rc = ocfs2_refcount_cow(inode, NULL, di_bh, zero_cpos,
+ rc = ocfs2_refcount_cow(inode, di_bh, zero_cpos,
zero_clusters, UINT_MAX);
if (rc) {
mlog_errno(rc);
*meta_level = 1;
- ret = ocfs2_refcount_cow(inode, file, di_bh, cpos, clusters, UINT_MAX);
+ ret = ocfs2_refcount_cow(inode, di_bh, cpos, clusters, UINT_MAX);
if (ret)
mlog_errno(ret);
out:
extent_blocks = 1 + 1 + le16_to_cpu(root_el->l_tree_depth);
return bitmap_blocks + sysfile_bitmap_blocks + extent_blocks +
- ocfs2_quota_trans_credits(sb) + bits_wanted;
+ ocfs2_quota_trans_credits(sb);
}
static inline int ocfs2_calc_symlink_credits(struct super_block *sb)
u64 ino = ocfs2_metadata_cache_owner(context->et.et_ci);
u64 old_blkno = ocfs2_clusters_to_blocks(inode->i_sb, p_cpos);
- ret = ocfs2_duplicate_clusters_by_page(handle, context->file, cpos,
+ ret = ocfs2_duplicate_clusters_by_page(handle, inode, cpos,
p_cpos, new_p_cpos, len);
if (ret) {
mlog_errno(ret);
struct ocfs2_cow_context {
struct inode *inode;
- struct file *file;
u32 cow_start;
u32 cow_len;
struct ocfs2_extent_tree data_et;
u32 *num_clusters,
unsigned int *extent_flags);
int (*cow_duplicate_clusters)(handle_t *handle,
- struct file *file,
+ struct inode *inode,
u32 cpos, u32 old_cluster,
u32 new_cluster, u32 new_len);
};
}
int ocfs2_duplicate_clusters_by_page(handle_t *handle,
- struct file *file,
+ struct inode *inode,
u32 cpos, u32 old_cluster,
u32 new_cluster, u32 new_len)
{
int ret = 0, partial;
- struct inode *inode = file_inode(file);
- struct ocfs2_caching_info *ci = INODE_CACHE(inode);
- struct super_block *sb = ocfs2_metadata_cache_get_super(ci);
+ struct super_block *sb = inode->i_sb;
u64 new_block = ocfs2_clusters_to_blocks(sb, new_cluster);
struct page *page;
pgoff_t page_index;
if (PAGE_CACHE_SIZE <= OCFS2_SB(sb)->s_clustersize)
BUG_ON(PageDirty(page));
- if (PageReadahead(page)) {
- page_cache_async_readahead(mapping,
- &file->f_ra, file,
- page, page_index,
- readahead_pages);
- }
-
if (!PageUptodate(page)) {
ret = block_read_full_page(page, ocfs2_get_block);
if (ret) {
}
}
- ocfs2_map_and_dirty_page(inode, handle, from, to,
+ ocfs2_map_and_dirty_page(inode,
+ handle, from, to,
page, 0, &new_block);
mark_page_accessed(page);
unlock:
}
int ocfs2_duplicate_clusters_by_jbd(handle_t *handle,
- struct file *file,
+ struct inode *inode,
u32 cpos, u32 old_cluster,
u32 new_cluster, u32 new_len)
{
int ret = 0;
- struct inode *inode = file_inode(file);
struct super_block *sb = inode->i_sb;
struct ocfs2_caching_info *ci = INODE_CACHE(inode);
int i, blocks = ocfs2_clusters_to_blocks(sb, new_len);
/*If the old clusters is unwritten, no need to duplicate. */
if (!(ext_flags & OCFS2_EXT_UNWRITTEN)) {
- ret = context->cow_duplicate_clusters(handle, context->file,
+ ret = context->cow_duplicate_clusters(handle, context->inode,
cpos, old, new, len);
if (ret) {
mlog_errno(ret);
return ret;
}
-static void ocfs2_readahead_for_cow(struct inode *inode,
- struct file *file,
- u32 start, u32 len)
-{
- struct address_space *mapping;
- pgoff_t index;
- unsigned long num_pages;
- int cs_bits = OCFS2_SB(inode->i_sb)->s_clustersize_bits;
-
- if (!file)
- return;
-
- mapping = file->f_mapping;
- num_pages = (len << cs_bits) >> PAGE_CACHE_SHIFT;
- if (!num_pages)
- num_pages = 1;
-
- index = ((loff_t)start << cs_bits) >> PAGE_CACHE_SHIFT;
- page_cache_sync_readahead(mapping, &file->f_ra, file,
- index, num_pages);
-}
-
/*
* Starting at cpos, try to CoW write_len clusters. Don't CoW
* past max_cpos. This will stop when it runs into a hole or an
* unrefcounted extent.
*/
static int ocfs2_refcount_cow_hunk(struct inode *inode,
- struct file *file,
struct buffer_head *di_bh,
u32 cpos, u32 write_len, u32 max_cpos)
{
BUG_ON(cow_len == 0);
- ocfs2_readahead_for_cow(inode, file, cow_start, cow_len);
-
context = kzalloc(sizeof(struct ocfs2_cow_context), GFP_NOFS);
if (!context) {
ret = -ENOMEM;
context->ref_root_bh = ref_root_bh;
context->cow_duplicate_clusters = ocfs2_duplicate_clusters_by_page;
context->get_clusters = ocfs2_di_get_clusters;
- context->file = file;
ocfs2_init_dinode_extent_tree(&context->data_et,
INODE_CACHE(inode), di_bh);
* clusters between cpos and cpos+write_len are safe to modify.
*/
int ocfs2_refcount_cow(struct inode *inode,
- struct file *file,
struct buffer_head *di_bh,
u32 cpos, u32 write_len, u32 max_cpos)
{
num_clusters = write_len;
if (ext_flags & OCFS2_EXT_REFCOUNTED) {
- ret = ocfs2_refcount_cow_hunk(inode, file, di_bh, cpos,
+ ret = ocfs2_refcount_cow_hunk(inode, di_bh, cpos,
num_clusters, max_cpos);
if (ret) {
mlog_errno(ret);
int *credits,
int *ref_blocks);
int ocfs2_refcount_cow(struct inode *inode,
- struct file *filep, struct buffer_head *di_bh,
+ struct buffer_head *di_bh,
u32 cpos, u32 write_len, u32 max_cpos);
typedef int (ocfs2_post_refcount_func)(struct inode *inode,
u32 cpos, u32 write_len,
struct ocfs2_post_refcount *post);
int ocfs2_duplicate_clusters_by_page(handle_t *handle,
- struct file *file,
+ struct inode *inode,
u32 cpos, u32 old_cluster,
u32 new_cluster, u32 new_len);
int ocfs2_duplicate_clusters_by_jbd(handle_t *handle,
- struct file *file,
+ struct inode *inode,
u32 cpos, u32 old_cluster,
u32 new_cluster, u32 new_len);
int ocfs2_cow_sync_writeback(struct super_block *sb,
* of how soft-dirty works.
*/
pte_t ptent = *pte;
- ptent = pte_wrprotect(ptent);
- ptent = pte_clear_flags(ptent, _PAGE_SOFT_DIRTY);
+
+ if (pte_present(ptent)) {
+ ptent = pte_wrprotect(ptent);
+ ptent = pte_clear_flags(ptent, _PAGE_SOFT_DIRTY);
+ } else if (is_swap_pte(ptent)) {
+ ptent = pte_swp_clear_soft_dirty(ptent);
+ } else if (pte_file(ptent)) {
+ ptent = pte_file_clear_soft_dirty(ptent);
+ }
+
set_pte_at(vma->vm_mm, addr, pte, ptent);
#endif
}
pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
for (; addr != end; pte++, addr += PAGE_SIZE) {
ptent = *pte;
- if (!pte_present(ptent))
- continue;
if (cp->type == CLEAR_REFS_SOFT_DIRTY) {
clear_soft_dirty(vma, addr, pte);
continue;
}
+ if (!pte_present(ptent))
+ continue;
+
page = vm_normal_page(vma, addr, ptent);
if (!page)
continue;
} pagemap_entry_t;
struct pagemapread {
- int pos, len;
+ int pos, len; /* units: PM_ENTRY_BYTES, not bytes */
pagemap_entry_t *buffer;
bool v2;
};
#define PAGEMAP_WALK_SIZE (PMD_SIZE)
#define PAGEMAP_WALK_MASK (PMD_MASK)
-#define PM_ENTRY_BYTES sizeof(u64)
+#define PM_ENTRY_BYTES sizeof(pagemap_entry_t)
#define PM_STATUS_BITS 3
#define PM_STATUS_OFFSET (64 - PM_STATUS_BITS)
#define PM_STATUS_MASK (((1LL << PM_STATUS_BITS) - 1) << PM_STATUS_OFFSET)
flags = PM_PRESENT;
page = vm_normal_page(vma, addr, pte);
} else if (is_swap_pte(pte)) {
- swp_entry_t entry = pte_to_swp_entry(pte);
-
+ swp_entry_t entry;
+ if (pte_swp_soft_dirty(pte))
+ flags2 |= __PM_SOFT_DIRTY;
+ entry = pte_to_swp_entry(pte);
frame = swp_type(entry) |
(swp_offset(entry) << MAX_SWAPFILES_SHIFT);
flags = PM_SWAP;
goto out_task;
pm.v2 = soft_dirty_cleared;
- pm.len = PM_ENTRY_BYTES * (PAGEMAP_WALK_SIZE >> PAGE_SHIFT);
- pm.buffer = kmalloc(pm.len, GFP_TEMPORARY);
+ pm.len = (PAGEMAP_WALK_SIZE >> PAGE_SHIFT);
+ pm.buffer = kmalloc(pm.len * PM_ENTRY_BYTES, GFP_TEMPORARY);
ret = -ENOMEM;
if (!pm.buffer)
goto out_task;
{
return pmd;
}
+
+static inline pte_t pte_swp_mksoft_dirty(pte_t pte)
+{
+ return pte;
+}
+
+static inline int pte_swp_soft_dirty(pte_t pte)
+{
+ return 0;
+}
+
+static inline pte_t pte_swp_clear_soft_dirty(pte_t pte)
+{
+ return pte;
+}
+
+static inline pte_t pte_file_clear_soft_dirty(pte_t pte)
+{
+ return pte;
+}
+
+static inline pte_t pte_file_mksoft_dirty(pte_t pte)
+{
+ return pte;
+}
+
+static inline int pte_file_soft_dirty(pte_t pte)
+{
+ return 0;
+}
#endif
#ifndef __HAVE_PFNMAP_TRACKING
#define HAVE_GENERIC_MMU_GATHER
-void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, bool fullmm);
+void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long start, unsigned long end);
void tlb_flush_mmu(struct mmu_gather *tlb);
void tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start,
unsigned long end);
__be16 max_desc_sz_rq;
u8 rsvd21[2];
__be16 max_desc_sz_sq_dc;
- u8 rsvd22[4];
- __be16 max_qp_mcg;
- u8 rsvd23;
+ __be32 max_qp_mcg;
+ u8 rsvd22[3];
u8 log_max_mcg;
- u8 rsvd24;
+ u8 rsvd23;
u8 log_max_pd;
- u8 rsvd25;
+ u8 rsvd24;
u8 log_max_xrcd;
- u8 rsvd26[42];
+ u8 rsvd25[42];
__be16 log_uar_page_sz;
- u8 rsvd27[28];
+ u8 rsvd26[28];
u8 log_msx_atomic_size_qp;
- u8 rsvd28[2];
+ u8 rsvd27[2];
u8 log_msx_atomic_size_dc;
- u8 rsvd29[76];
+ u8 rsvd28[76];
};
struct mlx5_eqe_page_req {
u8 rsvd0[2];
__be16 func_id;
- u8 rsvd1[2];
- __be16 num_pages;
- __be32 rsvd2[5];
+ __be32 num_pages;
+ __be32 rsvd1[5];
};
union ev_data {
u32 reserved_lkey;
u8 local_ca_ack_delay;
u8 log_max_mcg;
- u16 max_qp_mcg;
+ u32 max_qp_mcg;
int min_page_sz;
};
int mlx5_pagealloc_start(struct mlx5_core_dev *dev);
void mlx5_pagealloc_stop(struct mlx5_core_dev *dev);
void mlx5_core_req_pages_handler(struct mlx5_core_dev *dev, u16 func_id,
- s16 npages);
+ s32 npages);
int mlx5_satisfy_startup_pages(struct mlx5_core_dev *dev, int boot);
int mlx5_reclaim_startup_pages(struct mlx5_core_dev *dev);
void mlx5_register_debugfs(void);
int mlx5_db_alloc(struct mlx5_core_dev *dev, struct mlx5_db *db);
void mlx5_db_free(struct mlx5_core_dev *dev, struct mlx5_db *db);
-typedef void (*health_handler_t)(struct pci_dev *pdev, struct health_buffer __iomem *buf, int size);
-int mlx5_register_health_report_handler(health_handler_t handler);
-void mlx5_unregister_health_report_handler(void);
const char *mlx5_command_str(int command);
int mlx5_cmdif_debugfs_init(struct mlx5_core_dev *dev);
void mlx5_cmdif_debugfs_cleanup(struct mlx5_core_dev *dev);
struct user_namespace;
#ifdef CONFIG_MMU
+extern unsigned long mmap_legacy_base(void);
extern void arch_pick_mmap_layout(struct mm_struct *mm);
extern unsigned long
arch_get_unmapped_area(struct file *, unsigned long, unsigned long,
* Test if a process is not yet dead (at most zombie state)
* If pid_alive fails, then pointers within the task structure
* can be stale and must not be dereferenced.
+ *
+ * Return: 1 if the process is alive. 0 otherwise.
*/
static inline int pid_alive(struct task_struct *p)
{
* @tsk: Task structure to be checked.
*
* Check if a task structure is the first user space task the kernel created.
+ *
+ * Return: 1 if the task structure is init. 0 otherwise.
*/
static inline int is_global_init(struct task_struct *tsk)
{
/**
* is_idle_task - is the specified task an idle task?
* @p: the task in question.
+ *
+ * Return: 1 if @p is an idle task. 0 otherwise.
*/
static inline bool is_idle_task(const struct task_struct *p)
{
#endif /*arch_spin_is_contended*/
#endif
-/* The lock does not imply full memory barrier. */
-#ifndef ARCH_HAS_SMP_MB_AFTER_LOCK
-static inline void smp_mb__after_lock(void) { smp_mb(); }
+/*
+ * Despite its name it doesn't necessarily has to be a full barrier.
+ * It should only guarantee that a STORE before the critical section
+ * can not be reordered with a LOAD inside this section.
+ * spin_lock() is the one-way barrier, this LOAD can not escape out
+ * of the region. So the default implementation simply ensures that
+ * a STORE can not move into the critical section, smp_wmb() should
+ * serialize it with another STORE done by spin_lock().
+ */
+#ifndef smp_mb__before_spinlock
+#define smp_mb__before_spinlock() smp_wmb()
#endif
/**
swp_entry_t arch_entry;
BUG_ON(pte_file(pte));
+ if (pte_swp_soft_dirty(pte))
+ pte = pte_swp_clear_soft_dirty(pte);
arch_entry = __pte_to_swp_entry(pte);
return swp_entry(__swp_type(arch_entry), __swp_offset(arch_entry));
}
asmlinkage long sys_clone(unsigned long, unsigned long, int __user *, int,
int __user *);
#else
+#ifdef CONFIG_CLONE_BACKWARDS3
+asmlinkage long sys_clone(unsigned long, unsigned long, int, int __user *,
+ int __user *, int);
+#else
asmlinkage long sys_clone(unsigned long, unsigned long, int __user *,
int __user *, int);
#endif
+#endif
asmlinkage long sys_execve(const char __user *filename,
const char __user *const __user *argv,
if (rc > 0)
/* local bh are disabled so it is ok to use _BH */
NET_ADD_STATS_BH(sock_net(sk),
- LINUX_MIB_LOWLATENCYRXPACKETS, rc);
+ LINUX_MIB_BUSYPOLLRXPACKETS, rc);
} while (!nonblock && skb_queue_empty(&sk->sk_receive_queue) &&
!need_resched() && !busy_loop_timeout(end_time));
return false;
}
-static inline bool sk_busy_poll(struct sock *sk, int nonblock)
-{
- return false;
-}
-
static inline void skb_mark_napi_id(struct sk_buff *skb,
struct napi_struct *napi)
{
return INET_ECN_encapsulate(tos, inner);
}
-static inline void tunnel_ip_select_ident(struct sk_buff *skb,
- const struct iphdr *old_iph,
- struct dst_entry *dst)
-{
- struct iphdr *iph = ip_hdr(skb);
-
- /* Use inner packet iph-id if possible. */
- if (skb->protocol == htons(ETH_P_IP) && old_iph->id)
- iph->id = old_iph->id;
- else
- __ip_select_ident(iph, dst,
- (skb_shinfo(skb)->gso_segs ?: 1) - 1);
-}
-
int iptunnel_pull_header(struct sk_buff *skb, int hdr_len, __be16 inner_proto);
int iptunnel_xmit(struct net *net, struct rtable *rt,
struct sk_buff *skb,
u64 rate_bytes_ps; /* bytes per second */
u32 mult;
u16 overhead;
+ u8 linklayer;
u8 shift;
};
static inline u64 psched_l2t_ns(const struct psched_ratecfg *r,
unsigned int len)
{
- return ((u64)(len + r->overhead) * r->mult) >> r->shift;
+ len += r->overhead;
+
+ if (unlikely(r->linklayer == TC_LINKLAYER_ATM))
+ return ((u64)(DIV_ROUND_UP(len,48)*53) * r->mult) >> r->shift;
+
+ return ((u64)len * r->mult) >> r->shift;
}
extern void psched_ratecfg_precompute(struct psched_ratecfg *r, const struct tc_ratespec *conf);
memset(res, 0, sizeof(*res));
res->rate = r->rate_bytes_ps;
res->overhead = r->overhead;
+ res->linklayer = (r->linklayer & TC_LINKLAYER_MASK);
}
#endif
#define TC_H_ROOT (0xFFFFFFFFU)
#define TC_H_INGRESS (0xFFFFFFF1U)
+/* Need to corrospond to iproute2 tc/tc_core.h "enum link_layer" */
+enum tc_link_layer {
+ TC_LINKLAYER_UNAWARE, /* Indicate unaware old iproute2 util */
+ TC_LINKLAYER_ETHERNET,
+ TC_LINKLAYER_ATM,
+};
+#define TC_LINKLAYER_MASK 0x0F /* limit use to lower 4 bits */
+
struct tc_ratespec {
unsigned char cell_log;
- unsigned char __reserved;
+ __u8 linklayer; /* lower 4 bits */
unsigned short overhead;
short cell_align;
unsigned short mpu;
LINUX_MIB_TCPFASTOPENLISTENOVERFLOW, /* TCPFastOpenListenOverflow */
LINUX_MIB_TCPFASTOPENCOOKIEREQD, /* TCPFastOpenCookieReqd */
LINUX_MIB_TCPSPURIOUS_RTX_HOSTQUEUES, /* TCPSpuriousRtxHostQueues */
- LINUX_MIB_LOWLATENCYRXPACKETS, /* LowLatencyRxPackets */
+ LINUX_MIB_BUSYPOLLRXPACKETS, /* BusyPollRxPackets */
__LINUX_MIB_MAX
};
int __user *, parent_tidptr,
int __user *, child_tidptr,
int, tls_val)
+#elif defined(CONFIG_CLONE_BACKWARDS3)
+SYSCALL_DEFINE6(clone, unsigned long, clone_flags, unsigned long, newsp,
+ int, stack_size,
+ int __user *, parent_tidptr,
+ int __user *, child_tidptr,
+ int, tls_val)
#else
SYSCALL_DEFINE5(clone, unsigned long, clone_flags, unsigned long, newsp,
int __user *, parent_tidptr,
might_sleep();
ret = __mutex_lock_common(&lock->base, TASK_UNINTERRUPTIBLE,
0, &ctx->dep_map, _RET_IP_, ctx);
- if (!ret && ctx->acquired > 0)
+ if (!ret && ctx->acquired > 1)
return ww_mutex_deadlock_injection(lock, ctx);
return ret;
ret = __mutex_lock_common(&lock->base, TASK_INTERRUPTIBLE,
0, &ctx->dep_map, _RET_IP_, ctx);
- if (!ret && ctx->acquired > 0)
+ if (!ret && ctx->acquired > 1)
return ww_mutex_deadlock_injection(lock, ctx);
return ret;
/**
* task_curr - is this task currently executing on a CPU?
* @p: the task in question.
+ *
+ * Return: 1 if the task is currently executing. 0 otherwise.
*/
inline int task_curr(const struct task_struct *p)
{
* the simpler "current->state = TASK_RUNNING" to mark yourself
* runnable without the overhead of this.
*
- * Returns %true if @p was woken up, %false if it was already running
+ * Return: %true if @p was woken up, %false if it was already running.
* or @state didn't match @p's state.
*/
static int
unsigned long flags;
int cpu, success = 0;
- smp_wmb();
+ /*
+ * If we are going to wake up a thread waiting for CONDITION we
+ * need to ensure that CONDITION=1 done by the caller can not be
+ * reordered with p->state check below. This pairs with mb() in
+ * set_current_state() the waiting thread does.
+ */
+ smp_mb__before_spinlock();
raw_spin_lock_irqsave(&p->pi_lock, flags);
if (!(p->state & state))
goto out;
* @p: The process to be woken up.
*
* Attempt to wake up the nominated process and move it to the set of runnable
- * processes. Returns 1 if the process was woken up, 0 if it was already
- * running.
+ * processes.
+ *
+ * Return: 1 if the process was woken up, 0 if it was already running.
*
* It may be assumed that this function implies a write memory barrier before
* changing the task state if and only if any tasks are woken up.
* This makes sure that uptime, CFS vruntime, load
* balancing, etc... continue to move forward, even
* with a very low granularity.
+ *
+ * Return: Maximum deferment in nanoseconds.
*/
u64 scheduler_tick_max_deferment(void)
{
if (sched_feat(HRTICK))
hrtick_clear(rq);
+ /*
+ * Make sure that signal_pending_state()->signal_pending() below
+ * can't be reordered with __set_current_state(TASK_INTERRUPTIBLE)
+ * done by the caller to avoid the race with signal_wake_up().
+ */
+ smp_mb__before_spinlock();
raw_spin_lock_irq(&rq->lock);
switch_count = &prev->nivcsw;
* specified timeout to expire. The timeout is in jiffies. It is not
* interruptible.
*
- * The return value is 0 if timed out, and positive (at least 1, or number of
- * jiffies left till timeout) if completed.
+ * Return: 0 if timed out, and positive (at least 1, or number of jiffies left
+ * till timeout) if completed.
*/
unsigned long __sched
wait_for_completion_timeout(struct completion *x, unsigned long timeout)
* specified timeout to expire. The timeout is in jiffies. It is not
* interruptible. The caller is accounted as waiting for IO.
*
- * The return value is 0 if timed out, and positive (at least 1, or number of
- * jiffies left till timeout) if completed.
+ * Return: 0 if timed out, and positive (at least 1, or number of jiffies left
+ * till timeout) if completed.
*/
unsigned long __sched
wait_for_completion_io_timeout(struct completion *x, unsigned long timeout)
* This waits for completion of a specific task to be signaled. It is
* interruptible.
*
- * The return value is -ERESTARTSYS if interrupted, 0 if completed.
+ * Return: -ERESTARTSYS if interrupted, 0 if completed.
*/
int __sched wait_for_completion_interruptible(struct completion *x)
{
* This waits for either a completion of a specific task to be signaled or for a
* specified timeout to expire. It is interruptible. The timeout is in jiffies.
*
- * The return value is -ERESTARTSYS if interrupted, 0 if timed out,
- * positive (at least 1, or number of jiffies left till timeout) if completed.
+ * Return: -ERESTARTSYS if interrupted, 0 if timed out, positive (at least 1,
+ * or number of jiffies left till timeout) if completed.
*/
long __sched
wait_for_completion_interruptible_timeout(struct completion *x,
* This waits to be signaled for completion of a specific task. It can be
* interrupted by a kill signal.
*
- * The return value is -ERESTARTSYS if interrupted, 0 if completed.
+ * Return: -ERESTARTSYS if interrupted, 0 if completed.
*/
int __sched wait_for_completion_killable(struct completion *x)
{
* signaled or for a specified timeout to expire. It can be
* interrupted by a kill signal. The timeout is in jiffies.
*
- * The return value is -ERESTARTSYS if interrupted, 0 if timed out,
- * positive (at least 1, or number of jiffies left till timeout) if completed.
+ * Return: -ERESTARTSYS if interrupted, 0 if timed out, positive (at least 1,
+ * or number of jiffies left till timeout) if completed.
*/
long __sched
wait_for_completion_killable_timeout(struct completion *x,
* try_wait_for_completion - try to decrement a completion without blocking
* @x: completion structure
*
- * Returns: 0 if a decrement cannot be done without blocking
+ * Return: 0 if a decrement cannot be done without blocking
* 1 if a decrement succeeded.
*
* If a completion is being used as a counting completion,
* completion_done - Test to see if a completion has any waiters
* @x: completion structure
*
- * Returns: 0 if there are waiters (wait_for_completion() in progress)
+ * Return: 0 if there are waiters (wait_for_completion() in progress)
* 1 if there are no waiters.
*
*/
* task_prio - return the priority value of a given task.
* @p: the task in question.
*
- * This is the priority value as seen by users in /proc.
+ * Return: The priority value as seen by users in /proc.
* RT tasks are offset by -200. Normal tasks are centered
* around 0, value goes from -16 to +15.
*/
/**
* task_nice - return the nice value of a given task.
* @p: the task in question.
+ *
+ * Return: The nice value [ -20 ... 0 ... 19 ].
*/
int task_nice(const struct task_struct *p)
{
/**
* idle_cpu - is a given cpu idle currently?
* @cpu: the processor in question.
+ *
+ * Return: 1 if the CPU is currently idle. 0 otherwise.
*/
int idle_cpu(int cpu)
{
/**
* idle_task - return the idle task for a given cpu.
* @cpu: the processor in question.
+ *
+ * Return: The idle task for the cpu @cpu.
*/
struct task_struct *idle_task(int cpu)
{
/**
* find_process_by_pid - find a process with a matching PID value.
* @pid: the pid in question.
+ *
+ * The task of @pid, if found. %NULL otherwise.
*/
static struct task_struct *find_process_by_pid(pid_t pid)
{
* @policy: new policy.
* @param: structure containing the new RT priority.
*
+ * Return: 0 on success. An error code otherwise.
+ *
* NOTE that the task may be already dead.
*/
int sched_setscheduler(struct task_struct *p, int policy,
* current context has permission. For example, this is needed in
* stop_machine(): we create temporary high priority worker threads,
* but our caller might not have that capability.
+ *
+ * Return: 0 on success. An error code otherwise.
*/
int sched_setscheduler_nocheck(struct task_struct *p, int policy,
const struct sched_param *param)
* @pid: the pid in question.
* @policy: new policy.
* @param: structure containing the new RT priority.
+ *
+ * Return: 0 on success. An error code otherwise.
*/
SYSCALL_DEFINE3(sched_setscheduler, pid_t, pid, int, policy,
struct sched_param __user *, param)
* sys_sched_setparam - set/change the RT priority of a thread
* @pid: the pid in question.
* @param: structure containing the new RT priority.
+ *
+ * Return: 0 on success. An error code otherwise.
*/
SYSCALL_DEFINE2(sched_setparam, pid_t, pid, struct sched_param __user *, param)
{
/**
* sys_sched_getscheduler - get the policy (scheduling class) of a thread
* @pid: the pid in question.
+ *
+ * Return: On success, the policy of the thread. Otherwise, a negative error
+ * code.
*/
SYSCALL_DEFINE1(sched_getscheduler, pid_t, pid)
{
* sys_sched_getparam - get the RT priority of a thread
* @pid: the pid in question.
* @param: structure containing the RT priority.
+ *
+ * Return: On success, 0 and the RT priority is in @param. Otherwise, an error
+ * code.
*/
SYSCALL_DEFINE2(sched_getparam, pid_t, pid, struct sched_param __user *, param)
{
* @pid: pid of the process
* @len: length in bytes of the bitmask pointed to by user_mask_ptr
* @user_mask_ptr: user-space pointer to the new cpu mask
+ *
+ * Return: 0 on success. An error code otherwise.
*/
SYSCALL_DEFINE3(sched_setaffinity, pid_t, pid, unsigned int, len,
unsigned long __user *, user_mask_ptr)
* @pid: pid of the process
* @len: length in bytes of the bitmask pointed to by user_mask_ptr
* @user_mask_ptr: user-space pointer to hold the current cpu mask
+ *
+ * Return: 0 on success. An error code otherwise.
*/
SYSCALL_DEFINE3(sched_getaffinity, pid_t, pid, unsigned int, len,
unsigned long __user *, user_mask_ptr)
*
* This function yields the current CPU to other tasks. If there are no
* other threads running on this CPU then this function will return.
+ *
+ * Return: 0.
*/
SYSCALL_DEFINE0(sched_yield)
{
* It's the caller's job to ensure that the target task struct
* can't go away on us before we can do any checks.
*
- * Returns:
+ * Return:
* true (>0) if we indeed boosted the target task.
* false (0) if we failed to boost the target.
* -ESRCH if there's no task to yield to.
* sys_sched_get_priority_max - return maximum RT priority.
* @policy: scheduling class.
*
- * this syscall returns the maximum rt_priority that can be used
- * by a given scheduling class.
+ * Return: On success, this syscall returns the maximum
+ * rt_priority that can be used by a given scheduling class.
+ * On failure, a negative error code is returned.
*/
SYSCALL_DEFINE1(sched_get_priority_max, int, policy)
{
* sys_sched_get_priority_min - return minimum RT priority.
* @policy: scheduling class.
*
- * this syscall returns the minimum rt_priority that can be used
- * by a given scheduling class.
+ * Return: On success, this syscall returns the minimum
+ * rt_priority that can be used by a given scheduling class.
+ * On failure, a negative error code is returned.
*/
SYSCALL_DEFINE1(sched_get_priority_min, int, policy)
{
*
* this syscall writes the default timeslice value of a given process
* into the user-space timespec buffer. A value of '0' means infinity.
+ *
+ * Return: On success, 0 and the timeslice is in @interval. Otherwise,
+ * an error code.
*/
SYSCALL_DEFINE2(sched_rr_get_interval, pid_t, pid,
struct timespec __user *, interval)
* @cpu: the processor in question.
*
* ONLY VALID WHEN THE WHOLE SYSTEM IS STOPPED!
+ *
+ * Return: The current task for @cpu.
*/
struct task_struct *curr_task(int cpu)
{
* any discrepancies created by racing against the uncertainty of the current
* priority configuration.
*
- * Returns: (int)bool - CPUs were found
+ * Return: (int)bool - CPUs were found
*/
int cpupri_find(struct cpupri *cp, struct task_struct *p,
struct cpumask *lowest_mask)
* cpupri_init - initialize the cpupri structure
* @cp: The cpupri context
*
- * Returns: -ENOMEM if memory fails.
+ * Return: -ENOMEM on memory allocation failure.
*/
int cpupri_init(struct cpupri *cp)
{
*/
update_entity_load_avg(curr, 1);
update_cfs_rq_blocked_load(cfs_rq, 1);
+ update_cfs_shares(cfs_rq);
#ifdef CONFIG_SCHED_HRTICK
/*
* get_sd_load_idx - Obtain the load index for a given sched domain.
* @sd: The sched_domain whose load_idx is to be obtained.
* @idle: The Idle status of the CPU for whose sd load_icx is obtained.
+ *
+ * Return: The load index.
*/
static inline int get_sd_load_idx(struct sched_domain *sd,
enum cpu_idle_type idle)
*
* Determine if @sg is a busier group than the previously selected
* busiest group.
+ *
+ * Return: %true if @sg is a busier group than the previously selected
+ * busiest group. %false otherwise.
*/
static bool update_sd_pick_busiest(struct lb_env *env,
struct sd_lb_stats *sds,
* assuming lower CPU number will be equivalent to lower a SMT thread
* number.
*
- * Returns 1 when packing is required and a task should be moved to
+ * Return: 1 when packing is required and a task should be moved to
* this CPU. The amount of the imbalance is returned in *imbalance.
*
* @env: The load balancing environment.
* @balance: Pointer to a variable indicating if this_cpu
* is the appropriate cpu to perform load balancing at this_level.
*
- * Returns: - the busiest group if imbalance exists.
+ * Return: - The busiest group if imbalance exists.
* - If no imbalance and user has opted for power-savings balance,
* return the least loaded group whose CPUs can be
* put to idle by rebalancing its tasks onto our group.
unsigned long addr, unsigned long pgoff, pgprot_t prot)
{
int err = -ENOMEM;
- pte_t *pte;
+ pte_t *pte, ptfile;
spinlock_t *ptl;
pte = get_locked_pte(mm, addr, &ptl);
if (!pte)
goto out;
- if (!pte_none(*pte))
+ ptfile = pgoff_to_pte(pgoff);
+
+ if (!pte_none(*pte)) {
+ if (pte_present(*pte) && pte_soft_dirty(*pte))
+ pte_file_mksoft_dirty(ptfile);
zap_pte(mm, vma, addr, pte);
+ }
- set_pte_at(mm, addr, pte, pgoff_to_pte(pgoff));
+ set_pte_at(mm, addr, pte, ptfile);
/*
* We don't need to run update_mmu_cache() here because the "file pte"
* being installed by install_file_pte() is not a real pte - it's a
mm = vma->vm_mm;
- tlb_gather_mmu(&tlb, mm, 0);
+ tlb_gather_mmu(&tlb, mm, start, end);
__unmap_hugepage_range(&tlb, vma, start, end, ref_page);
tlb_finish_mmu(&tlb, start, end);
}
if (!s->memcg_params)
return -ENOMEM;
- INIT_WORK(&s->memcg_params->destroy,
- kmem_cache_destroy_work_func);
if (memcg) {
s->memcg_params->memcg = memcg;
s->memcg_params->root_cache = root_cache;
+ INIT_WORK(&s->memcg_params->destroy,
+ kmem_cache_destroy_work_func);
} else
s->memcg_params->is_root_cache = true;
* tear-down from @mm. The @fullmm argument is used when @mm is without
* users and we're going to destroy the full address space (exit/execve).
*/
-void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, bool fullmm)
+void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long start, unsigned long end)
{
tlb->mm = mm;
- tlb->fullmm = fullmm;
+ /* Is it from 0 to ~0? */
+ tlb->fullmm = !(start | (end+1));
tlb->need_flush_all = 0;
- tlb->start = -1UL;
- tlb->end = 0;
+ tlb->start = start;
+ tlb->end = end;
tlb->need_flush = 0;
tlb->local.next = NULL;
tlb->local.nr = 0;
{
struct mmu_gather_batch *batch, *next;
- tlb->start = start;
- tlb->end = end;
tlb_flush_mmu(tlb);
/* keep the page table cache within bounds */
spinlock_t *ptl;
pte_t *start_pte;
pte_t *pte;
- unsigned long range_start = addr;
again:
init_rss_vec(rss);
continue;
if (unlikely(details) && details->nonlinear_vma
&& linear_page_index(details->nonlinear_vma,
- addr) != page->index)
- set_pte_at(mm, addr, pte,
- pgoff_to_pte(page->index));
+ addr) != page->index) {
+ pte_t ptfile = pgoff_to_pte(page->index);
+ if (pte_soft_dirty(ptent))
+ pte_file_mksoft_dirty(ptfile);
+ set_pte_at(mm, addr, pte, ptfile);
+ }
if (PageAnon(page))
rss[MM_ANONPAGES]--;
else {
* and page-free while holding it.
*/
if (force_flush) {
+ unsigned long old_end;
+
force_flush = 0;
-#ifdef HAVE_GENERIC_MMU_GATHER
- tlb->start = range_start;
+ /*
+ * Flush the TLB just for the previous segment,
+ * then update the range to be the remaining
+ * TLB range.
+ */
+ old_end = tlb->end;
tlb->end = addr;
-#endif
+
tlb_flush_mmu(tlb);
- if (addr != end) {
- range_start = addr;
+
+ tlb->start = addr;
+ tlb->end = old_end;
+
+ if (addr != end)
goto again;
- }
}
return addr;
unsigned long end = start + size;
lru_add_drain();
- tlb_gather_mmu(&tlb, mm, 0);
+ tlb_gather_mmu(&tlb, mm, start, end);
update_hiwater_rss(mm);
mmu_notifier_invalidate_range_start(mm, start, end);
for ( ; vma && vma->vm_start < end; vma = vma->vm_next)
unsigned long end = address + size;
lru_add_drain();
- tlb_gather_mmu(&tlb, mm, 0);
+ tlb_gather_mmu(&tlb, mm, address, end);
update_hiwater_rss(mm);
mmu_notifier_invalidate_range_start(mm, address, end);
unmap_single_vma(&tlb, vma, address, end, details);
exclusive = 1;
}
flush_icache_page(vma, page);
+ if (pte_swp_soft_dirty(orig_pte))
+ pte = pte_mksoft_dirty(pte);
set_pte_at(mm, address, page_table, pte);
if (page == swapcache)
do_page_add_anon_rmap(page, vma, address, exclusive);
entry = mk_pte(page, vma->vm_page_prot);
if (flags & FAULT_FLAG_WRITE)
entry = maybe_mkwrite(pte_mkdirty(entry), vma);
+ else if (pte_file(orig_pte) && pte_file_soft_dirty(orig_pte))
+ pte_mksoft_dirty(entry);
if (anon) {
inc_mm_counter_fast(mm, MM_ANONPAGES);
page_add_new_anon_rmap(page, vma, address);
struct mmu_gather tlb;
lru_add_drain();
- tlb_gather_mmu(&tlb, mm, 0);
+ tlb_gather_mmu(&tlb, mm, start, end);
update_hiwater_rss(mm);
unmap_vmas(&tlb, vma, start, end);
free_pgtables(&tlb, vma, prev ? prev->vm_end : FIRST_USER_ADDRESS,
lru_add_drain();
flush_cache_mm(mm);
- tlb_gather_mmu(&tlb, mm, 1);
+ tlb_gather_mmu(&tlb, mm, 0, -1);
/* update_hiwater_rss(mm) here? but nobody should be looking */
/* Use -1 here to ensure all VMAs in the mm are unmapped */
unmap_vmas(&tlb, vma, 0, -1);
swp_entry_to_pte(make_hwpoison_entry(page)));
} else if (PageAnon(page)) {
swp_entry_t entry = { .val = page_private(page) };
+ pte_t swp_pte;
if (PageSwapCache(page)) {
/*
BUG_ON(TTU_ACTION(flags) != TTU_MIGRATION);
entry = make_migration_entry(page, pte_write(pteval));
}
- set_pte_at(mm, address, pte, swp_entry_to_pte(entry));
+ swp_pte = swp_entry_to_pte(entry);
+ if (pte_soft_dirty(pteval))
+ swp_pte = pte_swp_mksoft_dirty(swp_pte);
+ set_pte_at(mm, address, pte, swp_pte);
BUG_ON(pte_file(*pte));
} else if (IS_ENABLED(CONFIG_MIGRATION) &&
(TTU_ACTION(flags) == TTU_MIGRATION)) {
pteval = ptep_clear_flush(vma, address, pte);
/* If nonlinear, store the file page offset in the pte. */
- if (page->index != linear_page_index(vma, address))
- set_pte_at(mm, address, pte, pgoff_to_pte(page->index));
+ if (page->index != linear_page_index(vma, address)) {
+ pte_t ptfile = pgoff_to_pte(page->index);
+ if (pte_soft_dirty(pteval))
+ pte_file_mksoft_dirty(ptfile);
+ set_pte_at(mm, address, pte, ptfile);
+ }
/* Move the dirty bit to the physical page now the pte is gone. */
if (pte_dirty(pteval))
}
#endif /* CONFIG_HIBERNATION */
+static inline int maybe_same_pte(pte_t pte, pte_t swp_pte)
+{
+#ifdef CONFIG_MEM_SOFT_DIRTY
+ /*
+ * When pte keeps soft dirty bit the pte generated
+ * from swap entry does not has it, still it's same
+ * pte from logical point of view.
+ */
+ pte_t swp_pte_dirty = pte_swp_mksoft_dirty(swp_pte);
+ return pte_same(pte, swp_pte) || pte_same(pte, swp_pte_dirty);
+#else
+ return pte_same(pte, swp_pte);
+#endif
+}
+
/*
* No need to decide whether this PTE shares the swap entry with others,
* just let do_wp_page work it out if a write is requested later - to
}
pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
- if (unlikely(!pte_same(*pte, swp_entry_to_pte(entry)))) {
+ if (unlikely(!maybe_same_pte(*pte, swp_entry_to_pte(entry)))) {
mem_cgroup_cancel_charge_swapin(memcg);
ret = 0;
goto out;
* swapoff spends a _lot_ of time in this loop!
* Test inline before going to call unuse_pte.
*/
- if (unlikely(pte_same(*pte, swp_pte))) {
+ if (unlikely(maybe_same_pte(*pte, swp_pte))) {
pte_unmap(pte);
ret = unuse_pte(vma, pmd, addr, entry, page);
if (ret)
struct net_device *vlan_dev_real_dev(const struct net_device *dev)
{
- return vlan_dev_priv(dev)->real_dev;
+ struct net_device *ret = vlan_dev_priv(dev)->real_dev;
+
+ while (is_vlan_dev(ret))
+ ret = vlan_dev_priv(ret)->real_dev;
+
+ return ret;
}
EXPORT_SYMBOL(vlan_dev_real_dev);
* in these cases, the skb is further handled by this function and
* returns 1, otherwise it returns 0 and the caller shall further
* process the skb.
+ *
+ * This call might reallocate skb data.
*/
int batadv_bla_tx(struct batadv_priv *bat_priv, struct sk_buff *skb,
unsigned short vid)
return 0;
}
+/* this call might reallocate skb data */
static bool batadv_is_type_dhcprequest(struct sk_buff *skb, int header_len)
{
int ret = false;
return ret;
}
+/* this call might reallocate skb data */
bool batadv_gw_is_dhcp_target(struct sk_buff *skb, unsigned int *header_len)
{
struct ethhdr *ethhdr;
if (!pskb_may_pull(skb, *header_len + sizeof(*udphdr)))
return false;
+
+ /* skb->data might have been reallocated by pskb_may_pull() */
+ ethhdr = (struct ethhdr *)skb->data;
+ if (ntohs(ethhdr->h_proto) == ETH_P_8021Q)
+ ethhdr = (struct ethhdr *)(skb->data + VLAN_HLEN);
+
udphdr = (struct udphdr *)(skb->data + *header_len);
*header_len += sizeof(*udphdr);
return true;
}
+/* this call might reallocate skb data */
bool batadv_gw_out_of_range(struct batadv_priv *bat_priv,
- struct sk_buff *skb, struct ethhdr *ethhdr)
+ struct sk_buff *skb)
{
struct batadv_neigh_node *neigh_curr = NULL, *neigh_old = NULL;
struct batadv_orig_node *orig_dst_node = NULL;
struct batadv_gw_node *curr_gw = NULL;
+ struct ethhdr *ethhdr;
bool ret, out_of_range = false;
unsigned int header_len = 0;
uint8_t curr_tq_avg;
if (!ret)
goto out;
+ ethhdr = (struct ethhdr *)skb->data;
orig_dst_node = batadv_transtable_search(bat_priv, ethhdr->h_source,
ethhdr->h_dest);
if (!orig_dst_node)
void batadv_gw_node_purge(struct batadv_priv *bat_priv);
int batadv_gw_client_seq_print_text(struct seq_file *seq, void *offset);
bool batadv_gw_is_dhcp_target(struct sk_buff *skb, unsigned int *header_len);
-bool batadv_gw_out_of_range(struct batadv_priv *bat_priv,
- struct sk_buff *skb, struct ethhdr *ethhdr);
+bool batadv_gw_out_of_range(struct batadv_priv *bat_priv, struct sk_buff *skb);
#endif /* _NET_BATMAN_ADV_GATEWAY_CLIENT_H_ */
if (batadv_bla_tx(bat_priv, skb, vid))
goto dropped;
+ /* skb->data might have been reallocated by batadv_bla_tx() */
+ ethhdr = (struct ethhdr *)skb->data;
+
/* Register the client MAC in the transtable */
if (!is_multicast_ether_addr(ethhdr->h_source))
batadv_tt_local_add(soft_iface, ethhdr->h_source, skb->skb_iif);
default:
break;
}
+
+ /* reminder: ethhdr might have become unusable from here on
+ * (batadv_gw_is_dhcp_target() might have reallocated skb data)
+ */
}
/* ethernet packet should be broadcasted */
/* unicast packet */
} else {
if (atomic_read(&bat_priv->gw_mode) != BATADV_GW_MODE_OFF) {
- ret = batadv_gw_out_of_range(bat_priv, skb, ethhdr);
+ ret = batadv_gw_out_of_range(bat_priv, skb);
if (ret)
goto dropped;
}
* @skb: the skb containing the payload to encapsulate
* @orig_node: the destination node
*
- * Returns false if the payload could not be encapsulated or true otherwise
+ * Returns false if the payload could not be encapsulated or true otherwise.
+ *
+ * This call might reallocate skb data.
*/
static bool batadv_unicast_prepare_skb(struct sk_buff *skb,
struct batadv_orig_node *orig_node)
* @orig_node: the destination node
* @packet_subtype: the batman 4addr packet subtype to use
*
- * Returns false if the payload could not be encapsulated or true otherwise
+ * Returns false if the payload could not be encapsulated or true otherwise.
+ *
+ * This call might reallocate skb data.
*/
bool batadv_unicast_4addr_prepare_skb(struct batadv_priv *bat_priv,
struct sk_buff *skb,
struct batadv_neigh_node *neigh_node;
int data_len = skb->len;
int ret = NET_RX_DROP;
- unsigned int dev_mtu;
+ unsigned int dev_mtu, header_len;
/* get routing information */
if (is_multicast_ether_addr(ethhdr->h_dest)) {
switch (packet_type) {
case BATADV_UNICAST:
batadv_unicast_prepare_skb(skb, orig_node);
+ header_len = sizeof(struct batadv_unicast_packet);
break;
case BATADV_UNICAST_4ADDR:
batadv_unicast_4addr_prepare_skb(bat_priv, skb, orig_node,
packet_subtype);
+ header_len = sizeof(struct batadv_unicast_4addr_packet);
break;
default:
/* this function supports UNICAST and UNICAST_4ADDR only. It
goto out;
}
+ ethhdr = (struct ethhdr *)(skb->data + header_len);
unicast_packet = (struct batadv_unicast_packet *)skb->data;
/* inform the destination node that we are still missing a correct route
max_delay = msecs_to_jiffies(ntohs(mld->mld_maxdelay));
if (max_delay)
group = &mld->mld_mca;
- } else if (skb->len >= sizeof(*mld2q)) {
+ } else {
if (!pskb_may_pull(skb, sizeof(*mld2q))) {
err = -EINVAL;
goto out;
/*
- * Sysfs attributes of bridge ports
+ * Sysfs attributes of bridge
* Linux ethernet bridge
*
* Authors:
nhoff += sizeof(struct ipv6hdr);
break;
}
+ case __constant_htons(ETH_P_8021AD):
case __constant_htons(ETH_P_8021Q): {
const struct vlan_hdr *vlan;
struct vlan_hdr _vlan;
atomic_set(&p->refcnt, 1);
p->reachable_time =
neigh_rand_reach_time(p->base_reachable_time);
+ dev_hold(dev);
+ p->dev = dev;
+ write_pnet(&p->net, hold_net(net));
+ p->sysctl_table = NULL;
if (ops->ndo_neigh_setup && ops->ndo_neigh_setup(dev, p)) {
+ release_net(net);
+ dev_put(dev);
kfree(p);
return NULL;
}
- dev_hold(dev);
- p->dev = dev;
- write_pnet(&p->net, hold_net(net));
- p->sysctl_table = NULL;
write_lock_bh(&tbl->lock);
p->next = tbl->parms.next;
tbl->parms.next = p;
/* If aging addresses are supported device will need to
* implement its own handler for this.
*/
- if (ndm->ndm_state & NUD_PERMANENT) {
+ if (!(ndm->ndm_state & NUD_PERMANENT)) {
pr_info("%s: FDB only supports static addresses\n", dev->name);
return -EINVAL;
}
struct nlattr *extfilt;
u32 filter_mask = 0;
- extfilt = nlmsg_find_attr(cb->nlh, sizeof(struct rtgenmsg),
+ extfilt = nlmsg_find_attr(cb->nlh, sizeof(struct ifinfomsg),
IFLA_EXT_MASK);
if (extfilt)
filter_mask = nla_get_u32(extfilt);
}
return ((mtu - x->props.header_len - crypto_aead_authsize(esp->aead) -
- net_adj) & ~(align - 1)) + (net_adj - 2);
+ net_adj) & ~(align - 1)) + net_adj - 2;
}
static void esp4_err(struct sk_buff *skb, u32 info)
#include <linux/init.h>
#include <linux/list.h>
#include <linux/slab.h>
-#include <linux/prefetch.h>
#include <linux/export.h>
#include <net/net_namespace.h>
#include <net/ip.h>
if (!c)
continue;
- if (IS_LEAF(c)) {
- prefetch(rcu_dereference_rtnl(p->child[idx]));
+ if (IS_LEAF(c))
return (struct leaf *) c;
- }
/* Rescan start scanning in new node */
p = (struct tnode *) c;
if (daddr)
memcpy(&iph->daddr, daddr, 4);
if (iph->daddr)
- return t->hlen;
+ return t->hlen + sizeof(*iph);
return -(t->hlen + sizeof(*iph));
}
iph->daddr = dst;
iph->saddr = src;
iph->ttl = ttl;
- tunnel_ip_select_ident(skb,
- (const struct iphdr *)skb_inner_network_header(skb),
- &rt->dst);
+ __ip_select_ident(iph, &rt->dst, (skb_shinfo(skb)->gso_segs ?: 1) - 1);
err = ip_local_out(skb);
if (unlikely(net_xmit_eval(err)))
SNMP_MIB_ITEM("TCPFastOpenListenOverflow", LINUX_MIB_TCPFASTOPENLISTENOVERFLOW),
SNMP_MIB_ITEM("TCPFastOpenCookieReqd", LINUX_MIB_TCPFASTOPENCOOKIEREQD),
SNMP_MIB_ITEM("TCPSpuriousRtxHostQueues", LINUX_MIB_TCPSPURIOUS_RTX_HOSTQUEUES),
- SNMP_MIB_ITEM("LowLatencyRxPackets", LINUX_MIB_LOWLATENCYRXPACKETS),
+ SNMP_MIB_ITEM("BusyPollRxPackets", LINUX_MIB_BUSYPOLLRXPACKETS),
SNMP_MIB_SENTINEL
};
*/
static inline void bictcp_update(struct bictcp *ca, u32 cwnd)
{
- u64 offs;
- u32 delta, t, bic_target, max_cnt;
+ u32 delta, bic_target, max_cnt;
+ u64 offs, t;
ca->ack_cnt++; /* count the number of ACKs */
* if the cwnd < 1 million packets !!!
*/
+ t = (s32)(tcp_time_stamp - ca->epoch_start);
+ t += msecs_to_jiffies(ca->delay_min >> 3);
/* change the unit from HZ to bictcp_HZ */
- t = ((tcp_time_stamp + msecs_to_jiffies(ca->delay_min>>3)
- - ca->epoch_start) << BICTCP_HZ) / HZ;
+ t <<= BICTCP_HZ;
+ do_div(t, HZ);
if (t < ca->bic_K) /* t - K */
offs = ca->bic_K - t;
return;
/* Discard delay samples right after fast recovery */
- if ((s32)(tcp_time_stamp - ca->epoch_start) < HZ)
+ if (ca->epoch_start && (s32)(tcp_time_stamp - ca->epoch_start) < HZ)
return;
delay = (rtt_us << 3) / USEC_PER_MSEC;
net_adj = 0;
return ((mtu - x->props.header_len - crypto_aead_authsize(esp->aead) -
- net_adj) & ~(align - 1)) + (net_adj - 2);
+ net_adj) & ~(align - 1)) + net_adj - 2;
}
static void esp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
if (ipv6_prefix_equal(&key->addr, args->addr, key->plen)) {
#ifdef CONFIG_IPV6_SUBTREES
- if (fn->subtree)
- fn = fib6_lookup_1(fn->subtree, args + 1);
+ if (fn->subtree) {
+ struct fib6_node *sfn;
+ sfn = fib6_lookup_1(fn->subtree,
+ args + 1);
+ if (!sfn)
+ goto backtrack;
+ fn = sfn;
+ }
#endif
- if (!fn || fn->fn_flags & RTN_RTINFO)
+ if (fn->fn_flags & RTN_RTINFO)
return fn;
}
}
-
+#ifdef CONFIG_IPV6_SUBTREES
+backtrack:
+#endif
if (fn->fn_flags & RTN_ROOT)
break;
#include "led.h"
#define IEEE80211_AUTH_TIMEOUT (HZ / 5)
+#define IEEE80211_AUTH_TIMEOUT_LONG (HZ / 2)
#define IEEE80211_AUTH_TIMEOUT_SHORT (HZ / 10)
#define IEEE80211_AUTH_MAX_TRIES 3
#define IEEE80211_AUTH_WAIT_ASSOC (HZ * 5)
#define IEEE80211_ASSOC_TIMEOUT (HZ / 5)
+#define IEEE80211_ASSOC_TIMEOUT_LONG (HZ / 2)
#define IEEE80211_ASSOC_TIMEOUT_SHORT (HZ / 10)
#define IEEE80211_ASSOC_MAX_TRIES 3
struct ieee80211_channel *channel,
const struct ieee80211_ht_operation *ht_oper,
const struct ieee80211_vht_operation *vht_oper,
- struct cfg80211_chan_def *chandef, bool verbose)
+ struct cfg80211_chan_def *chandef, bool tracking)
{
+ struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
struct cfg80211_chan_def vht_chandef;
u32 ht_cfreq, ret;
ht_cfreq = ieee80211_channel_to_frequency(ht_oper->primary_chan,
channel->band);
/* check that channel matches the right operating channel */
- if (channel->center_freq != ht_cfreq) {
+ if (!tracking && channel->center_freq != ht_cfreq) {
/*
* It's possible that some APs are confused here;
* Netgear WNDR3700 sometimes reports 4 higher than
* since we look at probe response/beacon data here
* it should be OK.
*/
- if (verbose)
- sdata_info(sdata,
- "Wrong control channel: center-freq: %d ht-cfreq: %d ht->primary_chan: %d band: %d - Disabling HT\n",
- channel->center_freq, ht_cfreq,
- ht_oper->primary_chan, channel->band);
+ sdata_info(sdata,
+ "Wrong control channel: center-freq: %d ht-cfreq: %d ht->primary_chan: %d band: %d - Disabling HT\n",
+ channel->center_freq, ht_cfreq,
+ ht_oper->primary_chan, channel->band);
ret = IEEE80211_STA_DISABLE_HT | IEEE80211_STA_DISABLE_VHT;
goto out;
}
channel->band);
break;
default:
- if (verbose)
+ if (!(ifmgd->flags & IEEE80211_STA_DISABLE_VHT))
sdata_info(sdata,
"AP VHT operation IE has invalid channel width (%d), disable VHT\n",
vht_oper->chan_width);
}
if (!cfg80211_chandef_valid(&vht_chandef)) {
- if (verbose)
+ if (!(ifmgd->flags & IEEE80211_STA_DISABLE_VHT))
sdata_info(sdata,
"AP VHT information is invalid, disable VHT\n");
ret = IEEE80211_STA_DISABLE_VHT;
}
if (!cfg80211_chandef_compatible(chandef, &vht_chandef)) {
- if (verbose)
+ if (!(ifmgd->flags & IEEE80211_STA_DISABLE_VHT))
sdata_info(sdata,
"AP VHT information doesn't match HT, disable VHT\n");
ret = IEEE80211_STA_DISABLE_VHT;
if (ret & IEEE80211_STA_DISABLE_VHT)
vht_chandef = *chandef;
+ /*
+ * Ignore the DISABLED flag when we're already connected and only
+ * tracking the APs beacon for bandwidth changes - otherwise we
+ * might get disconnected here if we connect to an AP, update our
+ * regulatory information based on the AP's country IE and the
+ * information we have is wrong/outdated and disables the channel
+ * that we're actually using for the connection to the AP.
+ */
while (!cfg80211_chandef_usable(sdata->local->hw.wiphy, chandef,
- IEEE80211_CHAN_DISABLED)) {
+ tracking ? 0 :
+ IEEE80211_CHAN_DISABLED)) {
if (WARN_ON(chandef->width == NL80211_CHAN_WIDTH_20_NOHT)) {
ret = IEEE80211_STA_DISABLE_HT |
IEEE80211_STA_DISABLE_VHT;
- goto out;
+ break;
}
ret |= chandef_downgrade(chandef);
}
- if (chandef->width != vht_chandef.width && verbose)
+ if (chandef->width != vht_chandef.width && !tracking)
sdata_info(sdata,
"capabilities/regulatory prevented using AP HT/VHT configuration, downgraded\n");
/* calculate new channel (type) based on HT/VHT operation IEs */
flags = ieee80211_determine_chantype(sdata, sband, chan, ht_oper,
- vht_oper, &chandef, false);
+ vht_oper, &chandef, true);
/*
* Downgrade the new channel if we associated with restricted
if (tx_flags == 0) {
auth_data->timeout = jiffies + IEEE80211_AUTH_TIMEOUT;
- ifmgd->auth_data->timeout_started = true;
+ auth_data->timeout_started = true;
run_again(sdata, auth_data->timeout);
} else {
- auth_data->timeout_started = false;
+ auth_data->timeout =
+ round_jiffies_up(jiffies + IEEE80211_AUTH_TIMEOUT_LONG);
+ auth_data->timeout_started = true;
+ run_again(sdata, auth_data->timeout);
}
return 0;
assoc_data->timeout_started = true;
run_again(sdata, assoc_data->timeout);
} else {
- assoc_data->timeout_started = false;
+ assoc_data->timeout =
+ round_jiffies_up(jiffies +
+ IEEE80211_ASSOC_TIMEOUT_LONG);
+ assoc_data->timeout_started = true;
+ run_again(sdata, assoc_data->timeout);
}
return 0;
ifmgd->flags |= ieee80211_determine_chantype(sdata, sband,
cbss->channel,
ht_oper, vht_oper,
- &chandef, true);
+ &chandef, false);
sdata->needed_rx_chains = min(ieee80211_ht_vht_rx_chains(sdata, cbss),
local->rx_chains);
const struct nf_conntrack_tuple *tuple = &ct->tuplehash[dir].tuple;
__u32 seq, ack, sack, end, win, swin;
s16 receiver_offset;
- bool res;
+ bool res, in_recv_win;
/*
* Get the required data from the packet.
receiver->td_end, receiver->td_maxend, receiver->td_maxwin,
receiver->td_scale);
+ /* Is the ending sequence in the receive window (if available)? */
+ in_recv_win = !receiver->td_maxwin ||
+ after(end, sender->td_end - receiver->td_maxwin - 1);
+
pr_debug("tcp_in_window: I=%i II=%i III=%i IV=%i\n",
before(seq, sender->td_maxend + 1),
- after(end, sender->td_end - receiver->td_maxwin - 1),
+ (in_recv_win ? 1 : 0),
before(sack, receiver->td_end + 1),
after(sack, receiver->td_end - MAXACKWINDOW(sender) - 1));
if (before(seq, sender->td_maxend + 1) &&
- after(end, sender->td_end - receiver->td_maxwin - 1) &&
+ in_recv_win &&
before(sack, receiver->td_end + 1) &&
after(sack, receiver->td_end - MAXACKWINDOW(sender) - 1)) {
/*
nf_log_packet(net, pf, 0, skb, NULL, NULL, NULL,
"nf_ct_tcp: %s ",
before(seq, sender->td_maxend + 1) ?
- after(end, sender->td_end - receiver->td_maxwin - 1) ?
+ in_recv_win ?
before(sack, receiver->td_end + 1) ?
after(sack, receiver->td_end - MAXACKWINDOW(sender) - 1) ? "BUG"
: "ACK is under the lower bound (possible overly delayed ACK)"
nfmsg->version = NFNETLINK_V0;
nfmsg->res_id = htons(inst->group_num);
+ memset(&pmsg, 0, sizeof(pmsg));
pmsg.hw_protocol = skb->protocol;
pmsg.hook = hooknum;
if (indev && skb->dev &&
skb->mac_header != skb->network_header) {
struct nfulnl_msg_packet_hw phw;
- int len = dev_parse_header(skb, phw.hw_addr);
+ int len;
+
+ memset(&phw, 0, sizeof(phw));
+ len = dev_parse_header(skb, phw.hw_addr);
if (len > 0) {
phw.hw_addrlen = htons(len);
if (nla_put(inst->skb, NFULA_HWADDR, sizeof(phw), &phw))
if (indev && entskb->dev &&
entskb->mac_header != entskb->network_header) {
struct nfqnl_msg_packet_hw phw;
- int len = dev_parse_header(entskb, phw.hw_addr);
+ int len;
+
+ memset(&phw, 0, sizeof(phw));
+ len = dev_parse_header(entskb, phw.hw_addr);
if (len) {
phw.hw_addrlen = htons(len);
if (nla_put(skb, NFQA_HWADDR, sizeof(phw), &phw))
{
const struct xt_tcpmss_info *info = par->targinfo;
struct tcphdr *tcph;
- unsigned int tcplen, i;
+ int len, tcp_hdrlen;
+ unsigned int i;
__be16 oldval;
u16 newmss;
u8 *opt;
if (!skb_make_writable(skb, skb->len))
return -1;
- tcplen = skb->len - tcphoff;
+ len = skb->len - tcphoff;
+ if (len < (int)sizeof(struct tcphdr))
+ return -1;
+
tcph = (struct tcphdr *)(skb_network_header(skb) + tcphoff);
+ tcp_hdrlen = tcph->doff * 4;
- /* Header cannot be larger than the packet */
- if (tcplen < tcph->doff*4)
+ if (len < tcp_hdrlen)
return -1;
if (info->mss == XT_TCPMSS_CLAMP_PMTU) {
newmss = info->mss;
opt = (u_int8_t *)tcph;
- for (i = sizeof(struct tcphdr); i < tcph->doff*4; i += optlen(opt, i)) {
- if (opt[i] == TCPOPT_MSS && tcph->doff*4 - i >= TCPOLEN_MSS &&
- opt[i+1] == TCPOLEN_MSS) {
+ for (i = sizeof(struct tcphdr); i <= tcp_hdrlen - TCPOLEN_MSS; i += optlen(opt, i)) {
+ if (opt[i] == TCPOPT_MSS && opt[i+1] == TCPOLEN_MSS) {
u_int16_t oldmss;
oldmss = (opt[i+2] << 8) | opt[i+3];
}
/* There is data after the header so the option can't be added
- without moving it, and doing so may make the SYN packet
- itself too large. Accept the packet unmodified instead. */
- if (tcplen > tcph->doff*4)
+ * without moving it, and doing so may make the SYN packet
+ * itself too large. Accept the packet unmodified instead.
+ */
+ if (len > tcp_hdrlen)
return 0;
/*
newmss = min(newmss, (u16)1220);
opt = (u_int8_t *)tcph + sizeof(struct tcphdr);
- memmove(opt + TCPOLEN_MSS, opt, tcplen - sizeof(struct tcphdr));
+ memmove(opt + TCPOLEN_MSS, opt, len - sizeof(struct tcphdr));
inet_proto_csum_replace2(&tcph->check, skb,
- htons(tcplen), htons(tcplen + TCPOLEN_MSS), 1);
+ htons(len), htons(len + TCPOLEN_MSS), 1);
opt[0] = TCPOPT_MSS;
opt[1] = TCPOLEN_MSS;
opt[2] = (newmss & 0xff00) >> 8;
struct tcphdr *tcph;
u_int16_t n, o;
u_int8_t *opt;
- int len;
+ int len, tcp_hdrlen;
/* This is a fragment, no TCP header is available */
if (par->fragoff != 0)
return NF_DROP;
tcph = (struct tcphdr *)(skb_network_header(skb) + tcphoff);
- if (tcph->doff * 4 > len)
+ tcp_hdrlen = tcph->doff * 4;
+
+ if (len < tcp_hdrlen)
return NF_DROP;
opt = (u_int8_t *)tcph;
* Walk through all TCP options - if we find some option to remove,
* set all octets to %TCPOPT_NOP and adjust checksum.
*/
- for (i = sizeof(struct tcphdr); i < tcp_hdrlen(skb); i += optl) {
+ for (i = sizeof(struct tcphdr); i < tcp_hdrlen - 1; i += optl) {
optl = optlen(opt, i);
- if (i + optl > tcp_hdrlen(skb))
+ if (i + optl > tcp_hdrlen)
break;
if (!tcpoptstrip_test_bit(info->strip_bmap, opt[i]))
struct net *net = sock_net(skb->sk);
int chains_to_skip = cb->args[0];
int fams_to_skip = cb->args[1];
+ bool need_locking = chains_to_skip || fams_to_skip;
+
+ if (need_locking)
+ genl_lock();
for (i = chains_to_skip; i < GENL_FAM_TAB_SIZE; i++) {
n = 0;
cb->args[0] = i;
cb->args[1] = n;
+ if (need_locking)
+ genl_unlock();
+
return skb->len;
}
{
struct sw_flow_actions *acts = rcu_dereference(OVS_CB(skb)->flow->sf_acts);
+ OVS_CB(skb)->tun_key = NULL;
return do_execute_actions(dp, skb, acts->actions,
acts->actions_len, false);
}
ovs_notify(reply, info, &ovs_dp_vport_multicast_group);
return 0;
- rtnl_unlock();
- return 0;
-
exit_free:
kfree_skb(reply);
exit_unlock:
struct flex_array *buckets;
int i, err;
- buckets = flex_array_alloc(sizeof(struct hlist_head *),
+ buckets = flex_array_alloc(sizeof(struct hlist_head),
n_buckets, GFP_KERNEL);
if (!buckets)
return NULL;
return q;
}
+/* The linklayer setting were not transferred from iproute2, in older
+ * versions, and the rate tables lookup systems have been dropped in
+ * the kernel. To keep backward compatible with older iproute2 tc
+ * utils, we detect the linklayer setting by detecting if the rate
+ * table were modified.
+ *
+ * For linklayer ATM table entries, the rate table will be aligned to
+ * 48 bytes, thus some table entries will contain the same value. The
+ * mpu (min packet unit) is also encoded into the old rate table, thus
+ * starting from the mpu, we find low and high table entries for
+ * mapping this cell. If these entries contain the same value, when
+ * the rate tables have been modified for linklayer ATM.
+ *
+ * This is done by rounding mpu to the nearest 48 bytes cell/entry,
+ * and then roundup to the next cell, calc the table entry one below,
+ * and compare.
+ */
+static __u8 __detect_linklayer(struct tc_ratespec *r, __u32 *rtab)
+{
+ int low = roundup(r->mpu, 48);
+ int high = roundup(low+1, 48);
+ int cell_low = low >> r->cell_log;
+ int cell_high = (high >> r->cell_log) - 1;
+
+ /* rtab is too inaccurate at rates > 100Mbit/s */
+ if ((r->rate > (100000000/8)) || (rtab[0] == 0)) {
+ pr_debug("TC linklayer: Giving up ATM detection\n");
+ return TC_LINKLAYER_ETHERNET;
+ }
+
+ if ((cell_high > cell_low) && (cell_high < 256)
+ && (rtab[cell_low] == rtab[cell_high])) {
+ pr_debug("TC linklayer: Detected ATM, low(%d)=high(%d)=%u\n",
+ cell_low, cell_high, rtab[cell_high]);
+ return TC_LINKLAYER_ATM;
+ }
+ return TC_LINKLAYER_ETHERNET;
+}
+
static struct qdisc_rate_table *qdisc_rtab_list;
struct qdisc_rate_table *qdisc_get_rtab(struct tc_ratespec *r, struct nlattr *tab)
rtab->rate = *r;
rtab->refcnt = 1;
memcpy(rtab->data, nla_data(tab), 1024);
+ if (r->linklayer == TC_LINKLAYER_UNAWARE)
+ r->linklayer = __detect_linklayer(r, rtab->data);
rtab->next = qdisc_rtab_list;
qdisc_rtab_list = rtab;
}
#include <linux/rcupdate.h>
#include <linux/list.h>
#include <linux/slab.h>
+#include <linux/if_vlan.h>
#include <net/sch_generic.h>
#include <net/pkt_sched.h>
#include <net/dst.h>
unsigned long dev_trans_start(struct net_device *dev)
{
- unsigned long val, res = dev->trans_start;
+ unsigned long val, res;
unsigned int i;
+ if (is_vlan_dev(dev))
+ dev = vlan_dev_real_dev(dev);
+ res = dev->trans_start;
for (i = 0; i < dev->num_tx_queues; i++) {
val = netdev_get_tx_queue(dev, i)->trans_start;
if (val && time_after(val, res))
res = val;
}
dev->trans_start = res;
+
return res;
}
EXPORT_SYMBOL(dev_trans_start);
memset(r, 0, sizeof(*r));
r->overhead = conf->overhead;
r->rate_bytes_ps = conf->rate;
+ r->linklayer = (conf->linklayer & TC_LINKLAYER_MASK);
r->mult = 1;
/*
* The deal here is to replace a divide by a reciprocal one
struct htb_sched *q = qdisc_priv(sch);
struct htb_class *cl = (struct htb_class *)*arg, *parent;
struct nlattr *opt = tca[TCA_OPTIONS];
+ struct qdisc_rate_table *rtab = NULL, *ctab = NULL;
struct nlattr *tb[TCA_HTB_MAX + 1];
struct tc_htb_opt *hopt;
if (!hopt->rate.rate || !hopt->ceil.rate)
goto failure;
+ /* Keeping backward compatible with rate_table based iproute2 tc */
+ if (hopt->rate.linklayer == TC_LINKLAYER_UNAWARE) {
+ rtab = qdisc_get_rtab(&hopt->rate, tb[TCA_HTB_RTAB]);
+ if (rtab)
+ qdisc_put_rtab(rtab);
+ }
+ if (hopt->ceil.linklayer == TC_LINKLAYER_UNAWARE) {
+ ctab = qdisc_get_rtab(&hopt->ceil, tb[TCA_HTB_CTAB]);
+ if (ctab)
+ qdisc_put_rtab(ctab);
+ }
+
if (!cl) { /* new class */
struct Qdisc *new_q;
int prio;
else
spc_state = SCTP_ADDR_AVAILABLE;
/* Don't inform ULP about transition from PF to
- * active state and set cwnd to 1, see SCTP
+ * active state and set cwnd to 1 MTU, see SCTP
* Quick failover draft section 5.1, point 5
*/
if (transport->state == SCTP_PF) {
ulp_notify = false;
- transport->cwnd = 1;
+ transport->cwnd = asoc->pathmtu;
}
transport->state = SCTP_ACTIVE;
break;
return;
}
- call_rcu(&transport->rcu, sctp_transport_destroy_rcu);
-
sctp_packet_free(&transport->packet);
if (transport->asoc)
sctp_association_put(transport->asoc);
+
+ call_rcu(&transport->rcu, sctp_transport_destroy_rcu);
}
/* Start T3_rtx timer if it is not already running and update the heartbeat
{
struct tipc_link *l_ptr;
struct tipc_link *temp_l_ptr;
+ struct tipc_link_req *temp_req;
pr_info("Disabling bearer <%s>\n", b_ptr->name);
spin_lock_bh(&b_ptr->lock);
list_for_each_entry_safe(l_ptr, temp_l_ptr, &b_ptr->links, link_list) {
tipc_link_delete(l_ptr);
}
- if (b_ptr->link_req)
- tipc_disc_delete(b_ptr->link_req);
+ temp_req = b_ptr->link_req;
+ b_ptr->link_req = NULL;
spin_unlock_bh(&b_ptr->lock);
+
+ if (temp_req)
+ tipc_disc_delete(temp_req);
+
memset(b_ptr, 0, sizeof(struct tipc_bearer));
}
for (i = 0; i < ARRAY_SIZE(vsock_connected_table); i++) {
struct vsock_sock *vsk;
list_for_each_entry(vsk, &vsock_connected_table[i],
- connected_table);
+ connected_table)
fn(sk_vsock(vsk));
}
cfg80211_leave_mesh(rdev, dev);
break;
case NL80211_IFTYPE_AP:
+ case NL80211_IFTYPE_P2P_GO:
cfg80211_stop_ap(rdev, dev);
break;
default:
goto out_unlock;
}
*rdev = wiphy_to_dev((*wdev)->wiphy);
- cb->args[0] = (*rdev)->wiphy_idx;
+ /* 0 is the first index - add 1 to parse only once */
+ cb->args[0] = (*rdev)->wiphy_idx + 1;
cb->args[1] = (*wdev)->identifier;
} else {
- struct wiphy *wiphy = wiphy_idx_to_wiphy(cb->args[0]);
+ /* subtract the 1 again here */
+ struct wiphy *wiphy = wiphy_idx_to_wiphy(cb->args[0] - 1);
struct wireless_dev *tmp;
if (!wiphy) {
projects / ~andy / linux / commitdiff