* Re: [PATCH net-next] net: phy: remove states PHY_STARTING and PHY_PENDING
From: David Miller @ 2018-11-11 18:05 UTC (permalink / raw)
To: hkallweit1; +Cc: andrew, f.fainelli, netdev
In-Reply-To: <4bb8b90e-4958-6774-6984-0ca51e57b011@gmail.com>
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Sat, 10 Nov 2018 23:40:50 +0100
> Both states aren't used. Most likely they result from an idea that
> never materialized. So remove them.
>
> Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Applied.
^ permalink raw reply
* Re: [RFC] mm: Replace all open encodings for NUMA_NO_NODE
From: Joseph Qi @ 2018-11-12 3:57 UTC (permalink / raw)
To: Anshuman Khandual, linux-mm, linux-kernel
Cc: ocfs2-devel, linux-fbdev, dri-devel, netdev, intel-wired-lan,
linux-media, iommu, linux-rdma, dmaengine, linux-block,
sparclinux, linuxppc-dev, linux-ia64, linux-alpha
In-Reply-To: <1541990515-11670-1-git-send-email-anshuman.khandual@arm.com>
For ocfs2 part, node means host in the cluster, not NUMA node.
Thanks,
Joseph
On 18/11/12 10:41, Anshuman Khandual wrote:
> At present there are multiple places where invalid node number is encoded
> as -1. Even though implicitly understood it is always better to have macros
> in there. Replace these open encodings for an invalid node number with the
> global macro NUMA_NO_NODE. This helps remove NUMA related assumptions like
> 'invalid node' from various places redirecting them to a common definition.
>
> Signed-off-by: Anshuman Khandual <anshuman.khandual@arm.com>
> ---
> Build tested this with multiple cross compiler options like alpha, sparc,
> arm64, x86, powerpc64le etc with their default config which might not have
> compiled tested all driver related changes. I will appreciate folks giving
> this a test in their respective build environment.
>
> All these places for replacement were found by running the following grep
> patterns on the entire kernel code. Please let me know if this might have
> missed some instances. This might also have replaced some false positives.
> I will appreciate suggestions, inputs and review.
>
> 1. git grep "nid == -1"
> 2. git grep "node == -1"
> 3. git grep "nid = -1"
> 4. git grep "node = -1"
>
> arch/alpha/include/asm/topology.h | 2 +-
> arch/ia64/kernel/numa.c | 2 +-
> arch/ia64/mm/discontig.c | 6 +++---
> arch/ia64/sn/kernel/io_common.c | 2 +-
> arch/powerpc/include/asm/pci-bridge.h | 2 +-
> arch/powerpc/kernel/paca.c | 2 +-
> arch/powerpc/kernel/pci-common.c | 2 +-
> arch/powerpc/mm/numa.c | 14 +++++++-------
> arch/powerpc/platforms/powernv/memtrace.c | 4 ++--
> arch/sparc/kernel/auxio_32.c | 2 +-
> arch/sparc/kernel/pci_fire.c | 2 +-
> arch/sparc/kernel/pci_schizo.c | 2 +-
> arch/sparc/kernel/pcic.c | 6 +++---
> arch/sparc/kernel/psycho_common.c | 2 +-
> arch/sparc/kernel/sbus.c | 2 +-
> arch/sparc/mm/init_64.c | 6 +++---
> arch/sparc/prom/init_32.c | 2 +-
> arch/sparc/prom/init_64.c | 4 ++--
> arch/sparc/prom/tree_32.c | 12 ++++++------
> arch/sparc/prom/tree_64.c | 18 +++++++++---------
> arch/x86/include/asm/pci.h | 2 +-
> arch/x86/kernel/apic/x2apic_uv_x.c | 6 +++---
> arch/x86/kernel/smpboot.c | 2 +-
> arch/x86/platform/olpc/olpc_dt.c | 16 ++++++++--------
> drivers/block/mtip32xx/mtip32xx.c | 4 ++--
> drivers/dma/dmaengine.c | 3 ++-
> drivers/infiniband/hw/hfi1/affinity.c | 2 +-
> drivers/infiniband/hw/hfi1/init.c | 2 +-
> drivers/iommu/dmar.c | 4 ++--
> drivers/iommu/intel-iommu.c | 2 +-
> drivers/media/pci/ivtv/ivtvfb.c | 2 +-
> drivers/media/platform/vivid/vivid-osd.c | 2 +-
> drivers/misc/sgi-xp/xpc_uv.c | 2 +-
> drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 4 ++--
> drivers/video/fbdev/mmp/fb/mmpfb.c | 2 +-
> drivers/video/fbdev/pxa168fb.c | 2 +-
> drivers/video/fbdev/w100fb.c | 2 +-
> fs/ocfs2/dlm/dlmcommon.h | 2 +-
> fs/ocfs2/dlm/dlmdomain.c | 10 +++++-----
> fs/ocfs2/dlm/dlmmaster.c | 2 +-
> fs/ocfs2/dlm/dlmrecovery.c | 2 +-
> fs/ocfs2/stack_user.c | 6 +++---
> init/init_task.c | 2 +-
> kernel/kthread.c | 2 +-
> kernel/sched/fair.c | 15 ++++++++-------
> lib/cpumask.c | 2 +-
> mm/huge_memory.c | 12 ++++++------
> mm/hugetlb.c | 2 +-
> mm/ksm.c | 2 +-
> mm/memory.c | 6 +++---
> mm/memory_hotplug.c | 12 ++++++------
> mm/mempolicy.c | 2 +-
> mm/page_alloc.c | 4 ++--
> mm/page_ext.c | 2 +-
> net/core/pktgen.c | 2 +-
> net/qrtr/qrtr.c | 2 +-
> tools/perf/bench/numa.c | 6 +++---
> 57 files changed, 125 insertions(+), 123 deletions(-)
>
> diff --git a/arch/alpha/include/asm/topology.h b/arch/alpha/include/asm/topology.h
> index e6e13a8..f6dc89c 100644
> --- a/arch/alpha/include/asm/topology.h
> +++ b/arch/alpha/include/asm/topology.h
> @@ -29,7 +29,7 @@ static const struct cpumask *cpumask_of_node(int node)
> {
> int cpu;
>
> - if (node == -1)
> + if (node == NUMA_NO_NODE)
> return cpu_all_mask;
>
> cpumask_clear(&node_to_cpumask_map[node]);
> diff --git a/arch/ia64/kernel/numa.c b/arch/ia64/kernel/numa.c
> index 92c3762..1315da6 100644
> --- a/arch/ia64/kernel/numa.c
> +++ b/arch/ia64/kernel/numa.c
> @@ -74,7 +74,7 @@ void __init build_cpu_to_node_map(void)
> cpumask_clear(&node_to_cpu_mask[node]);
>
> for_each_possible_early_cpu(cpu) {
> - node = -1;
> + node = NUMA_NO_NODE;
> for (i = 0; i < NR_CPUS; ++i)
> if (cpu_physical_id(cpu) == node_cpuid[i].phys_id) {
> node = node_cpuid[i].nid;
> diff --git a/arch/ia64/mm/discontig.c b/arch/ia64/mm/discontig.c
> index 8a96578..f9c3675 100644
> --- a/arch/ia64/mm/discontig.c
> +++ b/arch/ia64/mm/discontig.c
> @@ -227,7 +227,7 @@ void __init setup_per_cpu_areas(void)
> * CPUs are put into groups according to node. Walk cpu_map
> * and create new groups at node boundaries.
> */
> - prev_node = -1;
> + prev_node = NUMA_NO_NODE;
> ai->nr_groups = 0;
> for (unit = 0; unit < nr_units; unit++) {
> cpu = cpu_map[unit];
> @@ -435,7 +435,7 @@ static void __init *memory_less_node_alloc(int nid, unsigned long pernodesize)
> {
> void *ptr = NULL;
> u8 best = 0xff;
> - int bestnode = -1, node, anynode = 0;
> + int bestnode = NUMA_NO_NODE, node, anynode = 0;
>
> for_each_online_node(node) {
> if (node_isset(node, memory_less_mask))
> @@ -447,7 +447,7 @@ static void __init *memory_less_node_alloc(int nid, unsigned long pernodesize)
> anynode = node;
> }
>
> - if (bestnode == -1)
> + if (bestnode == NUMA_NO_NODE)
> bestnode = anynode;
>
> ptr = memblock_alloc_try_nid(pernodesize, PERCPU_PAGE_SIZE,
> diff --git a/arch/ia64/sn/kernel/io_common.c b/arch/ia64/sn/kernel/io_common.c
> index 8df13d0..86b3fcb 100644
> --- a/arch/ia64/sn/kernel/io_common.c
> +++ b/arch/ia64/sn/kernel/io_common.c
> @@ -344,7 +344,7 @@ sn_common_bus_fixup(struct pci_bus *bus,
> printk(KERN_WARNING "on node %d but only %d nodes online."
> "Association set to undetermined.\n",
> controller->node, num_online_nodes());
> - controller->node = -1;
> + controller->node = NUMA_NO_NODE;
> }
> }
>
> diff --git a/arch/powerpc/include/asm/pci-bridge.h b/arch/powerpc/include/asm/pci-bridge.h
> index 94d4490..25a9e33 100644
> --- a/arch/powerpc/include/asm/pci-bridge.h
> +++ b/arch/powerpc/include/asm/pci-bridge.h
> @@ -264,7 +264,7 @@ extern int pcibios_map_io_space(struct pci_bus *bus);
> #ifdef CONFIG_NUMA
> #define PHB_SET_NODE(PHB, NODE) ((PHB)->node = (NODE))
> #else
> -#define PHB_SET_NODE(PHB, NODE) ((PHB)->node = -1)
> +#define PHB_SET_NODE(PHB, NODE) ((PHB)->node = NUMA_NO_NODE)
> #endif
>
> #endif /* CONFIG_PPC64 */
> diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c
> index 913bfca..6a0bd51 100644
> --- a/arch/powerpc/kernel/paca.c
> +++ b/arch/powerpc/kernel/paca.c
> @@ -36,7 +36,7 @@ static void *__init alloc_paca_data(unsigned long size, unsigned long align,
> * which will put its paca in the right place.
> */
> if (cpu == boot_cpuid) {
> - nid = -1;
> + nid = NUMA_NO_NODE;
> memblock_set_bottom_up(true);
> } else {
> nid = early_cpu_to_node(cpu);
> diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
> index 88e4f69..14c33a9 100644
> --- a/arch/powerpc/kernel/pci-common.c
> +++ b/arch/powerpc/kernel/pci-common.c
> @@ -132,7 +132,7 @@ struct pci_controller *pcibios_alloc_controller(struct device_node *dev)
> int nid = of_node_to_nid(dev);
>
> if (nid < 0 || !node_online(nid))
> - nid = -1;
> + nid = NUMA_NO_NODE;
>
> PHB_SET_NODE(phb, nid);
> }
> diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
> index 3a048e9..77808a2 100644
> --- a/arch/powerpc/mm/numa.c
> +++ b/arch/powerpc/mm/numa.c
> @@ -215,7 +215,7 @@ static void initialize_distance_lookup_table(int nid,
> */
> static int associativity_to_nid(const __be32 *associativity)
> {
> - int nid = -1;
> + int nid = NUMA_NO_NODE;
>
> if (min_common_depth == -1)
> goto out;
> @@ -225,7 +225,7 @@ static int associativity_to_nid(const __be32 *associativity)
>
> /* POWER4 LPAR uses 0xffff as invalid node */
> if (nid == 0xffff || nid >= MAX_NUMNODES)
> - nid = -1;
> + nid = NUMA_NO_NODE;
>
> if (nid > 0 &&
> of_read_number(associativity, 1) >= distance_ref_points_depth) {
> @@ -244,7 +244,7 @@ static int associativity_to_nid(const __be32 *associativity)
> */
> static int of_node_to_nid_single(struct device_node *device)
> {
> - int nid = -1;
> + int nid = NUMA_NO_NODE;
> const __be32 *tmp;
>
> tmp = of_get_associativity(device);
> @@ -256,7 +256,7 @@ static int of_node_to_nid_single(struct device_node *device)
> /* Walk the device tree upwards, looking for an associativity id */
> int of_node_to_nid(struct device_node *device)
> {
> - int nid = -1;
> + int nid = NUMA_NO_NODE;
>
> of_node_get(device);
> while (device) {
> @@ -454,7 +454,7 @@ static int of_drconf_to_nid_single(struct drmem_lmb *lmb)
> */
> static int numa_setup_cpu(unsigned long lcpu)
> {
> - int nid = -1;
> + int nid = NUMA_NO_NODE;
> struct device_node *cpu;
>
> /*
> @@ -930,7 +930,7 @@ static int hot_add_drconf_scn_to_nid(unsigned long scn_addr)
> {
> struct drmem_lmb *lmb;
> unsigned long lmb_size;
> - int nid = -1;
> + int nid = NUMA_NO_NODE;
>
> lmb_size = drmem_lmb_size();
>
> @@ -960,7 +960,7 @@ static int hot_add_drconf_scn_to_nid(unsigned long scn_addr)
> static int hot_add_node_scn_to_nid(unsigned long scn_addr)
> {
> struct device_node *memory;
> - int nid = -1;
> + int nid = NUMA_NO_NODE;
>
> for_each_node_by_type(memory, "memory") {
> unsigned long start, size;
> diff --git a/arch/powerpc/platforms/powernv/memtrace.c b/arch/powerpc/platforms/powernv/memtrace.c
> index 84d038e..1ce3bfc 100644
> --- a/arch/powerpc/platforms/powernv/memtrace.c
> +++ b/arch/powerpc/platforms/powernv/memtrace.c
> @@ -223,7 +223,7 @@ static int memtrace_online(void)
> ent = &memtrace_array[i];
>
> /* We have onlined this chunk previously */
> - if (ent->nid == -1)
> + if (ent->nid == NUMA_NO_NODE)
> continue;
>
> /* Remove from io mappings */
> @@ -257,7 +257,7 @@ static int memtrace_online(void)
> */
> debugfs_remove_recursive(ent->dir);
> pr_info("Added trace memory back to node %d\n", ent->nid);
> - ent->size = ent->start = ent->nid = -1;
> + ent->size = ent->start = ent->nid = NUMA_NO_NODE;
> }
> if (ret)
> return ret;
> diff --git a/arch/sparc/kernel/auxio_32.c b/arch/sparc/kernel/auxio_32.c
> index a32d588..39f6c59 100644
> --- a/arch/sparc/kernel/auxio_32.c
> +++ b/arch/sparc/kernel/auxio_32.c
> @@ -120,7 +120,7 @@ void __init auxio_power_probe(void)
> node = prom_searchsiblings(node, "obio");
> node = prom_getchild(node);
> node = prom_searchsiblings(node, "power");
> - if (node == 0 || (s32)node == -1)
> + if (node == 0 || (s32)node == NUMA_NO_NODE)
> return;
>
> /* Map the power control register. */
> diff --git a/arch/sparc/kernel/pci_fire.c b/arch/sparc/kernel/pci_fire.c
> index be71ae0..474d3be 100644
> --- a/arch/sparc/kernel/pci_fire.c
> +++ b/arch/sparc/kernel/pci_fire.c
> @@ -416,7 +416,7 @@ static int pci_fire_pbm_init(struct pci_pbm_info *pbm,
> struct device_node *dp = op->dev.of_node;
> int err;
>
> - pbm->numa_node = -1;
> + pbm->numa_node = NUMA_NO_NODE;
>
> pbm->pci_ops = &sun4u_pci_ops;
> pbm->config_space_reg_bits = 12;
> diff --git a/arch/sparc/kernel/pci_schizo.c b/arch/sparc/kernel/pci_schizo.c
> index 934b97c..87bb231 100644
> --- a/arch/sparc/kernel/pci_schizo.c
> +++ b/arch/sparc/kernel/pci_schizo.c
> @@ -1347,7 +1347,7 @@ static int schizo_pbm_init(struct pci_pbm_info *pbm,
> pbm->next = pci_pbm_root;
> pci_pbm_root = pbm;
>
> - pbm->numa_node = -1;
> + pbm->numa_node = NUMA_NO_NODE;
>
> pbm->pci_ops = &sun4u_pci_ops;
> pbm->config_space_reg_bits = 8;
> diff --git a/arch/sparc/kernel/pcic.c b/arch/sparc/kernel/pcic.c
> index ee4c9a9..d5fe898 100644
> --- a/arch/sparc/kernel/pcic.c
> +++ b/arch/sparc/kernel/pcic.c
> @@ -476,7 +476,7 @@ static void pcic_map_pci_device(struct linux_pcic *pcic,
> unsigned long flags;
> int j;
>
> - if (node == 0 || node == -1) {
> + if (node == 0 || node == NUMA_NO_NODE) {
> strcpy(namebuf, "???");
> } else {
> prom_getstring(node, "name", namebuf, 63); namebuf[63] = 0;
> @@ -535,7 +535,7 @@ pcic_fill_irq(struct linux_pcic *pcic, struct pci_dev *dev, int node)
> int i, ivec;
> char namebuf[64];
>
> - if (node == 0 || node == -1) {
> + if (node == 0 || node == NUMA_NO_NODE) {
> strcpy(namebuf, "???");
> } else {
> prom_getstring(node, "name", namebuf, sizeof(namebuf));
> @@ -625,7 +625,7 @@ void pcibios_fixup_bus(struct pci_bus *bus)
> list_for_each_entry(dev, &bus->devices, bus_list) {
> node = pdev_to_pnode(&pcic->pbm, dev);
> if(node == 0)
> - node = -1;
> + node = NUMA_NO_NODE;
>
> /* cookies */
> pcp = pci_devcookie_alloc();
> diff --git a/arch/sparc/kernel/psycho_common.c b/arch/sparc/kernel/psycho_common.c
> index 81aa91e..dcbf492 100644
> --- a/arch/sparc/kernel/psycho_common.c
> +++ b/arch/sparc/kernel/psycho_common.c
> @@ -454,7 +454,7 @@ void psycho_pbm_init_common(struct pci_pbm_info *pbm, struct platform_device *op
> struct device_node *dp = op->dev.of_node;
>
> pbm->name = dp->full_name;
> - pbm->numa_node = -1;
> + pbm->numa_node = NUMA_NO_NODE;
> pbm->chip_type = chip_type;
> pbm->chip_version = of_getintprop_default(dp, "version#", 0);
> pbm->chip_revision = of_getintprop_default(dp, "module-revision#", 0);
> diff --git a/arch/sparc/kernel/sbus.c b/arch/sparc/kernel/sbus.c
> index c133dfc..28a4aa9 100644
> --- a/arch/sparc/kernel/sbus.c
> +++ b/arch/sparc/kernel/sbus.c
> @@ -561,7 +561,7 @@ static void __init sbus_iommu_init(struct platform_device *op)
>
> op->dev.archdata.iommu = iommu;
> op->dev.archdata.stc = strbuf;
> - op->dev.archdata.numa_node = -1;
> + op->dev.archdata.numa_node = NUMA_NO_NODE;
>
> reg_base = regs + SYSIO_IOMMUREG_BASE;
> iommu->iommu_control = reg_base + IOMMU_CONTROL;
> diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c
> index 3c8aac2..cb1bed1 100644
> --- a/arch/sparc/mm/init_64.c
> +++ b/arch/sparc/mm/init_64.c
> @@ -976,13 +976,13 @@ static u64 __init memblock_nid_range_sun4u(u64 start, u64 end, int *nid)
> {
> int prev_nid, new_nid;
>
> - prev_nid = -1;
> + prev_nid = NUMA_NO_NODE;
> for ( ; start < end; start += PAGE_SIZE) {
> for (new_nid = 0; new_nid < num_node_masks; new_nid++) {
> struct node_mem_mask *p = &node_masks[new_nid];
>
> if ((start & p->mask) == p->match) {
> - if (prev_nid == -1)
> + if (prev_nid == NUMA_NO_NODE)
> prev_nid = new_nid;
> break;
> }
> @@ -1208,7 +1208,7 @@ int of_node_to_nid(struct device_node *dp)
> md = mdesc_grab();
>
> count = 0;
> - nid = -1;
> + nid = NUMA_NO_NODE;
> mdesc_for_each_node_by_name(md, grp, "group") {
> if (!scan_arcs_for_cfg_handle(md, grp, cfg_handle)) {
> nid = count;
> diff --git a/arch/sparc/prom/init_32.c b/arch/sparc/prom/init_32.c
> index d204701..4c6e540 100644
> --- a/arch/sparc/prom/init_32.c
> +++ b/arch/sparc/prom/init_32.c
> @@ -58,7 +58,7 @@ void __init prom_init(struct linux_romvec *rp)
> prom_nodeops = romvec->pv_nodeops;
>
> prom_root_node = prom_getsibling(0);
> - if ((prom_root_node == 0) || ((s32)prom_root_node == -1))
> + if ((prom_root_node == 0) || ((s32)prom_root_node == NUMA_NO_NODE))
> prom_halt();
>
> if((((unsigned long) prom_nodeops) == 0) ||
> diff --git a/arch/sparc/prom/init_64.c b/arch/sparc/prom/init_64.c
> index 103aa91..85669c0 100644
> --- a/arch/sparc/prom/init_64.c
> +++ b/arch/sparc/prom/init_64.c
> @@ -36,13 +36,13 @@ void __init prom_init(void *cif_handler)
> prom_cif_init(cif_handler);
>
> prom_chosen_node = prom_finddevice(prom_chosen_path);
> - if (!prom_chosen_node || (s32)prom_chosen_node == -1)
> + if (!prom_chosen_node || (s32)prom_chosen_node == NUMA_NO_NODE)
> prom_halt();
>
> prom_stdout = prom_getint(prom_chosen_node, "stdout");
>
> node = prom_finddevice("/openprom");
> - if (!node || (s32)node == -1)
> + if (!node || (s32)node == NUMA_NO_NODE)
> prom_halt();
>
> prom_getstring(node, "version", prom_version, sizeof(prom_version));
> diff --git a/arch/sparc/prom/tree_32.c b/arch/sparc/prom/tree_32.c
> index 0fed893..2d0a204 100644
> --- a/arch/sparc/prom/tree_32.c
> +++ b/arch/sparc/prom/tree_32.c
> @@ -41,11 +41,11 @@ phandle prom_getchild(phandle node)
> {
> phandle cnode;
>
> - if ((s32)node == -1)
> + if ((s32)node == NUMA_NO_NODE)
> return 0;
>
> cnode = __prom_getchild(node);
> - if (cnode == 0 || (s32)cnode == -1)
> + if (cnode == 0 || (s32)cnode == NUMA_NO_NODE)
> return 0;
>
> return cnode;
> @@ -73,11 +73,11 @@ phandle prom_getsibling(phandle node)
> {
> phandle sibnode;
>
> - if ((s32)node == -1)
> + if ((s32)node == NUMA_NO_NODE)
> return 0;
>
> sibnode = __prom_getsibling(node);
> - if (sibnode == 0 || (s32)sibnode == -1)
> + if (sibnode == 0 || (s32)sibnode == NUMA_NO_NODE)
> return 0;
>
> return sibnode;
> @@ -220,7 +220,7 @@ static char *__prom_nextprop(phandle node, char * oprop)
> */
> char *prom_nextprop(phandle node, char *oprop, char *buffer)
> {
> - if (node == 0 || (s32)node == -1)
> + if (node == 0 || (s32)node == NUMA_NO_NODE)
> return "";
>
> return __prom_nextprop(node, oprop);
> @@ -304,7 +304,7 @@ phandle prom_inst2pkg(int inst)
> node = (*romvec->pv_v2devops.v2_inst2pkg)(inst);
> restore_current();
> spin_unlock_irqrestore(&prom_lock, flags);
> - if ((s32)node == -1)
> + if ((s32)node == NUMA_NO_NODE)
> return 0;
> return node;
> }
> diff --git a/arch/sparc/prom/tree_64.c b/arch/sparc/prom/tree_64.c
> index 989e799..2b4c515 100644
> --- a/arch/sparc/prom/tree_64.c
> +++ b/arch/sparc/prom/tree_64.c
> @@ -44,10 +44,10 @@ phandle prom_getchild(phandle node)
> {
> phandle cnode;
>
> - if ((s32)node == -1)
> + if ((s32)node == NUMA_NO_NODE)
> return 0;
> cnode = __prom_getchild(node);
> - if ((s32)cnode == -1)
> + if ((s32)cnode == NUMA_NO_NODE)
> return 0;
> return cnode;
> }
> @@ -57,10 +57,10 @@ inline phandle prom_getparent(phandle node)
> {
> phandle cnode;
>
> - if ((s32)node == -1)
> + if ((s32)node == NUMA_NO_NODE)
> return 0;
> cnode = prom_node_to_node("parent", node);
> - if ((s32)cnode == -1)
> + if ((s32)cnode == NUMA_NO_NODE)
> return 0;
> return cnode;
> }
> @@ -77,10 +77,10 @@ phandle prom_getsibling(phandle node)
> {
> phandle sibnode;
>
> - if ((s32)node == -1)
> + if ((s32)node == NUMA_NO_NODE)
> return 0;
> sibnode = __prom_getsibling(node);
> - if ((s32)sibnode == -1)
> + if ((s32)sibnode == NUMA_NO_NODE)
> return 0;
>
> return sibnode;
> @@ -241,7 +241,7 @@ char *prom_firstprop(phandle node, char *buffer)
> unsigned long args[7];
>
> *buffer = 0;
> - if ((s32)node == -1)
> + if ((s32)node == NUMA_NO_NODE)
> return buffer;
>
> args[0] = (unsigned long) prom_nextprop_name;
> @@ -267,7 +267,7 @@ char *prom_nextprop(phandle node, const char *oprop, char *buffer)
> unsigned long args[7];
> char buf[32];
>
> - if ((s32)node == -1) {
> + if ((s32)node == NUMA_NO_NODE) {
> *buffer = 0;
> return buffer;
> }
> @@ -370,7 +370,7 @@ inline phandle prom_inst2pkg(int inst)
> p1275_cmd_direct(args);
>
> node = (int) args[4];
> - if ((s32)node == -1)
> + if ((s32)node == NUMA_NO_NODE)
> return 0;
> return node;
> }
> diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h
> index 6629636..dee2a31 100644
> --- a/arch/x86/include/asm/pci.h
> +++ b/arch/x86/include/asm/pci.h
> @@ -141,7 +141,7 @@ cpumask_of_pcibus(const struct pci_bus *bus)
> int node;
>
> node = __pcibus_to_node(bus);
> - return (node == -1) ? cpu_online_mask :
> + return (node == NUMA_NO_NODE) ? cpu_online_mask :
> cpumask_of_node(node);
> }
> #endif
> diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
> index 391f358..3c3378a 100644
> --- a/arch/x86/kernel/apic/x2apic_uv_x.c
> +++ b/arch/x86/kernel/apic/x2apic_uv_x.c
> @@ -1390,7 +1390,7 @@ static void __init build_socket_tables(void)
> }
>
> /* Set socket -> node values: */
> - lnid = -1;
> + lnid = NUMA_NO_NODE;
> for_each_present_cpu(cpu) {
> int nid = cpu_to_node(cpu);
> int apicid, sockid;
> @@ -1521,7 +1521,7 @@ static void __init uv_system_init_hub(void)
> new_hub->pnode = 0xffff;
>
> new_hub->numa_blade_id = uv_node_to_blade_id(nodeid);
> - new_hub->memory_nid = -1;
> + new_hub->memory_nid = NUMA_NO_NODE;
> new_hub->nr_possible_cpus = 0;
> new_hub->nr_online_cpus = 0;
> }
> @@ -1538,7 +1538,7 @@ static void __init uv_system_init_hub(void)
>
> uv_cpu_info_per(cpu)->p_uv_hub_info = uv_hub_info_list(nodeid);
> uv_cpu_info_per(cpu)->blade_cpu_id = uv_cpu_hub_info(cpu)->nr_possible_cpus++;
> - if (uv_cpu_hub_info(cpu)->memory_nid == -1)
> + if (uv_cpu_hub_info(cpu)->memory_nid == NUMA_NO_NODE)
> uv_cpu_hub_info(cpu)->memory_nid = cpu_to_node(cpu);
>
> /* Init memoryless node: */
> diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
> index a9134d1..c1d45dc 100644
> --- a/arch/x86/kernel/smpboot.c
> +++ b/arch/x86/kernel/smpboot.c
> @@ -841,7 +841,7 @@ wakeup_secondary_cpu_via_init(int phys_apicid, unsigned long start_eip)
> /* reduce the number of lines printed when booting a large cpu count system */
> static void announce_cpu(int cpu, int apicid)
> {
> - static int current_node = -1;
> + static int current_node = NUMA_NO_NODE;
> int node = early_cpu_to_node(cpu);
> static int width, node_width;
>
> diff --git a/arch/x86/platform/olpc/olpc_dt.c b/arch/x86/platform/olpc/olpc_dt.c
> index 24d2175..7098127 100644
> --- a/arch/x86/platform/olpc/olpc_dt.c
> +++ b/arch/x86/platform/olpc/olpc_dt.c
> @@ -29,10 +29,10 @@ static phandle __init olpc_dt_getsibling(phandle node)
> const void *args[] = { (void *)node };
> void *res[] = { &node };
>
> - if ((s32)node == -1)
> + if ((s32)node == NUMA_NO_NODE)
> return 0;
>
> - if (olpc_ofw("peer", args, res) || (s32)node == -1)
> + if (olpc_ofw("peer", args, res) || (s32)node == NUMA_NO_NODE)
> return 0;
>
> return node;
> @@ -43,10 +43,10 @@ static phandle __init olpc_dt_getchild(phandle node)
> const void *args[] = { (void *)node };
> void *res[] = { &node };
>
> - if ((s32)node == -1)
> + if ((s32)node == NUMA_NO_NODE)
> return 0;
>
> - if (olpc_ofw("child", args, res) || (s32)node == -1) {
> + if (olpc_ofw("child", args, res) || (s32)node == NUMA_NO_NODE) {
> pr_err("PROM: %s: fetching child failed!\n", __func__);
> return 0;
> }
> @@ -60,7 +60,7 @@ static int __init olpc_dt_getproplen(phandle node, const char *prop)
> int len;
> void *res[] = { &len };
>
> - if ((s32)node == -1)
> + if ((s32)node == NUMA_NO_NODE)
> return -1;
>
> if (olpc_ofw("getproplen", args, res)) {
> @@ -100,7 +100,7 @@ static int __init olpc_dt_nextprop(phandle node, char *prev, char *buf)
>
> buf[0] = '\0';
>
> - if ((s32)node == -1)
> + if ((s32)node == NUMA_NO_NODE)
> return -1;
>
> if (olpc_ofw("nextprop", args, res) || success != 1)
> @@ -115,7 +115,7 @@ static int __init olpc_dt_pkg2path(phandle node, char *buf,
> const void *args[] = { (void *)node, buf, (void *)buflen };
> void *res[] = { len };
>
> - if ((s32)node == -1)
> + if ((s32)node == NUMA_NO_NODE)
> return -1;
>
> if (olpc_ofw("package-to-path", args, res) || *len < 1)
> @@ -176,7 +176,7 @@ static phandle __init olpc_dt_finddevice(const char *path)
> return 0;
> }
>
> - if ((s32) node == -1)
> + if ((s32) node == NUMA_NO_NODE)
> return 0;
>
> return node;
> diff --git a/drivers/block/mtip32xx/mtip32xx.c b/drivers/block/mtip32xx/mtip32xx.c
> index a7daa8a..b889452 100644
> --- a/drivers/block/mtip32xx/mtip32xx.c
> +++ b/drivers/block/mtip32xx/mtip32xx.c
> @@ -4084,9 +4084,9 @@ static int get_least_used_cpu_on_node(int node)
> /* Helper for selecting a node in round robin mode */
> static inline int mtip_get_next_rr_node(void)
> {
> - static int next_node = -1;
> + static int next_node = NUMA_NO_NODE;
>
> - if (next_node == -1) {
> + if (next_node == NUMA_NO_NODE) {
> next_node = first_online_node;
> return next_node;
> }
> diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c
> index f1a441ab..1aeefc7 100644
> --- a/drivers/dma/dmaengine.c
> +++ b/drivers/dma/dmaengine.c
> @@ -386,7 +386,8 @@ EXPORT_SYMBOL(dma_issue_pending_all);
> static bool dma_chan_is_local(struct dma_chan *chan, int cpu)
> {
> int node = dev_to_node(chan->device->dev);
> - return node == -1 || cpumask_test_cpu(cpu, cpumask_of_node(node));
> + return node == NUMA_NO_NODE ||
> + cpumask_test_cpu(cpu, cpumask_of_node(node));
> }
>
> /**
> diff --git a/drivers/infiniband/hw/hfi1/affinity.c b/drivers/infiniband/hw/hfi1/affinity.c
> index 2baf38c..3e8acb8 100644
> --- a/drivers/infiniband/hw/hfi1/affinity.c
> +++ b/drivers/infiniband/hw/hfi1/affinity.c
> @@ -777,7 +777,7 @@ void hfi1_dev_affinity_clean_up(struct hfi1_devdata *dd)
> _dev_comp_vect_cpu_mask_clean_up(dd, entry);
> unlock:
> mutex_unlock(&node_affinity.lock);
> - dd->node = -1;
> + dd->node = NUMA_NO_NODE;
> }
>
> /*
> diff --git a/drivers/infiniband/hw/hfi1/init.c b/drivers/infiniband/hw/hfi1/init.c
> index 0904490..0bf4577 100644
> --- a/drivers/infiniband/hw/hfi1/init.c
> +++ b/drivers/infiniband/hw/hfi1/init.c
> @@ -1303,7 +1303,7 @@ static struct hfi1_devdata *hfi1_alloc_devdata(struct pci_dev *pdev,
> dd->unit = ret;
> list_add(&dd->list, &hfi1_dev_list);
> }
> - dd->node = -1;
> + dd->node = NUMA_NO_NODE;
>
> spin_unlock_irqrestore(&hfi1_devs_lock, flags);
> idr_preload_end();
> diff --git a/drivers/iommu/dmar.c b/drivers/iommu/dmar.c
> index d9c748b..86a9c19 100644
> --- a/drivers/iommu/dmar.c
> +++ b/drivers/iommu/dmar.c
> @@ -477,7 +477,7 @@ static int dmar_parse_one_rhsa(struct acpi_dmar_header *header, void *arg)
> int node = acpi_map_pxm_to_node(rhsa->proximity_domain);
>
> if (!node_online(node))
> - node = -1;
> + node = NUMA_NO_NODE;
> drhd->iommu->node = node;
> return 0;
> }
> @@ -1062,7 +1062,7 @@ static int alloc_iommu(struct dmar_drhd_unit *drhd)
> iommu->msagaw = msagaw;
> iommu->segment = drhd->segment;
>
> - iommu->node = -1;
> + iommu->node = NUMA_NO_NODE;
>
> ver = readl(iommu->reg + DMAR_VER_REG);
> pr_info("%s: reg_base_addr %llx ver %d:%d cap %llx ecap %llx\n",
> diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
> index f3ccf02..9f6fb13 100644
> --- a/drivers/iommu/intel-iommu.c
> +++ b/drivers/iommu/intel-iommu.c
> @@ -1772,7 +1772,7 @@ static struct dmar_domain *alloc_domain(int flags)
> return NULL;
>
> memset(domain, 0, sizeof(*domain));
> - domain->nid = -1;
> + domain->nid = NUMA_NO_NODE;
> domain->flags = flags;
> domain->has_iotlb_device = false;
> INIT_LIST_HEAD(&domain->devices);
> diff --git a/drivers/media/pci/ivtv/ivtvfb.c b/drivers/media/pci/ivtv/ivtvfb.c
> index 3e02de0..81bd41c 100644
> --- a/drivers/media/pci/ivtv/ivtvfb.c
> +++ b/drivers/media/pci/ivtv/ivtvfb.c
> @@ -1054,7 +1054,7 @@ static int ivtvfb_init_vidmode(struct ivtv *itv)
>
> /* Generate valid fb_info */
>
> - oi->ivtvfb_info.node = -1;
> + oi->ivtvfb_info.node = NUMA_NO_NODE;
> oi->ivtvfb_info.flags = FBINFO_FLAG_DEFAULT;
> oi->ivtvfb_info.fbops = &ivtvfb_ops;
> oi->ivtvfb_info.par = itv;
> diff --git a/drivers/media/platform/vivid/vivid-osd.c b/drivers/media/platform/vivid/vivid-osd.c
> index 1a89593..56a2d41 100644
> --- a/drivers/media/platform/vivid/vivid-osd.c
> +++ b/drivers/media/platform/vivid/vivid-osd.c
> @@ -309,7 +309,7 @@ static int vivid_fb_init_vidmode(struct vivid_dev *dev)
>
> /* Generate valid fb_info */
>
> - dev->fb_info.node = -1;
> + dev->fb_info.node = NUMA_NO_NODE;
> dev->fb_info.flags = FBINFO_FLAG_DEFAULT;
> dev->fb_info.fbops = &vivid_fb_ops;
> dev->fb_info.par = dev;
> diff --git a/drivers/misc/sgi-xp/xpc_uv.c b/drivers/misc/sgi-xp/xpc_uv.c
> index 0441abe..eef36dd 100644
> --- a/drivers/misc/sgi-xp/xpc_uv.c
> +++ b/drivers/misc/sgi-xp/xpc_uv.c
> @@ -61,7 +61,7 @@ static struct xpc_heartbeat_uv *xpc_heartbeat_uv;
> XPC_NOTIFY_MSG_SIZE_UV)
> #define XPC_NOTIFY_IRQ_NAME "xpc_notify"
>
> -static int xpc_mq_node = -1;
> +static int xpc_mq_node = NUMA_NO_NODE;
>
> static struct xpc_gru_mq_uv *xpc_activate_mq_uv;
> static struct xpc_gru_mq_uv *xpc_notify_mq_uv;
> diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
> index 113b38e..4fae85c 100644
> --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
> +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
> @@ -6414,7 +6414,7 @@ int ixgbe_setup_tx_resources(struct ixgbe_ring *tx_ring)
> {
> struct device *dev = tx_ring->dev;
> int orig_node = dev_to_node(dev);
> - int ring_node = -1;
> + int ring_node = NUMA_NO_NODE;
> int size;
>
> size = sizeof(struct ixgbe_tx_buffer) * tx_ring->count;
> @@ -6508,7 +6508,7 @@ int ixgbe_setup_rx_resources(struct ixgbe_adapter *adapter,
> {
> struct device *dev = rx_ring->dev;
> int orig_node = dev_to_node(dev);
> - int ring_node = -1;
> + int ring_node = NUMA_NO_NODE;
> int size;
>
> size = sizeof(struct ixgbe_rx_buffer) * rx_ring->count;
> diff --git a/drivers/video/fbdev/mmp/fb/mmpfb.c b/drivers/video/fbdev/mmp/fb/mmpfb.c
> index ee212be..298be9b 100644
> --- a/drivers/video/fbdev/mmp/fb/mmpfb.c
> +++ b/drivers/video/fbdev/mmp/fb/mmpfb.c
> @@ -519,7 +519,7 @@ static int fb_info_setup(struct fb_info *info,
> /* Initialise static fb parameters.*/
> info->flags = FBINFO_DEFAULT | FBINFO_PARTIAL_PAN_OK |
> FBINFO_HWACCEL_XPAN | FBINFO_HWACCEL_YPAN;
> - info->node = -1;
> + info->node = NUMA_NO_NODE;
> strcpy(info->fix.id, fbi->name);
> info->fix.type = FB_TYPE_PACKED_PIXELS;
> info->fix.type_aux = 0;
> diff --git a/drivers/video/fbdev/pxa168fb.c b/drivers/video/fbdev/pxa168fb.c
> index e31340f..7d775de 100644
> --- a/drivers/video/fbdev/pxa168fb.c
> +++ b/drivers/video/fbdev/pxa168fb.c
> @@ -649,7 +649,7 @@ static int pxa168fb_probe(struct platform_device *pdev)
> */
> info->flags = FBINFO_DEFAULT | FBINFO_PARTIAL_PAN_OK |
> FBINFO_HWACCEL_XPAN | FBINFO_HWACCEL_YPAN;
> - info->node = -1;
> + info->node = NUMA_NO_NODE;
> strlcpy(info->fix.id, mi->id, 16);
> info->fix.type = FB_TYPE_PACKED_PIXELS;
> info->fix.type_aux = 0;
> diff --git a/drivers/video/fbdev/w100fb.c b/drivers/video/fbdev/w100fb.c
> index 696106e..8b0f20c 100644
> --- a/drivers/video/fbdev/w100fb.c
> +++ b/drivers/video/fbdev/w100fb.c
> @@ -703,7 +703,7 @@ int w100fb_probe(struct platform_device *pdev)
> info->fbops = &w100fb_ops;
> info->flags = FBINFO_DEFAULT | FBINFO_HWACCEL_COPYAREA |
> FBINFO_HWACCEL_FILLRECT;
> - info->node = -1;
> + info->node = NUMA_NO_NODE;
> info->screen_base = remapped_fbuf + (W100_FB_BASE-MEM_WINDOW_BASE);
> info->screen_size = REMAPPED_FB_LEN;
>
> diff --git a/fs/ocfs2/dlm/dlmcommon.h b/fs/ocfs2/dlm/dlmcommon.h
> index d06e27e..11111f6 100644
> --- a/fs/ocfs2/dlm/dlmcommon.h
> +++ b/fs/ocfs2/dlm/dlmcommon.h
> @@ -1121,7 +1121,7 @@ static inline void dlm_node_iter_init(unsigned long *map,
> struct dlm_node_iter *iter)
> {
> memcpy(iter->node_map, map, sizeof(iter->node_map));
> - iter->curnode = -1;
> + iter->curnode = NUMA_NO_NODE;
> }
>
> static inline int dlm_node_iter_next(struct dlm_node_iter *iter)
> diff --git a/fs/ocfs2/dlm/dlmdomain.c b/fs/ocfs2/dlm/dlmdomain.c
> index 2acd58b..381a323 100644
> --- a/fs/ocfs2/dlm/dlmdomain.c
> +++ b/fs/ocfs2/dlm/dlmdomain.c
> @@ -546,7 +546,7 @@ static void dlm_mark_domain_leaving(struct dlm_ctxt *dlm)
>
> static void __dlm_print_nodes(struct dlm_ctxt *dlm)
> {
> - int node = -1, num = 0;
> + int node = NUMA_NO_NODE, num = 0;
>
> assert_spin_locked(&dlm->spinlock);
>
> @@ -613,7 +613,7 @@ static int dlm_send_one_domain_exit(struct dlm_ctxt *dlm, u32 msg_type,
>
> static void dlm_begin_exit_domain(struct dlm_ctxt *dlm)
> {
> - int node = -1;
> + int node = NUMA_NO_NODE;
>
> /* Support for begin exit domain was added in 1.2 */
> if (dlm->dlm_locking_proto.pv_major == 1 &&
> @@ -1407,7 +1407,7 @@ static int dlm_send_join_cancels(struct dlm_ctxt *dlm,
> }
>
> status = 0;
> - node = -1;
> + node = NUMA_NO_NODE;
> while ((node = find_next_bit(node_map, O2NM_MAX_NODES,
> node + 1)) < O2NM_MAX_NODES) {
> if (node == dlm->node_num)
> @@ -1547,7 +1547,7 @@ static void dlm_send_join_asserts(struct dlm_ctxt *dlm,
> int status, node, live;
>
> status = 0;
> - node = -1;
> + node = NUMA_NO_NODE;
> while ((node = find_next_bit(node_map, O2NM_MAX_NODES,
> node + 1)) < O2NM_MAX_NODES) {
> if (node == dlm->node_num)
> @@ -1631,7 +1631,7 @@ static int dlm_try_to_join_domain(struct dlm_ctxt *dlm)
>
> spin_unlock(&dlm->spinlock);
>
> - node = -1;
> + node = NUMA_NO_NODE;
> while ((node = find_next_bit(ctxt->live_map, O2NM_MAX_NODES,
> node + 1)) < O2NM_MAX_NODES) {
> if (node == dlm->node_num)
> diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c
> index 826f056..e54bbbc 100644
> --- a/fs/ocfs2/dlm/dlmmaster.c
> +++ b/fs/ocfs2/dlm/dlmmaster.c
> @@ -1183,7 +1183,7 @@ static void dlm_bitmap_diff_iter_init(struct dlm_bitmap_diff_iter *iter,
> unsigned long p1, p2;
> int i;
>
> - iter->curnode = -1;
> + iter->curnode = NUMA_NO_NODE;
> iter->orig_bm = orig_bm;
> iter->cur_bm = cur_bm;
>
> diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c
> index 802636d5..704fa8b 100644
> --- a/fs/ocfs2/dlm/dlmrecovery.c
> +++ b/fs/ocfs2/dlm/dlmrecovery.c
> @@ -2903,7 +2903,7 @@ static int dlm_send_finalize_reco_message(struct dlm_ctxt *dlm)
> }
> if (stage == 1) {
> /* reset the node_iter back to the top and send finalize2 */
> - iter.curnode = -1;
> + iter.curnode = NUMA_NO_NODE;
> stage = 2;
> goto stage2;
> }
> diff --git a/fs/ocfs2/stack_user.c b/fs/ocfs2/stack_user.c
> index d2fb97b..a673efa 100644
> --- a/fs/ocfs2/stack_user.c
> +++ b/fs/ocfs2/stack_user.c
> @@ -171,7 +171,7 @@ union ocfs2_control_message {
> static struct ocfs2_stack_plugin ocfs2_user_plugin;
>
> static atomic_t ocfs2_control_opened;
> -static int ocfs2_control_this_node = -1;
> +static int ocfs2_control_this_node = NUMA_NO_NODE;
> static struct ocfs2_protocol_version running_proto;
>
> static LIST_HEAD(ocfs2_live_connection_list);
> @@ -589,7 +589,7 @@ static int ocfs2_control_release(struct inode *inode, struct file *file)
> * Last valid close clears the node number and resets
> * the locking protocol version
> */
> - ocfs2_control_this_node = -1;
> + ocfs2_control_this_node = NUMA_NO_NODE;
> running_proto.pv_major = 0;
> running_proto.pv_minor = 0;
> }
> @@ -612,7 +612,7 @@ static int ocfs2_control_open(struct inode *inode, struct file *file)
> p = kzalloc(sizeof(struct ocfs2_control_private), GFP_KERNEL);
> if (!p)
> return -ENOMEM;
> - p->op_this_node = -1;
> + p->op_this_node = NUMA_NO_NODE;
>
> mutex_lock(&ocfs2_control_lock);
> file->private_data = p;
> diff --git a/init/init_task.c b/init/init_task.c
> index 5aebe3b..6641836 100644
> --- a/init/init_task.c
> +++ b/init/init_task.c
> @@ -154,7 +154,7 @@ struct task_struct init_task
> .vtime.state = VTIME_SYS,
> #endif
> #ifdef CONFIG_NUMA_BALANCING
> - .numa_preferred_nid = -1,
> + .numa_preferred_nid = NUMA_NO_NODE,
> .numa_group = NULL,
> .numa_faults = NULL,
> #endif
> diff --git a/kernel/kthread.c b/kernel/kthread.c
> index 087d18d..77f3d94 100644
> --- a/kernel/kthread.c
> +++ b/kernel/kthread.c
> @@ -675,7 +675,7 @@ __kthread_create_worker(int cpu, unsigned int flags,
> {
> struct kthread_worker *worker;
> struct task_struct *task;
> - int node = -1;
> + int node = NUMA_NO_NODE;
>
> worker = kzalloc(sizeof(*worker), GFP_KERNEL);
> if (!worker)
> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> index ee271bb..d830fa7 100644
> --- a/kernel/sched/fair.c
> +++ b/kernel/sched/fair.c
> @@ -1161,7 +1161,7 @@ void init_numa_balancing(unsigned long clone_flags, struct task_struct *p)
>
> /* New address space, reset the preferred nid */
> if (!(clone_flags & CLONE_VM)) {
> - p->numa_preferred_nid = -1;
> + p->numa_preferred_nid = NUMA_NO_NODE;
> return;
> }
>
> @@ -1181,13 +1181,13 @@ void init_numa_balancing(unsigned long clone_flags, struct task_struct *p)
>
> static void account_numa_enqueue(struct rq *rq, struct task_struct *p)
> {
> - rq->nr_numa_running += (p->numa_preferred_nid != -1);
> + rq->nr_numa_running += (p->numa_preferred_nid != NUMA_NO_NODE);
> rq->nr_preferred_running += (p->numa_preferred_nid == task_node(p));
> }
>
> static void account_numa_dequeue(struct rq *rq, struct task_struct *p)
> {
> - rq->nr_numa_running -= (p->numa_preferred_nid != -1);
> + rq->nr_numa_running -= (p->numa_preferred_nid != NUMA_NO_NODE);
> rq->nr_preferred_running -= (p->numa_preferred_nid == task_node(p));
> }
>
> @@ -1401,7 +1401,7 @@ bool should_numa_migrate_memory(struct task_struct *p, struct page * page,
> * two full passes of the "multi-stage node selection" test that is
> * executed below.
> */
> - if ((p->numa_preferred_nid == -1 || p->numa_scan_seq <= 4) &&
> + if ((p->numa_preferred_nid == NUMA_NO_NODE || p->numa_scan_seq <= 4) &&
> (cpupid_pid_unset(last_cpupid) || cpupid_match_pid(p, last_cpupid)))
> return true;
>
> @@ -1849,7 +1849,7 @@ static void numa_migrate_preferred(struct task_struct *p)
> unsigned long interval = HZ;
>
> /* This task has no NUMA fault statistics yet */
> - if (unlikely(p->numa_preferred_nid == -1 || !p->numa_faults))
> + if (unlikely(p->numa_preferred_nid == NUMA_NO_NODE || !p->numa_faults))
> return;
>
> /* Periodically retry migrating the task to the preferred node */
> @@ -2096,7 +2096,7 @@ static int preferred_group_nid(struct task_struct *p, int nid)
>
> static void task_numa_placement(struct task_struct *p)
> {
> - int seq, nid, max_nid = -1;
> + int seq, nid, max_nid = NUMA_NO_NODE;
> unsigned long max_faults = 0;
> unsigned long fault_types[2] = { 0, 0 };
> unsigned long total_faults;
> @@ -2639,7 +2639,8 @@ static void update_scan_period(struct task_struct *p, int new_cpu)
> * the preferred node.
> */
> if (dst_nid == p->numa_preferred_nid ||
> - (p->numa_preferred_nid != -1 && src_nid != p->numa_preferred_nid))
> + (p->numa_preferred_nid != NUMA_NO_NODE &&
> + src_nid != p->numa_preferred_nid))
> return;
> }
>
> diff --git a/lib/cpumask.c b/lib/cpumask.c
> index 8d666ab..a089c3f 100644
> --- a/lib/cpumask.c
> +++ b/lib/cpumask.c
> @@ -206,7 +206,7 @@ unsigned int cpumask_local_spread(unsigned int i, int node)
> /* Wrap: we always want a cpu. */
> i %= num_online_cpus();
>
> - if (node == -1) {
> + if (node == NUMA_NO_NODE) {
> for_each_cpu(cpu, cpu_online_mask)
> if (i-- == 0)
> return cpu;
> diff --git a/mm/huge_memory.c b/mm/huge_memory.c
> index 55478ab..5ccf89e 100644
> --- a/mm/huge_memory.c
> +++ b/mm/huge_memory.c
> @@ -1480,7 +1480,7 @@ vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t pmd)
> struct anon_vma *anon_vma = NULL;
> struct page *page;
> unsigned long haddr = vmf->address & HPAGE_PMD_MASK;
> - int page_nid = -1, this_nid = numa_node_id();
> + int page_nid = NUMA_NO_NODE, this_nid = numa_node_id();
> int target_nid, last_cpupid = -1;
> bool page_locked;
> bool migrated = false;
> @@ -1526,7 +1526,7 @@ vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t pmd)
> */
> page_locked = trylock_page(page);
> target_nid = mpol_misplaced(page, vma, haddr);
> - if (target_nid == -1) {
> + if (target_nid == NUMA_NO_NODE) {
> /* If the page was locked, there are no parallel migrations */
> if (page_locked)
> goto clear_pmdnuma;
> @@ -1534,7 +1534,7 @@ vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t pmd)
>
> /* Migration could have started since the pmd_trans_migrating check */
> if (!page_locked) {
> - page_nid = -1;
> + page_nid = NUMA_NO_NODE;
> if (!get_page_unless_zero(page))
> goto out_unlock;
> spin_unlock(vmf->ptl);
> @@ -1556,14 +1556,14 @@ vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t pmd)
> if (unlikely(!pmd_same(pmd, *vmf->pmd))) {
> unlock_page(page);
> put_page(page);
> - page_nid = -1;
> + page_nid = NUMA_NO_NODE;
> goto out_unlock;
> }
>
> /* Bail if we fail to protect against THP splits for any reason */
> if (unlikely(!anon_vma)) {
> put_page(page);
> - page_nid = -1;
> + page_nid = NUMA_NO_NODE;
> goto clear_pmdnuma;
> }
>
> @@ -1625,7 +1625,7 @@ vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t pmd)
> if (anon_vma)
> page_unlock_anon_vma_read(anon_vma);
>
> - if (page_nid != -1)
> + if (page_nid != NUMA_NO_NODE)
> task_numa_fault(last_cpupid, page_nid, HPAGE_PMD_NR,
> flags);
>
> diff --git a/mm/hugetlb.c b/mm/hugetlb.c
> index c007fb5..b769db7 100644
> --- a/mm/hugetlb.c
> +++ b/mm/hugetlb.c
> @@ -887,7 +887,7 @@ static struct page *dequeue_huge_page_nodemask(struct hstate *h, gfp_t gfp_mask,
> struct zonelist *zonelist;
> struct zone *zone;
> struct zoneref *z;
> - int node = -1;
> + int node = NUMA_NO_NODE;
>
> zonelist = node_zonelist(nid, gfp_mask);
>
> diff --git a/mm/ksm.c b/mm/ksm.c
> index 5b0894b..d5f8834 100644
> --- a/mm/ksm.c
> +++ b/mm/ksm.c
> @@ -597,7 +597,7 @@ static struct stable_node *alloc_stable_node_chain(struct stable_node *dup,
> chain->chain_prune_time = jiffies;
> chain->rmap_hlist_len = STABLE_NODE_CHAIN;
> #if defined (CONFIG_DEBUG_VM) && defined(CONFIG_NUMA)
> - chain->nid = -1; /* debug */
> + chain->nid = NUMA_NO_NODE; /* debug */
> #endif
> ksm_stable_node_chains++;
>
> diff --git a/mm/memory.c b/mm/memory.c
> index 4ad2d29..c0e0348 100644
> --- a/mm/memory.c
> +++ b/mm/memory.c
> @@ -3564,7 +3564,7 @@ static vm_fault_t do_numa_page(struct vm_fault *vmf)
> {
> struct vm_area_struct *vma = vmf->vma;
> struct page *page = NULL;
> - int page_nid = -1;
> + int page_nid = NUMA_NO_NODE;
> int last_cpupid;
> int target_nid;
> bool migrated = false;
> @@ -3631,7 +3631,7 @@ static vm_fault_t do_numa_page(struct vm_fault *vmf)
> target_nid = numa_migrate_prep(page, vma, vmf->address, page_nid,
> &flags);
> pte_unmap_unlock(vmf->pte, vmf->ptl);
> - if (target_nid == -1) {
> + if (target_nid == NUMA_NO_NODE) {
> put_page(page);
> goto out;
> }
> @@ -3645,7 +3645,7 @@ static vm_fault_t do_numa_page(struct vm_fault *vmf)
> flags |= TNF_MIGRATE_FAIL;
>
> out:
> - if (page_nid != -1)
> + if (page_nid != NUMA_NO_NODE)
> task_numa_fault(last_cpupid, page_nid, 1, flags);
> return 0;
> }
> diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
> index 2b2b3cc..70e02f8 100644
> --- a/mm/memory_hotplug.c
> +++ b/mm/memory_hotplug.c
> @@ -688,9 +688,9 @@ static void node_states_check_changes_online(unsigned long nr_pages,
> {
> int nid = zone_to_nid(zone);
>
> - arg->status_change_nid = -1;
> - arg->status_change_nid_normal = -1;
> - arg->status_change_nid_high = -1;
> + arg->status_change_nid = NUMA_NO_NODE;
> + arg->status_change_nid_normal = NUMA_NO_NODE;
> + arg->status_change_nid_high = NUMA_NO_NODE;
>
> if (!node_state(nid, N_MEMORY))
> arg->status_change_nid = nid;
> @@ -1484,9 +1484,9 @@ static void node_states_check_changes_offline(unsigned long nr_pages,
> unsigned long present_pages = 0;
> enum zone_type zt;
>
> - arg->status_change_nid = -1;
> - arg->status_change_nid_normal = -1;
> - arg->status_change_nid_high = -1;
> + arg->status_change_nid = NUMA_NO_NODE;
> + arg->status_change_nid_normal = NUMA_NO_NODE;
> + arg->status_change_nid_high = NUMA_NO_NODE;
>
> /*
> * Check whether node_states[N_NORMAL_MEMORY] will be changed.
> diff --git a/mm/mempolicy.c b/mm/mempolicy.c
> index 5837a06..e4f8248 100644
> --- a/mm/mempolicy.c
> +++ b/mm/mempolicy.c
> @@ -2278,7 +2278,7 @@ int mpol_misplaced(struct page *page, struct vm_area_struct *vma, unsigned long
> unsigned long pgoff;
> int thiscpu = raw_smp_processor_id();
> int thisnid = cpu_to_node(thiscpu);
> - int polnid = -1;
> + int polnid = NUMA_NO_NODE;
> int ret = -1;
>
> pol = get_vma_policy(vma, addr);
> diff --git a/mm/page_alloc.c b/mm/page_alloc.c
> index a919ba5..9d38d9c 100644
> --- a/mm/page_alloc.c
> +++ b/mm/page_alloc.c
> @@ -5846,7 +5846,7 @@ int __meminit __early_pfn_to_nid(unsigned long pfn,
> return state->last_nid;
>
> nid = memblock_search_pfn_nid(pfn, &start_pfn, &end_pfn);
> - if (nid != -1) {
> + if (nid != NUMA_NO_NODE) {
> state->last_start = start_pfn;
> state->last_end = end_pfn;
> state->last_nid = nid;
> @@ -6607,7 +6607,7 @@ unsigned long __init node_map_pfn_alignment(void)
> {
> unsigned long accl_mask = 0, last_end = 0;
> unsigned long start, end, mask;
> - int last_nid = -1;
> + int last_nid = NUMA_NO_NODE;
> int i, nid;
>
> for_each_mem_pfn_range(i, MAX_NUMNODES, &start, &end, &nid) {
> diff --git a/mm/page_ext.c b/mm/page_ext.c
> index ae44f7a..dfb0206 100644
> --- a/mm/page_ext.c
> +++ b/mm/page_ext.c
> @@ -300,7 +300,7 @@ static int __meminit online_page_ext(unsigned long start_pfn,
> start = SECTION_ALIGN_DOWN(start_pfn);
> end = SECTION_ALIGN_UP(start_pfn + nr_pages);
>
> - if (nid == -1) {
> + if (nid == NUMA_NO_NODE) {
> /*
> * In this case, "nid" already exists and contains valid memory.
> * "start_pfn" passed to us is a pfn which is an arg for
> diff --git a/net/core/pktgen.c b/net/core/pktgen.c
> index 6ac9198..af3a746 100644
> --- a/net/core/pktgen.c
> +++ b/net/core/pktgen.c
> @@ -3625,7 +3625,7 @@ static int pktgen_add_device(struct pktgen_thread *t, const char *ifname)
> pkt_dev->svlan_cfi = 0;
> pkt_dev->svlan_id = 0xffff;
> pkt_dev->burst = 1;
> - pkt_dev->node = -1;
> + pkt_dev->node = NUMA_NO_NODE;
>
> err = pktgen_setup_dev(t->net, pkt_dev, ifname);
> if (err)
> diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c
> index 86e1e37..0c56ae2 100644
> --- a/net/qrtr/qrtr.c
> +++ b/net/qrtr/qrtr.c
> @@ -101,7 +101,7 @@ static inline struct qrtr_sock *qrtr_sk(struct sock *sk)
> return container_of(sk, struct qrtr_sock, sk);
> }
>
> -static unsigned int qrtr_local_nid = -1;
> +static unsigned int qrtr_local_nid = NUMA_NO_NODE;
>
> /* for node ids */
> static RADIX_TREE(qrtr_nodes, GFP_KERNEL);
> diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c
> index 4419551..e0ad5f1 100644
> --- a/tools/perf/bench/numa.c
> +++ b/tools/perf/bench/numa.c
> @@ -298,7 +298,7 @@ static cpu_set_t bind_to_node(int target_node)
>
> CPU_ZERO(&mask);
>
> - if (target_node == -1) {
> + if (target_node == NUMA_NO_NODE) {
> for (cpu = 0; cpu < g->p.nr_cpus; cpu++)
> CPU_SET(cpu, &mask);
> } else {
> @@ -339,7 +339,7 @@ static void bind_to_memnode(int node)
> unsigned long nodemask;
> int ret;
>
> - if (node == -1)
> + if (node == NUMA_NO_NODE)
> return;
>
> BUG_ON(g->p.nr_nodes > (int)sizeof(nodemask)*8);
> @@ -1363,7 +1363,7 @@ static void init_thread_data(void)
> int cpu;
>
> /* Allow all nodes by default: */
> - td->bind_node = -1;
> + td->bind_node = NUMA_NO_NODE;
>
> /* Allow all CPUs by default: */
> CPU_ZERO(&td->bind_cpumask);
>
^ permalink raw reply
* Re: [PATCH net-next 0/5] net: phy: convert advertise and supported to linkmode
From: David Miller @ 2018-11-11 18:10 UTC (permalink / raw)
To: andrew; +Cc: netdev, florain
In-Reply-To: <1541889817-2295-1-git-send-email-andrew@lunn.ch>
From: Andrew Lunn <andrew@lunn.ch>
Date: Sat, 10 Nov 2018 23:43:32 +0100
> This is the last part in converting phylib to make use of a linux
> bitmap, not a u32, to represent links modes. This will allow support
> for PHYs > 1Gbps, which need to use link modes represented by a bit >
> 32.
>
> A number of MAC and PHY drivers need changes to support this. However
> the previous two patchesets reduced the number somewhat, the helpers
> which were introduced have been modified instead of the actual
> drivers.
>
> The follow on patches then make use of the extra bits, adding support
> for more link modes.
Series applied.
> Given how invasive this change is, i expect the build is broken for
> some architectures i did not test. I will fixup the breakage as fast
> as i can.
I will hold you to this :-)
^ permalink raw reply
* Re: [PATCH net-next 0/4] net: dsa: mv88e6xxx: Support more SERDES interfacxes
From: David Miller @ 2018-11-11 18:18 UTC (permalink / raw)
To: andrew; +Cc: netdev, f.fainelli
In-Reply-To: <1541892737-3960-1-git-send-email-andrew@lunn.ch>
From: Andrew Lunn <andrew@lunn.ch>
Date: Sun, 11 Nov 2018 00:32:13 +0100
> Currently the SERDES interfaces for ports 9 and 10 on the mv88e6390x
> are supported, allowing upto 10G. However, when unused, these SERDES
> interfaces can be used by some of the lower ports for 1000Base-X.
>
> The tricky bit here is ordering. The SERDES have to become free from
> ports 9 or 10 before they can be used with lower ports. Normally, this
> would happen only when these ports would be configured up, which is
> too late. So at probe time, defaulting ports 9 and 10 to 1000BaseX
> frees them for use with lower ports. If they are actually needed, they
> will be taken back when port 9 and 10 goes up.
Series applied, thanks Andrew.
^ permalink raw reply
* Re: [patch net] net: dsa: mv88e6xxx: Fix clearing of stats counters
From: David Miller @ 2018-11-11 18:19 UTC (permalink / raw)
To: andrew; +Cc: netdev
In-Reply-To: <1541893270-4442-1-git-send-email-andrew@lunn.ch>
From: Andrew Lunn <andrew@lunn.ch>
Date: Sun, 11 Nov 2018 00:41:10 +0100
> The mv88e6161 would sometime fail to probe with a timeout waiting for
> the switch to complete an operation. This operation is supposed to
> clear the statistics counters. However, due to a read/modify/write,
> without the needed mask, the operation actually carried out was more
> random, with invalid parameters, resulting in the switch not
> responding. We need to preserve the histogram mode bits, so apply a
> mask to keep them.
>
> Reported-by: Chris Healy <Chris.Healy@zii.aero>
> Fixes: 40cff8fca9e3 ("net: dsa: mv88e6xxx: Fix stats histogram mode")
> Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Oops.
Applied and queued up for -stable.
^ permalink raw reply
* Re: [PATCH net-next] net: dsa: mv88e6xxx: Work around mv886e6161 SERDES missing MII_PHYSID2
From: David Miller @ 2018-11-11 18:20 UTC (permalink / raw)
To: andrew; +Cc: netdev
In-Reply-To: <1541893839-4828-1-git-send-email-andrew@lunn.ch>
From: Andrew Lunn <andrew@lunn.ch>
Date: Sun, 11 Nov 2018 00:50:39 +0100
> We already have a workaround for a couple of switches whose internal
> PHYs only have the Marvel OUI, but no model number. We detect such
> PHYs and give them the 6390 ID as the model number. However the
> mv88e6161 has two SERDES interfaces in the same address range as its
> internal PHYs. These suffer from the same problem, the Marvell OUI,
> but no model number. As a result, these SERDES interfaces were getting
> the same PHY ID as the mv88e6390, even though they are not PHYs, and
> the Marvell PHY driver was trying to drive them.
>
> Add a special case to stop this happen.
>
> Reported-by: Chris Healy <Chris.Healy@zii.aero>
> Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Please address Sergei's feedback, thank you.
^ permalink raw reply
* Re: [RFC] mm: Replace all open encodings for NUMA_NO_NODE
From: Anshuman Khandual @ 2018-11-12 4:10 UTC (permalink / raw)
To: Joseph Qi, linux-mm, linux-kernel
Cc: ocfs2-devel, linux-fbdev, dri-devel, netdev, intel-wired-lan,
linux-media, iommu, linux-rdma, dmaengine, linux-block,
sparclinux, linuxppc-dev, linux-ia64, linux-alpha
In-Reply-To: <1e9393c5-ff43-8ec7-dd6c-a662f09ef7c1@gmail.com>
On 11/12/2018 09:27 AM, Joseph Qi wrote:
> For ocfs2 part, node means host in the cluster, not NUMA node.
>
Does not -1 indicate an invalid node which can never be present ?
^ permalink raw reply
* Re: [PATCH net] act_mirred: clear skb->tstamp on redirect
From: David Miller @ 2018-11-11 18:21 UTC (permalink / raw)
To: edumazet; +Cc: netdev, eric.dumazet
In-Reply-To: <20181111002229.157219-1-edumazet@google.com>
From: Eric Dumazet <edumazet@google.com>
Date: Sat, 10 Nov 2018 16:22:29 -0800
> If sch_fq is used at ingress, skbs that might have been
> timestamped by net_timestamp_set() if a packet capture
> is requesting timestamps could be delayed by arbitrary
> amount of time, since sch_fq time base is MONOTONIC.
>
> Fix this problem by moving code from sch_netem.c to act_mirred.c.
>
> Fixes: fb420d5d91c1 ("tcp/fq: move back to CLOCK_MONOTONIC")
> Signed-off-by: Eric Dumazet <edumazet@google.com>
Applied.
^ permalink raw reply
* Re: [PATCH net-next v2] PCI: add USR vendor id and use it in r8169 and w6692 driver
From: David Miller @ 2018-11-11 18:23 UTC (permalink / raw)
To: hkallweit1; +Cc: bhelgaas, isdn, netdev, linux-pci
In-Reply-To: <f35fbe1d-b1f3-c0f8-82d6-18b0c7cda0b4@gmail.com>
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Sun, 11 Nov 2018 11:50:08 +0100
> diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h
> index 69f0abe1b..1fac231fe 100644
> --- a/include/linux/pci_ids.h
> +++ b/include/linux/pci_ids.h
> @@ -2359,6 +2359,10 @@
>
> #define PCI_VENDOR_ID_SYNOPSYS 0x16c3
>
> +#define PCI_VENDOR_ID_USR 0x16ec
> +#define PCI_DEVICE_ID_USR_997902 0x0116
> +#define PCI_DEVICE_ID_USR_6692 0x3409
> +
> #define PCI_VENDOR_ID_VITESSE 0x1725
> #define PCI_DEVICE_ID_VITESSE_VSC7174 0x7174
Generally, as I understand the policy for linux/pci_ids.h, we only add
things used in multiple locations.
So PCI_VENDOR_ID_USR is OK, since it is used in both r8169 and w6692.
But the device IDs are not, since only w6692 uses them.
^ permalink raw reply
* Re: [PATCH net 4/4] qed: Fix reading wrong value in loop condition
From: David Miller @ 2018-11-11 18:26 UTC (permalink / raw)
To: denis.bolotin; +Cc: netdev, michal.kalderon, ariel.elior
In-Reply-To: <20181111150500.4345-5-denis.bolotin@cavium.com>
From: Denis Bolotin <denis.bolotin@cavium.com>
Date: Sun, 11 Nov 2018 17:05:00 +0200
> diff --git a/drivers/net/ethernet/qlogic/qed/qed_int.c b/drivers/net/ethernet/qlogic/qed/qed_int.c
> index 0f0aba7..aa7504a 100644
> --- a/drivers/net/ethernet/qlogic/qed/qed_int.c
> +++ b/drivers/net/ethernet/qlogic/qed/qed_int.c
> @@ -992,6 +992,8 @@ static int qed_int_attentions(struct qed_hwfn *p_hwfn)
> */
> do {
> index = p_sb_attn->sb_index;
> + /* finish reading index before the loop condition */
> + rmb();
Please use dma_rmb().
^ permalink raw reply
* Re: [PATCH net-next] net_sched: sch_fq: add dctcp-like marking
From: Neal Cardwell @ 2018-11-11 18:50 UTC (permalink / raw)
To: Eric Dumazet; +Cc: David Miller, Netdev, Eric Dumazet
In-Reply-To: <20181111171131.24115-1-edumazet@google.com>
On Sun, Nov 11, 2018 at 12:11 PM Eric Dumazet <edumazet@google.com> wrote:
>
> Similar to 80ba92fa1a92 ("codel: add ce_threshold attribute")
>
> After EDT adoption, it became easier to implement DCTCP-like CE marking.
>
> In many cases, queues are not building in the network fabric but on
> the hosts themselves.
>
> If packets leaving fq missed their Earliest Departure Time by XXX usec,
> we mark them with ECN CE. This gives a feedback (after one RTT) to
> the sender to slow down and find better operating mode.
>
> Example :
>
> tc qd replace dev eth0 root fq ce_threshold 2.5ms
>
> Signed-off-by: Eric Dumazet <edumazet@google.com>
> ---
Very nice! Thanks, Eric. :-)
Acked-by: Neal Cardwell <ncardwell@google.com>
neal
^ permalink raw reply
* Re: [PATCH net-next 1/3] tcp: do not try to defer skbs with eor mark (MSG_EOR)
From: Neal Cardwell @ 2018-11-11 18:58 UTC (permalink / raw)
To: Eric Dumazet; +Cc: David Miller, Netdev, Soheil Hassas Yeganeh, Eric Dumazet
In-Reply-To: <20181111144131.156754-2-edumazet@google.com>
On Sun, Nov 11, 2018 at 9:41 AM Eric Dumazet <edumazet@google.com> wrote:
>
> Applications using MSG_EOR are giving a strong hint to TCP stack :
>
> Subsequent sendmsg() can not append more bytes to skbs having
> the EOR mark.
>
> Do not try to TSO defer suchs skbs, there is really no hope.
>
> Signed-off-by: Eric Dumazet <edumazet@google.com>
> Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
> ---
> net/ipv4/tcp_output.c | 4 ++++
> 1 file changed, 4 insertions(+)
Thanks!
Acked-by: Neal Cardwell <ncardwell@google.com>
neal
^ permalink raw reply
* Re: [PATCH net-next 2/3] tcp: refine tcp_tso_should_defer() after EDT adoption
From: Neal Cardwell @ 2018-11-11 19:02 UTC (permalink / raw)
To: Eric Dumazet; +Cc: David Miller, Netdev, Soheil Hassas Yeganeh, Eric Dumazet
In-Reply-To: <20181111144131.156754-3-edumazet@google.com>
On Sun, Nov 11, 2018 at 9:41 AM Eric Dumazet <edumazet@google.com> wrote:
>
> tcp_tso_should_defer() last step tries to check if the probable
> next ACK packet is coming in less than half rtt.
>
> Problem is that the head->tstamp might be in the future,
> so we need to use signed arithmetics to avoid overflows.
>
> Signed-off-by: Eric Dumazet <edumazet@google.com>
> Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
> ---
> net/ipv4/tcp_output.c | 7 ++++---
> 1 file changed, 4 insertions(+), 3 deletions(-)
Thanks!
Acked-by: Neal Cardwell <ncardwell@google.com>
neal
^ permalink raw reply
* Re: [PATCH net-next 3/3] tcp: get rid of tcp_tso_should_defer() dependency on HZ/jiffies
From: Neal Cardwell @ 2018-11-11 19:06 UTC (permalink / raw)
To: Eric Dumazet; +Cc: David Miller, Netdev, Soheil Hassas Yeganeh, Eric Dumazet
In-Reply-To: <20181111144131.156754-4-edumazet@google.com>
On Sun, Nov 11, 2018 at 9:41 AM Eric Dumazet <edumazet@google.com> wrote:
>
> tcp_tso_should_defer() first heuristic is to not defer
> if last send is "old enough".
>
> Its current implementation uses jiffies and its low granularity.
>
> TSO autodefer performance should not rely on kernel HZ :/
>
> After EDT conversion, we have state variables in nanoseconds that
> can allow us to properly implement the heuristic.
>
> This patch increases TSO chunk sizes on medium rate flows,
> especially when receivers do not use GRO or similar aggregation.
>
> It also reduces bursts for HZ=100 or HZ=250 kernels, making TCP
> behavior more uniform.
>
> Signed-off-by: Eric Dumazet <edumazet@google.com>
> Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
> ---
Nice. Thanks!
Acked-by: Neal Cardwell <ncardwell@google.com>
neal
^ permalink raw reply
* [PATCH net-next v3] PCI: add USR vendor id and use it in r8169 and w6692 driver
From: Heiner Kallweit @ 2018-11-11 19:31 UTC (permalink / raw)
To: Bjorn Helgaas, David Miller, Karsten Keil
Cc: netdev@vger.kernel.org, linux-pci@vger.kernel.org
In-Reply-To: <9af6abf5-ba01-155f-17d1-ca4b71b74fa6@gmail.com>
The PCI vendor id of U.S. Robotics isn't defined in pci_ids.h so far,
only ISDN driver w6692 has a private definition. Move the definition
to pci_ids.h and use it in the r8169 driver too.
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
---
v2:
- The original patch caused a build failure in w6692 driver because
it broke the private PCI device id definition.
v3:
- Don't move device id's to pci_ids.h because they are used in
one module only respectively.
---
drivers/isdn/hardware/mISDN/w6692.c | 3 ---
drivers/net/ethernet/realtek/r8169.c | 2 +-
include/linux/pci_ids.h | 2 ++
3 files changed, 3 insertions(+), 4 deletions(-)
diff --git a/drivers/isdn/hardware/mISDN/w6692.c b/drivers/isdn/hardware/mISDN/w6692.c
index 5acf6ab67..6f60aced1 100644
--- a/drivers/isdn/hardware/mISDN/w6692.c
+++ b/drivers/isdn/hardware/mISDN/w6692.c
@@ -52,10 +52,7 @@ static const struct w6692map w6692_map[] =
{W6692_USR, "USR W6692"}
};
-#ifndef PCI_VENDOR_ID_USR
-#define PCI_VENDOR_ID_USR 0x16ec
#define PCI_DEVICE_ID_USR_6692 0x3409
-#endif
struct w6692_ch {
struct bchannel bch;
diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index 1fd01688d..366a690eb 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -224,7 +224,7 @@ static const struct pci_device_id rtl8169_pci_tbl[] = {
{ PCI_DEVICE(PCI_VENDOR_ID_DLINK, 0x4300), 0, 0, RTL_CFG_0 },
{ PCI_DEVICE(PCI_VENDOR_ID_DLINK, 0x4302), 0, 0, RTL_CFG_0 },
{ PCI_DEVICE(PCI_VENDOR_ID_AT, 0xc107), 0, 0, RTL_CFG_0 },
- { PCI_DEVICE(0x16ec, 0x0116), 0, 0, RTL_CFG_0 },
+ { PCI_DEVICE(PCI_VENDOR_ID_USR, 0x0116), 0, 0, RTL_CFG_0 },
{ PCI_VENDOR_ID_LINKSYS, 0x1032,
PCI_ANY_ID, 0x0024, 0, 0, RTL_CFG_0 },
{ 0x0001, 0x8168,
diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h
index 69f0abe1b..144de2e89 100644
--- a/include/linux/pci_ids.h
+++ b/include/linux/pci_ids.h
@@ -2359,6 +2359,8 @@
#define PCI_VENDOR_ID_SYNOPSYS 0x16c3
+#define PCI_VENDOR_ID_USR 0x16ec
+
#define PCI_VENDOR_ID_VITESSE 0x1725
#define PCI_DEVICE_ID_VITESSE_VSC7174 0x7174
--
2.19.1
^ permalink raw reply related
* [PATCH tip/core/rcu 33/41] net/bridge: Replace call_rcu_bh() and rcu_barrier_bh()
From: Paul E. McKenney @ 2018-11-11 19:44 UTC (permalink / raw)
To: linux-kernel
Cc: mingo, jiangshanlai, dipankar, akpm, mathieu.desnoyers, josh,
tglx, peterz, rostedt, dhowells, edumazet, fweisbec, oleg, joel,
Paul E. McKenney, Roopa Prabhu, Nikolay Aleksandrov,
David S. Miller, bridge, netdev
In-Reply-To: <20181111194104.GA4787@linux.ibm.com>
Now that call_rcu()'s callback is not invoked until after all bh-disable
regions of code have completed (in addition to explicitly marked
RCU read-side critical sections), call_rcu() can be used in place
of call_rcu_bh(). Similarly, rcu_barrier() can be used in place of
rcu_barrier_bh(). This commit therefore makes these changes.
Signed-off-by: Paul E. McKenney <paulmck@linux.ibm.com>
Cc: Roopa Prabhu <roopa@cumulusnetworks.com>
Cc: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: <bridge@lists.linux-foundation.org>
Cc: <netdev@vger.kernel.org>
---
net/bridge/br_mdb.c | 2 +-
net/bridge/br_multicast.c | 14 +++++++-------
2 files changed, 8 insertions(+), 8 deletions(-)
diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c
index a7ea2d431714..596ec6e7df11 100644
--- a/net/bridge/br_mdb.c
+++ b/net/bridge/br_mdb.c
@@ -728,7 +728,7 @@ static int __br_mdb_del(struct net_bridge *br, struct br_mdb_entry *entry)
rcu_assign_pointer(*pp, p->next);
hlist_del_init(&p->mglist);
del_timer(&p->timer);
- call_rcu_bh(&p->rcu, br_multicast_free_pg);
+ call_rcu(&p->rcu, br_multicast_free_pg);
err = 0;
if (!mp->ports && !mp->host_joined &&
diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index 6bac0d6b7b94..0255223f2001 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -260,7 +260,7 @@ static void br_multicast_group_expired(struct timer_list *t)
hlist_del_rcu(&mp->hlist[mdb->ver]);
mdb->size--;
- call_rcu_bh(&mp->rcu, br_multicast_free_group);
+ call_rcu(&mp->rcu, br_multicast_free_group);
out:
spin_unlock(&br->multicast_lock);
@@ -291,7 +291,7 @@ static void br_multicast_del_pg(struct net_bridge *br,
del_timer(&p->timer);
br_mdb_notify(br->dev, p->port, &pg->addr, RTM_DELMDB,
p->flags);
- call_rcu_bh(&p->rcu, br_multicast_free_pg);
+ call_rcu(&p->rcu, br_multicast_free_pg);
if (!mp->ports && !mp->host_joined &&
netif_running(br->dev))
@@ -358,7 +358,7 @@ static int br_mdb_rehash(struct net_bridge_mdb_htable __rcu **mdbp, int max,
}
br_mdb_rehash_seq++;
- call_rcu_bh(&mdb->rcu, br_mdb_free);
+ call_rcu(&mdb->rcu, br_mdb_free);
out:
rcu_assign_pointer(*mdbp, mdb);
@@ -1629,7 +1629,7 @@ br_multicast_leave_group(struct net_bridge *br,
rcu_assign_pointer(*pp, p->next);
hlist_del_init(&p->mglist);
del_timer(&p->timer);
- call_rcu_bh(&p->rcu, br_multicast_free_pg);
+ call_rcu(&p->rcu, br_multicast_free_pg);
br_mdb_notify(br->dev, port, group, RTM_DELMDB,
p->flags);
@@ -2051,19 +2051,19 @@ void br_multicast_dev_del(struct net_bridge *br)
hlist_for_each_entry_safe(mp, n, &mdb->mhash[i],
hlist[ver]) {
del_timer(&mp->timer);
- call_rcu_bh(&mp->rcu, br_multicast_free_group);
+ call_rcu(&mp->rcu, br_multicast_free_group);
}
}
if (mdb->old) {
spin_unlock_bh(&br->multicast_lock);
- rcu_barrier_bh();
+ rcu_barrier();
spin_lock_bh(&br->multicast_lock);
WARN_ON(mdb->old);
}
mdb->old = mdb;
- call_rcu_bh(&mdb->rcu, br_mdb_free);
+ call_rcu(&mdb->rcu, br_mdb_free);
out:
spin_unlock_bh(&br->multicast_lock);
--
2.17.1
^ permalink raw reply related
* [PATCH tip/core/rcu 39/41] net/decnet: Replace rcu_barrier_bh() with rcu_barrier()
From: Paul E. McKenney @ 2018-11-11 19:44 UTC (permalink / raw)
To: linux-kernel
Cc: mingo, jiangshanlai, dipankar, akpm, mathieu.desnoyers, josh,
tglx, peterz, rostedt, dhowells, edumazet, fweisbec, oleg, joel,
Paul E. McKenney, David S. Miller, linux-decnet-user, netdev
In-Reply-To: <20181111194104.GA4787@linux.ibm.com>
Now that all RCU flavors have been consolidated, rcu_barrier_bh()
is but a synonym for rcu_barrier(). This commit therefore replaces
the former with the latter.
Signed-off-by: Paul E. McKenney <paulmck@linux.ibm.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: <linux-decnet-user@lists.sourceforge.net>
Cc: <netdev@vger.kernel.org>
---
net/decnet/af_decnet.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c
index 7d6ff983ba2c..dbd0f7bae00a 100644
--- a/net/decnet/af_decnet.c
+++ b/net/decnet/af_decnet.c
@@ -2405,7 +2405,7 @@ static void __exit decnet_exit(void)
proto_unregister(&dn_proto);
- rcu_barrier_bh(); /* Wait for completion of call_rcu_bh()'s */
+ rcu_barrier(); /* Wait for completion of call_rcu()'s */
}
module_exit(decnet_exit);
#endif
--
2.17.1
^ permalink raw reply related
* [PATCH tip/core/rcu 12/41] ethernet/realtek: Replace synchronize_sched() with synchronize_rcu()
From: Paul E. McKenney @ 2018-11-11 19:43 UTC (permalink / raw)
To: linux-kernel
Cc: mingo, jiangshanlai, dipankar, akpm, mathieu.desnoyers, josh,
tglx, peterz, rostedt, dhowells, edumazet, fweisbec, oleg, joel,
Paul E. McKenney, Realtek linux nic maintainers, David S. Miller,
netdev
In-Reply-To: <20181111194104.GA4787@linux.ibm.com>
Now that synchronize_rcu() waits for preempt-disable regions of code
as well as RCU read-side critical sections, synchronize_sched() can be
replaced by synchronize_rcu(). This commit therefore makes this change.
Signed-off-by: Paul E. McKenney <paulmck@linux.ibm.com>
Cc: Realtek linux nic maintainers <nic_swsd@realtek.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: <netdev@vger.kernel.org>
---
drivers/net/ethernet/realtek/8139too.c | 2 +-
drivers/net/ethernet/realtek/r8169.c | 4 ++--
2 files changed, 3 insertions(+), 3 deletions(-)
diff --git a/drivers/net/ethernet/realtek/8139too.c b/drivers/net/ethernet/realtek/8139too.c
index ffd68a7bc9e1..69d752f0b621 100644
--- a/drivers/net/ethernet/realtek/8139too.c
+++ b/drivers/net/ethernet/realtek/8139too.c
@@ -1661,7 +1661,7 @@ static void rtl8139_tx_timeout_task (struct work_struct *work)
napi_disable(&tp->napi);
netif_stop_queue(dev);
- synchronize_sched();
+ synchronize_rcu();
netdev_dbg(dev, "Transmit timeout, status %02x %04x %04x media %02x\n",
RTL_R8(ChipCmd), RTL_R16(IntrStatus),
diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index 1fd01688d37b..4f1d89f0dc24 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -5866,7 +5866,7 @@ static void rtl_reset_work(struct rtl8169_private *tp)
napi_disable(&tp->napi);
netif_stop_queue(dev);
- synchronize_sched();
+ synchronize_rcu();
rtl8169_hw_reset(tp);
@@ -6609,7 +6609,7 @@ static void rtl8169_down(struct net_device *dev)
rtl8169_rx_missed(dev);
/* Give a racing hard_start_xmit a few cycles to complete. */
- synchronize_sched();
+ synchronize_rcu();
rtl8169_tx_clear(tp);
--
2.17.1
^ permalink raw reply related
* [PATCH tip/core/rcu 31/41] net/sched: Replace call_rcu_bh() and rcu_barrier_bh()
From: Paul E. McKenney @ 2018-11-11 19:44 UTC (permalink / raw)
To: linux-kernel
Cc: mingo, jiangshanlai, dipankar, akpm, mathieu.desnoyers, josh,
tglx, peterz, rostedt, dhowells, edumazet, fweisbec, oleg, joel,
Paul E. McKenney, Jamal Hadi Salim, Cong Wang, Jiri Pirko,
David S. Miller, netdev
In-Reply-To: <20181111194104.GA4787@linux.ibm.com>
Now that call_rcu()'s callback is not invoked until after bh-disable
regions of code have completed (in addition to explicitly marked
RCU read-side critical sections), call_rcu() can be used in place
of call_rcu_bh(). Similarly, rcu_barrier() can be used in place o
frcu_barrier_bh(). This commit therefore makes these changes.
Signed-off-by: Paul E. McKenney <paulmck@linux.ibm.com>
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Cc: Cong Wang <xiyou.wangcong@gmail.com>
Cc: Jiri Pirko <jiri@resnulli.us>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: <netdev@vger.kernel.org>
---
net/sched/sch_api.c | 2 +-
net/sched/sch_generic.c | 8 ++++----
2 files changed, 5 insertions(+), 5 deletions(-)
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index ca3b0f46de53..016e628c6ac9 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -540,7 +540,7 @@ void qdisc_put_stab(struct qdisc_size_table *tab)
if (--tab->refcnt == 0) {
list_del(&tab->list);
- call_rcu_bh(&tab->rcu, stab_kfree_rcu);
+ call_rcu(&tab->rcu, stab_kfree_rcu);
}
}
EXPORT_SYMBOL(qdisc_put_stab);
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index de1663f7d3ad..66ba2ce2320f 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -1372,7 +1372,7 @@ void mini_qdisc_pair_swap(struct mini_Qdisc_pair *miniqp,
if (!tp_head) {
RCU_INIT_POINTER(*miniqp->p_miniq, NULL);
/* Wait for flying RCU callback before it is freed. */
- rcu_barrier_bh();
+ rcu_barrier();
return;
}
@@ -1380,10 +1380,10 @@ void mini_qdisc_pair_swap(struct mini_Qdisc_pair *miniqp,
&miniqp->miniq1 : &miniqp->miniq2;
/* We need to make sure that readers won't see the miniq
- * we are about to modify. So wait until previous call_rcu_bh callback
+ * we are about to modify. So wait until previous call_rcu callback
* is done.
*/
- rcu_barrier_bh();
+ rcu_barrier();
miniq->filter_list = tp_head;
rcu_assign_pointer(*miniqp->p_miniq, miniq);
@@ -1392,7 +1392,7 @@ void mini_qdisc_pair_swap(struct mini_Qdisc_pair *miniqp,
* block potential new user of miniq_old until all readers
* are not seeing it.
*/
- call_rcu_bh(&miniq_old->rcu, mini_qdisc_rcu_func);
+ call_rcu(&miniq_old->rcu, mini_qdisc_rcu_func);
}
EXPORT_SYMBOL(mini_qdisc_pair_swap);
--
2.17.1
^ permalink raw reply related
* [PATCH tip/core/rcu 38/41] net/core/skmsg: Replace call_rcu_sched() with call_rcu()
From: Paul E. McKenney @ 2018-11-11 19:44 UTC (permalink / raw)
To: linux-kernel
Cc: mingo, jiangshanlai, dipankar, akpm, mathieu.desnoyers, josh,
tglx, peterz, rostedt, dhowells, edumazet, fweisbec, oleg, joel,
Paul E. McKenney, John Fastabend, Daniel Borkmann,
David S. Miller, netdev
In-Reply-To: <20181111194104.GA4787@linux.ibm.com>
Now that call_rcu()'s callback is not invoked until after all
preempt-disable regions of code have completed (in addition to explicitly
marked RCU read-side critical sections), call_rcu() can be used in place
of call_rcu_sched(). This commit therefore makes that change.
Signed-off-by: Paul E. McKenney <paulmck@linux.ibm.com>
Cc: John Fastabend <john.fastabend@gmail.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: <netdev@vger.kernel.org>
---
net/core/skmsg.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index 56a99d0c9aa0..c92d6ccce610 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -580,7 +580,7 @@ void sk_psock_drop(struct sock *sk, struct sk_psock *psock)
write_unlock_bh(&sk->sk_callback_lock);
sk_psock_clear_state(psock, SK_PSOCK_TX_ENABLED);
- call_rcu_sched(&psock->rcu, sk_psock_destroy);
+ call_rcu(&psock->rcu, sk_psock_destroy);
}
EXPORT_SYMBOL_GPL(sk_psock_drop);
--
2.17.1
^ permalink raw reply related
* general protection fault in rds_recv_rcvbuf_delta
From: syzbot @ 2018-11-12 5:51 UTC (permalink / raw)
To: davem, linux-kernel, linux-rdma, netdev, rds-devel,
santosh.shilimkar, syzkaller-bugs
Hello,
syzbot found the following crash on:
HEAD commit: e255aee5b66c Merge tag 'tty-4.20-rc2' of git://git.kernel...
git tree: upstream
console output: https://syzkaller.appspot.com/x/log.txt?x=124d66a3400000
kernel config: https://syzkaller.appspot.com/x/.config?x=8f215f21f041a0d7
dashboard link: https://syzkaller.appspot.com/bug?extid=4b4f8163c2e246df3c4c
compiler: gcc (GCC) 8.0.1 20180413 (experimental)
Unfortunately, I don't have any reproducer for this crash yet.
IMPORTANT: if you fix the bug, please add the following tag to the commit:
Reported-by: syzbot+4b4f8163c2e246df3c4c@syzkaller.appspotmail.com
vhci_hcd: default hub control req: 0000 v0000 i0001 l50287
kasan: CONFIG_KASAN_INLINE enabled
kasan: GPF could be caused by NULL-ptr deref or user memory access
general protection fault: 0000 [#1] PREEMPT SMP KASAN
CPU: 0 PID: 18919 Comm: syz-executor3 Not tainted 4.20.0-rc1+ #109
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS
Google 01/01/2011
RIP: 0010:rds_recv_rcvbuf_delta.part.3+0x14a/0x3f0 net/rds/recv.c:103
Code: c1 ea 03 80 3c 02 00 0f 85 6e 02 00 00 4c 8b a3 c0 04 00 00 48 b8 00
00 00 00 00 fc ff df 49 8d 7c 24 2c 48 89 fa 48 c1 ea 03 <0f> b6 14 02 48
89 f8 83 e0 07 83 c0 03 38 d0 7c 08 84 d2 0f 85 00
RSP: 0018:ffff88018b39efc0 EFLAGS: 00010007
RAX: dffffc0000000000 RBX: ffff8801be730780 RCX: ffffc9001061b000
RDX: 0000000000000005 RSI: ffffffff8749949b RDI: 000000000000002c
RBP: ffff88018b39eff8 R08: ffff8801ce388300 R09: ffffed0031673ded
R10: ffffed0031673ded R11: 0000000000000003 R12: 0000000000000000
R13: ffff8801be730ca4 R14: 000000000002e0c0 R15: ffff8801cbe88b00
FS: 00007fa7bf29b700(0000) GS:ffff8801dae00000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000001b33a27000 CR3: 00000001bf445000 CR4: 00000000001406f0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
rds_recv_rcvbuf_delta net/rds/recv.c:379 [inline]
rds_recv_incoming+0x8bb/0x1400 net/rds/recv.c:379
rds_loop_xmit+0xf3/0x2a0 net/rds/loop.c:96
rds_send_xmit+0x13ef/0x2bb0 net/rds/send.c:355
rds_sendmsg+0x290f/0x3180 net/rds/send.c:1338
sock_sendmsg_nosec net/socket.c:621 [inline]
sock_sendmsg+0xd5/0x120 net/socket.c:631
__sys_sendto+0x3d7/0x670 net/socket.c:1788
__do_sys_sendto net/socket.c:1800 [inline]
__se_sys_sendto net/socket.c:1796 [inline]
__x64_sys_sendto+0xe1/0x1a0 net/socket.c:1796
do_syscall_64+0x1b9/0x820 arch/x86/entry/common.c:290
entry_SYSCALL_64_after_hwframe+0x49/0xbe
RIP: 0033:0x457569
Code: fd b3 fb ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 48 89 f8 48 89 f7
48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff
ff 0f 83 cb b3 fb ff c3 66 2e 0f 1f 84 00 00 00 00
RSP: 002b:00007fa7bf29ac78 EFLAGS: 00000246 ORIG_RAX: 000000000000002c
RAX: ffffffffffffffda RBX: 0000000000000006 RCX: 0000000000457569
RDX: 0000000000000241 RSI: 0000000020000a00 RDI: 0000000000000008
RBP: 000000000072bf00 R08: 000000002069affb R09: 0000000000000010
R10: 0000000000000000 R11: 0000000000000246 R12: 00007fa7bf29b6d4
R13: 00000000004c3c11 R14: 00000000004d5e80 R15: 00000000ffffffff
Modules linked in:
---[ end trace ffda6d1117cbc209 ]---
RIP: 0010:rds_recv_rcvbuf_delta.part.3+0x14a/0x3f0 net/rds/recv.c:103
Code: c1 ea 03 80 3c 02 00 0f 85 6e 02 00 00 4c 8b a3 c0 04 00 00 48 b8 00
00 00 00 00 fc ff df 49 8d 7c 24 2c 48 89 fa 48 c1 ea 03 <0f> b6 14 02 48
89 f8 83 e0 07 83 c0 03 38 d0 7c 08 84 d2 0f 85 00
RSP: 0018:ffff88018b39efc0 EFLAGS: 00010007
RAX: dffffc0000000000 RBX: ffff8801be730780 RCX: ffffc9001061b000
RDX: 0000000000000005 RSI: ffffffff8749949b RDI: 000000000000002c
RBP: ffff88018b39eff8 R08: ffff8801ce388300 R09: ffffed0031673ded
R10: ffffed0031673ded R11: 0000000000000003 R12: 0000000000000000
R13: ffff8801be730ca4 R14: 000000000002e0c0 R15: ffff8801cbe88b00
FS: 00007fa7bf29b700(0000) GS:ffff8801dae00000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000001b33a27000 CR3: 00000001bf445000 CR4: 00000000001406f0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
---
This bug is generated by a bot. It may contain errors.
See https://goo.gl/tpsmEJ for more information about syzbot.
syzbot engineers can be reached at syzkaller@googlegroups.com.
syzbot will keep track of this bug report. See:
https://goo.gl/tpsmEJ#bug-status-tracking for how to communicate with
syzbot.
^ permalink raw reply
* [PATCH tip/core/rcu 3/7] smsc: Replace spin_is_locked() with lockdep
From: Paul E. McKenney @ 2018-11-11 20:04 UTC (permalink / raw)
To: linux-kernel
Cc: mingo, jiangshanlai, dipankar, akpm, mathieu.desnoyers, josh,
tglx, peterz, rostedt, dhowells, edumazet, fweisbec, oleg, joel,
Lance Roy, Steve Glendinning, David S. Miller, netdev,
Paul E . McKenney
In-Reply-To: <20181111200421.GA10551@linux.ibm.com>
From: Lance Roy <ldr709@gmail.com>
lockdep_assert_held() is better suited to checking locking requirements,
since it only checks if the current thread holds the lock regardless of
whether someone else does. This is also a step towards possibly removing
spin_is_locked().
Signed-off-by: Lance Roy <ldr709@gmail.com>
Cc: Steve Glendinning <steve.glendinning@shawell.net>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: <netdev@vger.kernel.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.ibm.com>
---
drivers/net/ethernet/smsc/smsc911x.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/smsc/smsc911x.h b/drivers/net/ethernet/smsc/smsc911x.h
index 8d75508acd2b..51b2fc1a395f 100644
--- a/drivers/net/ethernet/smsc/smsc911x.h
+++ b/drivers/net/ethernet/smsc/smsc911x.h
@@ -67,7 +67,7 @@
#ifdef CONFIG_DEBUG_SPINLOCK
#define SMSC_ASSERT_MAC_LOCK(pdata) \
- WARN_ON_SMP(!spin_is_locked(&pdata->mac_lock))
+ lockdep_assert_held(&pdata->mac_lock)
#else
#define SMSC_ASSERT_MAC_LOCK(pdata) do {} while (0)
#endif /* CONFIG_DEBUG_SPINLOCK */
--
2.17.1
^ permalink raw reply related
* [PATCH tip/core/rcu 2/7] sfc: Replace spin_is_locked() with lockdep
From: Paul E. McKenney @ 2018-11-11 20:04 UTC (permalink / raw)
To: linux-kernel
Cc: mingo, jiangshanlai, dipankar, akpm, mathieu.desnoyers, josh,
tglx, peterz, rostedt, dhowells, edumazet, fweisbec, oleg, joel,
Lance Roy, Solarflare linux maintainers, Edward Cree,
Bert Kenward, David S. Miller, netdev, Paul E . McKenney
In-Reply-To: <20181111200421.GA10551@linux.ibm.com>
From: Lance Roy <ldr709@gmail.com>
lockdep_assert_held() is better suited to checking locking requirements,
since it only checks if the current thread holds the lock regardless of
whether someone else does. This is also a step towards possibly removing
spin_is_locked().
Signed-off-by: Lance Roy <ldr709@gmail.com>
Cc: Solarflare linux maintainers <linux-net-drivers@solarflare.com>
Cc: Edward Cree <ecree@solarflare.com>
Cc: Bert Kenward <bkenward@solarflare.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: <netdev@vger.kernel.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.ibm.com>
---
drivers/net/ethernet/sfc/efx.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c
index 98fe7e762e17..3643015a55cf 100644
--- a/drivers/net/ethernet/sfc/efx.c
+++ b/drivers/net/ethernet/sfc/efx.c
@@ -3167,7 +3167,7 @@ struct hlist_head *efx_rps_hash_bucket(struct efx_nic *efx,
{
u32 hash = efx_filter_spec_hash(spec);
- WARN_ON(!spin_is_locked(&efx->rps_hash_lock));
+ lockdep_assert_held(&efx->rps_hash_lock);
if (!efx->rps_hash_table)
return NULL;
return &efx->rps_hash_table[hash % EFX_ARFS_HASH_TABLE_SIZE];
--
2.17.1
^ permalink raw reply related
* Re: WARN_ON() in netconsole with PREEMPT_RT
From: Oleksandr Natalenko @ 2018-11-11 20:16 UTC (permalink / raw)
To: David S. Miller
Cc: Steven Rostedt, Sebastian Andrzej Siewior, Thomas Gleixner,
Eric Dumazet, Dave Jones, netdev, linux-rt-users, linux-kernel
In-Reply-To: <f9111ab09dbc264c8ff8b3b79e9f4c06@natalenko.name>
On 11.11.2018 20:13, Oleksandr Natalenko wrote:
> Hi.
>
> I was just curious about PREEMPT_RT and decided to give it a (small)
> shot on my laptop. As a safety measure, I've enabled netconsole to
> catch all the weird stuff that can pop up, and immediately it indeed
> did… in the netconsole code itself (irony):
>
> ===
> [ 64.018949] WARNING: CPU: 0 PID: 1204 at net/core/netpoll.c:372
> netpoll_send_udp+0x3e8/0x3ef
> …
> [ 64.019057] CPU: 0 PID: 1204 Comm: bash Not tainted 4.19.0-ig1 #1
> [ 64.019058] Hardware name: Dell Inc. Vostro 3360/0F5DWF,
> BIOS A18 09/25/2013
> [ 64.019063] RIP: 0010:netpoll_send_udp+0x3e8/0x3ef
> [
> 64.019066] Code: dd ff ff 41 ba 86 dd ff ff 49 2b 96 d0 00 00 00 66 41
> 89 96 c6 00 00 00 66 44 89 48 0c 66 45 89 96 c0 00 00 00 e9
> 93 fe ff ff <0f> 0b e9 40 fc ff ff 0f 1f 44 00 00 53 0f b7 57 42 48 89
> fb 48 8b
> [ 64.019068] RSP: 0018:ffffaa6743f87c98 EFLAGS: 00010202
> [ 64.019070] RAX: 0000000000000292 RBX: 0000000000000014 RCX:
> 0000000000000028
> [ 64.019072] RDX: 0000000000000014 RSI: ffffffffb1e6a300 RDI:
> ffff95973d905668
> [ 64.019073] RBP: ffffaa6743f87cd8 R08: ffffffffc11f6ba0 R09:
> 0000000000000000
> [ 64.019075] R10: 0000000000000008 R11: 0000000000000000 R12:
> 00000000000003e8
> [ 64.019076] R13: ffff95973d905668 R14: 0000000000000014 R15:
> ffff95973d905668
> [ 64.019079] FS: 00007f2f8b809b80(0000) GS:ffff95976f000000(0000)
> knlGS:0000000000000000
> [ 64.019081] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
> [ 64.019083] CR2: 000055b8e126fbc8 CR3: 0000000415440006 CR4:
> 00000000001606f0
> [ 64.019084] Call Trace:
> [ 64.019098] write_msg+0xd1/0xe0 [netconsole]
> [ 64.019107] console_unlock.part.6+0x55b/0x5a0
> [ 64.019115] ? _raw_spin_unlock_irqrestore+0x20/0x60
> [ 64.019120] vprintk_emit+0x16a/0x1a0
> [ 64.019125] printk_emit+0x44/0x5b
> [ 64.019130] ? _raw_spin_trylock+0x13/0x80
> [ 64.019134] devkmsg_write.cold.16+0x21/0x4e
> [ 64.019140] __vfs_write+0x136/0x1a0
> [ 64.019145] vfs_write+0xa9/0x1a0
> [ 64.019149] ksys_write+0x52/0xc0
> [ 64.019156] do_syscall_64+0x5b/0x170
> [ 64.019160] entry_SYSCALL_64_after_hwframe+0x44/0xa9
> …
> ===
>
> This is a v4.19.1-rt3-based kernel.
>
> The WARN_ON() is:
>
> 362 void netpoll_send_udp(struct netpoll *np, const char *msg, int len)
> 363 {
> …
> 372 WARN_ON_ONCE(!irqs_disabled());
> …
>
> If that matters, I have "threadirqs" passed to the kernel.
>
> Netconsole seems to work even after this warning. Is this OK/expected?
>
> Thanks.
Oh, I see that write_msg() calls netpoll_send_udp() under
spin_lock_irqsave(), but in PREEMPT_RT this, AFAIK, does not disable
interrupts.
So, the real question here is whether the interrupts should be indeed
disabled. And if so, -rt should replace spin_lock_irqsave() call there
with what? local_irq_save()? and get rid of the warning?
--
Oleksandr Natalenko (post-factum)
^ permalink raw reply
* [PATCH net-next] net: phy: icplus: add config_intr callback
From: Heiner Kallweit @ 2018-11-11 20:49 UTC (permalink / raw)
To: Andrew Lunn, Florian Fainelli, David Miller; +Cc: netdev@vger.kernel.org
Move IRQ configuration for IP101A/G from config_init to config_intr
callback. Reasons:
1. This allows phylib to disable interrupts if needed.
2. Icplus was the only driver supporting interrupts w/o defining a
config_intr callback. Now we can add a phylib plausibility check
disabling interrupt mode if one of the two irq-related callbacks
isn't defined.
I don't own hardware with this PHY, and the change is based on the
datasheet for IP101A LF (which is supposed to be register-compatible
with IP101A/G). Change is compile-tested only.
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
---
drivers/net/phy/icplus.c | 23 ++++++++++++++++-------
1 file changed, 16 insertions(+), 7 deletions(-)
diff --git a/drivers/net/phy/icplus.c b/drivers/net/phy/icplus.c
index 21ce68964..ad87bd328 100644
--- a/drivers/net/phy/icplus.c
+++ b/drivers/net/phy/icplus.c
@@ -42,8 +42,8 @@ MODULE_LICENSE("GPL");
#define IP1001_APS_ON 11 /* IP1001 APS Mode bit */
#define IP101A_G_APS_ON 2 /* IP101A/G APS Mode bit */
#define IP101A_G_IRQ_CONF_STATUS 0x11 /* Conf Info IRQ & Status Reg */
-#define IP101A_G_IRQ_PIN_USED (1<<15) /* INTR pin used */
-#define IP101A_G_IRQ_DEFAULT IP101A_G_IRQ_PIN_USED
+#define IP101A_G_IRQ_PIN_USED BIT(15) /* INTR pin used */
+#define IP101A_G_NO_IRQ BIT(11) /* IRQ's inactive */
static int ip175c_config_init(struct phy_device *phydev)
{
@@ -170,11 +170,6 @@ static int ip101a_g_config_init(struct phy_device *phydev)
if (c < 0)
return c;
- /* INTR pin used: speed/link/duplex will cause an interrupt */
- c = phy_write(phydev, IP101A_G_IRQ_CONF_STATUS, IP101A_G_IRQ_DEFAULT);
- if (c < 0)
- return c;
-
/* Enable Auto Power Saving mode */
c = phy_read(phydev, IP10XX_SPEC_CTRL_STATUS);
c |= IP101A_G_APS_ON;
@@ -201,6 +196,19 @@ static int ip175c_config_aneg(struct phy_device *phydev)
return 0;
}
+static int ip101a_g_config_intr(struct phy_device *phydev)
+{
+ u16 val;
+
+ if (phydev->interrupts == PHY_INTERRUPT_ENABLED)
+ /* INTR pin used: Speed/link/duplex will cause an interrupt */
+ val = IP101A_G_IRQ_PIN_USED;
+ else
+ val = IP101A_G_NO_IRQ;
+
+ return phy_write(phydev, IP101A_G_IRQ_CONF_STATUS, val);
+}
+
static int ip101a_g_ack_interrupt(struct phy_device *phydev)
{
int err = phy_read(phydev, IP101A_G_IRQ_CONF_STATUS);
@@ -234,6 +242,7 @@ static struct phy_driver icplus_driver[] = {
.name = "ICPlus IP101A/G",
.phy_id_mask = 0x0ffffff0,
.features = PHY_BASIC_FEATURES,
+ .config_intr = ip101a_g_config_intr,
.ack_interrupt = ip101a_g_ack_interrupt,
.config_init = &ip101a_g_config_init,
.suspend = genphy_suspend,
--
2.19.1
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox