F: kernel/delayacct.c
PERFORMANCE EVENTS SUBSYSTEM
-M: Peter Zijlstra <a.p.zijlstra@chello.nl>
+M: Peter Zijlstra <peterz@infradead.org>
M: Ingo Molnar <mingo@redhat.com>
M: Arnaldo Carvalho de Melo <acme@kernel.org>
L: linux-kernel@vger.kernel.org
* Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar
* Copyright (C) 2009 Jaswinder Singh Rajput
* Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter
- * Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ * Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra
* Copyright (C) 2009 Intel Corporation, <markus.t.metzger@intel.com>
*
* ppc:
* Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar
* Copyright (C) 2009 Jaswinder Singh Rajput
* Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter
- * Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ * Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra
* Copyright (C) 2009 Intel Corporation, <markus.t.metzger@intel.com>
*
* ppc:
* Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar
* Copyright (C) 2009 Jaswinder Singh Rajput
* Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter
- * Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ * Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra
*/
#include <linux/perf_event.h>
* Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar
* Copyright (C) 2009 Jaswinder Singh Rajput
* Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter
- * Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ * Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra
* Copyright (C) 2009 Intel Corporation, <markus.t.metzger@intel.com>
* Copyright (C) 2009 Google, Inc., Stephane Eranian
*/
* Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar
* Copyright (C) 2009 Jaswinder Singh Rajput
* Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter
- * Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ * Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra
* Copyright (C) 2009 Intel Corporation, <markus.t.metzger@intel.com>
* Copyright (C) 2009 Google, Inc., Stephane Eranian
*
* Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar
* Copyright (C) 2009 Jaswinder Singh Rajput
* Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter
- * Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ * Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra
* Copyright (C) 2009 Intel Corporation, <markus.t.metzger@intel.com>
* Copyright (C) 2009 Google, Inc., Stephane Eranian
*
/* Check flags and event code/umask, and set the HSW N/A flag */
#define INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_NA(code, n) \
__EVENT_CONSTRAINT(code, n, \
- INTEL_ARCH_EVENT_MASK|INTEL_ARCH_EVENT_MASK, \
+ INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS, \
HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_NA_HSW)
u64 lbr_from[MAX_LBR_ENTRIES];
u64 lbr_to[MAX_LBR_ENTRIES];
u64 lbr_info[MAX_LBR_ENTRIES];
+ int tos;
int lbr_callstack_users;
int lbr_stack_state;
};
FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */
FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */
FIXED_EVENT_CONSTRAINT(0x0300, 2), /* CPU_CLK_UNHALTED.REF */
- INTEL_EVENT_CONSTRAINT(0x48, 0x4), /* L1D_PEND_MISS.* */
+ INTEL_UEVENT_CONSTRAINT(0x148, 0x4), /* L1D_PEND_MISS.PENDING */
INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PREC_DIST */
INTEL_EVENT_CONSTRAINT(0xcd, 0x8), /* MEM_TRANS_RETIRED.LOAD_LATENCY */
/* CYCLE_ACTIVITY.CYCLES_L1D_PENDING */
static inline struct perf_cgroup *event_to_cgroup(struct perf_event *event)
{
if (event->attach_state & PERF_ATTACH_TASK)
- return perf_cgroup_from_task(event->hw.target);
+ return perf_cgroup_from_task(event->hw.target, event->ctx);
return event->cgrp;
}
}
mask = x86_pmu.lbr_nr - 1;
- tos = intel_pmu_lbr_tos();
+ tos = task_ctx->tos;
for (i = 0; i < tos; i++) {
lbr_idx = (tos - i) & mask;
wrmsrl(x86_pmu.lbr_from + lbr_idx, task_ctx->lbr_from[i]);
if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO)
wrmsrl(MSR_LBR_INFO_0 + lbr_idx, task_ctx->lbr_info[i]);
}
+ wrmsrl(x86_pmu.lbr_tos, tos);
task_ctx->lbr_stack_state = LBR_NONE;
}
if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO)
rdmsrl(MSR_LBR_INFO_0 + lbr_idx, task_ctx->lbr_info[i]);
}
+ task_ctx->tos = tos;
task_ctx->lbr_stack_state = LBR_VALID;
}
/*
* x86 specific code for irq_work
*
- * Copyright (C) 2010 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ * Copyright (C) 2010 Red Hat, Inc., Peter Zijlstra
*/
#include <linux/kernel.h>
{ PCI_VDEVICE(INTEL, 0x1f37), board_ahci_avn }, /* Avoton RAID */
{ PCI_VDEVICE(INTEL, 0x1f3e), board_ahci_avn }, /* Avoton RAID */
{ PCI_VDEVICE(INTEL, 0x1f3f), board_ahci_avn }, /* Avoton RAID */
- { PCI_VDEVICE(INTEL, 0xa182), board_ahci }, /* Lewisburg AHCI*/
- { PCI_VDEVICE(INTEL, 0xa202), board_ahci }, /* Lewisburg AHCI*/
- { PCI_VDEVICE(INTEL, 0xa184), board_ahci }, /* Lewisburg RAID*/
- { PCI_VDEVICE(INTEL, 0xa204), board_ahci }, /* Lewisburg RAID*/
- { PCI_VDEVICE(INTEL, 0xa186), board_ahci }, /* Lewisburg RAID*/
- { PCI_VDEVICE(INTEL, 0xa206), board_ahci }, /* Lewisburg RAID*/
- { PCI_VDEVICE(INTEL, 0x2822), board_ahci }, /* Lewisburg RAID*/
- { PCI_VDEVICE(INTEL, 0x2826), board_ahci }, /* Lewisburg RAID*/
- { PCI_VDEVICE(INTEL, 0xa18e), board_ahci }, /* Lewisburg RAID*/
- { PCI_VDEVICE(INTEL, 0xa20e), board_ahci }, /* Lewisburg RAID*/
{ PCI_VDEVICE(INTEL, 0x2823), board_ahci }, /* Wellsburg RAID */
{ PCI_VDEVICE(INTEL, 0x2827), board_ahci }, /* Wellsburg RAID */
{ PCI_VDEVICE(INTEL, 0x8d02), board_ahci }, /* Wellsburg AHCI */
{ PCI_VDEVICE(INTEL, 0x9d03), board_ahci }, /* Sunrise Point-LP AHCI */
{ PCI_VDEVICE(INTEL, 0x9d05), board_ahci }, /* Sunrise Point-LP RAID */
{ PCI_VDEVICE(INTEL, 0x9d07), board_ahci }, /* Sunrise Point-LP RAID */
+ { PCI_VDEVICE(INTEL, 0xa102), board_ahci }, /* Sunrise Point-H AHCI */
{ PCI_VDEVICE(INTEL, 0xa103), board_ahci }, /* Sunrise Point-H AHCI */
{ PCI_VDEVICE(INTEL, 0xa105), board_ahci }, /* Sunrise Point-H RAID */
+ { PCI_VDEVICE(INTEL, 0xa106), board_ahci }, /* Sunrise Point-H RAID */
{ PCI_VDEVICE(INTEL, 0xa107), board_ahci }, /* Sunrise Point-H RAID */
{ PCI_VDEVICE(INTEL, 0xa10f), board_ahci }, /* Sunrise Point-H RAID */
+ { PCI_VDEVICE(INTEL, 0x2822), board_ahci }, /* Lewisburg RAID*/
+ { PCI_VDEVICE(INTEL, 0x2826), board_ahci }, /* Lewisburg RAID*/
+ { PCI_VDEVICE(INTEL, 0xa182), board_ahci }, /* Lewisburg AHCI*/
+ { PCI_VDEVICE(INTEL, 0xa184), board_ahci }, /* Lewisburg RAID*/
+ { PCI_VDEVICE(INTEL, 0xa186), board_ahci }, /* Lewisburg RAID*/
+ { PCI_VDEVICE(INTEL, 0xa18e), board_ahci }, /* Lewisburg RAID*/
+ { PCI_VDEVICE(INTEL, 0xa202), board_ahci }, /* Lewisburg AHCI*/
+ { PCI_VDEVICE(INTEL, 0xa204), board_ahci }, /* Lewisburg RAID*/
+ { PCI_VDEVICE(INTEL, 0xa206), board_ahci }, /* Lewisburg RAID*/
+ { PCI_VDEVICE(INTEL, 0xa20e), board_ahci }, /* Lewisburg RAID*/
/* JMicron 360/1/3/5/6, match class to avoid IDE function */
{ PCI_VENDOR_ID_JMICRON, PCI_ANY_ID, PCI_ANY_ID, PCI_ANY_ID,
writel(0x80, hpriv->mmio + AHCI_VENDOR_SPECIFIC_0_DATA);
}
+#ifdef CONFIG_PM_SLEEP
static int ahci_mvebu_suspend(struct platform_device *pdev, pm_message_t state)
{
return ahci_platform_suspend_host(&pdev->dev);
return ahci_platform_resume_host(&pdev->dev);
}
+#else
+#define ahci_mvebu_suspend NULL
+#define ahci_mvebu_resume NULL
+#endif
static const struct ata_port_info ahci_mvebu_port_info = {
.flags = AHCI_FLAG_COMMON,
ata_tf_to_fis(tf, pmp, is_cmd, fis);
ahci_fill_cmd_slot(pp, 0, cmd_fis_len | flags | (pmp << 12));
+ /* set port value for softreset of Port Multiplier */
+ if (pp->fbs_enabled && pp->fbs_last_dev != pmp) {
+ tmp = readl(port_mmio + PORT_FBS);
+ tmp &= ~(PORT_FBS_DEV_MASK | PORT_FBS_DEC);
+ tmp |= pmp << PORT_FBS_DEV_OFFSET;
+ writel(tmp, port_mmio + PORT_FBS);
+ pp->fbs_last_dev = pmp;
+ }
+
/* issue & wait */
writel(1, port_mmio + PORT_CMD_ISSUE);
unsigned int ata_read_log_page(struct ata_device *dev, u8 log,
u8 page, void *buf, unsigned int sectors)
{
+ unsigned long ap_flags = dev->link->ap->flags;
struct ata_taskfile tf;
unsigned int err_mask;
bool dma = false;
DPRINTK("read log page - log 0x%x, page 0x%x\n", log, page);
+ /*
+ * Return error without actually issuing the command on controllers
+ * which e.g. lockup on a read log page.
+ */
+ if (ap_flags & ATA_FLAG_NO_LOG_PAGE)
+ return AC_ERR_DEV;
+
retry:
ata_tf_init(dev, &tf);
if (dev->dma_mode && ata_id_has_read_log_dma_ext(dev->id) &&
SATA_FSL_MAX_PRD_DIRECT = 16, /* Direct PRDT entries */
SATA_FSL_HOST_FLAGS = (ATA_FLAG_SATA | ATA_FLAG_PIO_DMA |
- ATA_FLAG_PMP | ATA_FLAG_NCQ | ATA_FLAG_AN),
+ ATA_FLAG_PMP | ATA_FLAG_NCQ |
+ ATA_FLAG_AN | ATA_FLAG_NO_LOG_PAGE),
SATA_FSL_MAX_CMDS = SATA_FSL_QUEUE_DEPTH,
SATA_FSL_CMD_HDR_SIZE = 16, /* 4 DWORDS */
unsigned int n, quirks = 0;
unsigned char model_num[ATA_ID_PROD_LEN + 1];
+ /* This controller doesn't support trim */
+ dev->horkage |= ATA_HORKAGE_NOTRIM;
+
ata_id_c_string(dev->id, model_num, ATA_ID_PROD, sizeof(model_num));
for (n = 0; sil_blacklist[n].product; n++)
/* CPU hot plug notifier */
struct notifier_block nb;
+
+ /* Control VQ buffers: protected by the rtnl lock */
+ struct virtio_net_ctrl_hdr ctrl_hdr;
+ virtio_net_ctrl_ack ctrl_status;
+ u8 ctrl_promisc;
+ u8 ctrl_allmulti;
};
struct padded_vnet_hdr {
struct scatterlist *out)
{
struct scatterlist *sgs[4], hdr, stat;
- struct virtio_net_ctrl_hdr ctrl;
- virtio_net_ctrl_ack status = ~0;
unsigned out_num = 0, tmp;
/* Caller should know better */
BUG_ON(!virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_VQ));
- ctrl.class = class;
- ctrl.cmd = cmd;
+ vi->ctrl_status = ~0;
+ vi->ctrl_hdr.class = class;
+ vi->ctrl_hdr.cmd = cmd;
/* Add header */
- sg_init_one(&hdr, &ctrl, sizeof(ctrl));
+ sg_init_one(&hdr, &vi->ctrl_hdr, sizeof(vi->ctrl_hdr));
sgs[out_num++] = &hdr;
if (out)
sgs[out_num++] = out;
/* Add return status. */
- sg_init_one(&stat, &status, sizeof(status));
+ sg_init_one(&stat, &vi->ctrl_status, sizeof(vi->ctrl_status));
sgs[out_num] = &stat;
BUG_ON(out_num + 1 > ARRAY_SIZE(sgs));
virtqueue_add_sgs(vi->cvq, sgs, out_num, 1, vi, GFP_ATOMIC);
if (unlikely(!virtqueue_kick(vi->cvq)))
- return status == VIRTIO_NET_OK;
+ return vi->ctrl_status == VIRTIO_NET_OK;
/* Spin for a response, the kick causes an ioport write, trapping
* into the hypervisor, so the request should be handled immediately.
!virtqueue_is_broken(vi->cvq))
cpu_relax();
- return status == VIRTIO_NET_OK;
+ return vi->ctrl_status == VIRTIO_NET_OK;
}
static int virtnet_set_mac_address(struct net_device *dev, void *p)
{
struct virtnet_info *vi = netdev_priv(dev);
struct scatterlist sg[2];
- u8 promisc, allmulti;
struct virtio_net_ctrl_mac *mac_data;
struct netdev_hw_addr *ha;
int uc_count;
if (!virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_RX))
return;
- promisc = ((dev->flags & IFF_PROMISC) != 0);
- allmulti = ((dev->flags & IFF_ALLMULTI) != 0);
+ vi->ctrl_promisc = ((dev->flags & IFF_PROMISC) != 0);
+ vi->ctrl_allmulti = ((dev->flags & IFF_ALLMULTI) != 0);
- sg_init_one(sg, &promisc, sizeof(promisc));
+ sg_init_one(sg, &vi->ctrl_promisc, sizeof(vi->ctrl_promisc));
if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_RX,
VIRTIO_NET_CTRL_RX_PROMISC, sg))
dev_warn(&dev->dev, "Failed to %sable promisc mode.\n",
- promisc ? "en" : "dis");
+ vi->ctrl_promisc ? "en" : "dis");
- sg_init_one(sg, &allmulti, sizeof(allmulti));
+ sg_init_one(sg, &vi->ctrl_allmulti, sizeof(vi->ctrl_allmulti));
if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_RX,
VIRTIO_NET_CTRL_RX_ALLMULTI, sg))
dev_warn(&dev->dev, "Failed to %sable allmulti mode.\n",
- allmulti ? "en" : "dis");
+ vi->ctrl_allmulti ? "en" : "dis");
uc_count = netdev_uc_count(dev);
mc_count = netdev_mc_count(dev);
BUILD_BUG_ON(__alignof__ *vq->used > VRING_USED_ALIGN_SIZE);
if ((a.avail_user_addr & (VRING_AVAIL_ALIGN_SIZE - 1)) ||
(a.used_user_addr & (VRING_USED_ALIGN_SIZE - 1)) ||
- (a.log_guest_addr & (sizeof(u64) - 1))) {
+ (a.log_guest_addr & (VRING_USED_ALIGN_SIZE - 1))) {
r = -EINVAL;
break;
}
/* Grab the next descriptor number they're advertising, and increment
* the index we've seen. */
if (unlikely(__get_user(ring_head,
- &vq->avail->ring[last_avail_idx % vq->num]))) {
+ &vq->avail->ring[last_avail_idx & (vq->num - 1)]))) {
vq_err(vq, "Failed to read head: idx %d address %p\n",
last_avail_idx,
&vq->avail->ring[last_avail_idx % vq->num]);
u16 old, new;
int start;
- start = vq->last_used_idx % vq->num;
+ start = vq->last_used_idx & (vq->num - 1);
used = vq->used->ring + start;
if (count == 1) {
if (__put_user(heads[0].id, &used->id)) {
{
int start, n, r;
- start = vq->last_used_idx % vq->num;
+ start = vq->last_used_idx & (vq->num - 1);
n = vq->num - start;
if (n < count) {
r = __vhost_add_used_n(vq, heads, n);
static void __exit virtio_exit(void)
{
bus_unregister(&virtio_bus);
+ ida_destroy(&virtio_index_ida);
}
core_initcall(virtio_init);
module_exit(virtio_exit);
/* Last used index we've seen. */
u16 last_used_idx;
+ /* Last written value to avail->flags */
+ u16 avail_flags_shadow;
+
+ /* Last written value to avail->idx in guest byte order */
+ u16 avail_idx_shadow;
+
/* How to notify other side. FIXME: commonalize hcalls! */
bool (*notify)(struct virtqueue *vq);
* otherwise virt_to_phys will give us bogus addresses in the
* virtqueue.
*/
- gfp &= ~(__GFP_HIGHMEM | __GFP_HIGH);
+ gfp &= ~__GFP_HIGHMEM;
desc = kmalloc(total_sg * sizeof(struct vring_desc), gfp);
if (!desc)
/* Put entry in available array (but don't update avail->idx until they
* do sync). */
- avail = virtio16_to_cpu(_vq->vdev, vq->vring.avail->idx) & (vq->vring.num - 1);
+ avail = vq->avail_idx_shadow & (vq->vring.num - 1);
vq->vring.avail->ring[avail] = cpu_to_virtio16(_vq->vdev, head);
/* Descriptors and available array need to be set before we expose the
* new available array entries. */
virtio_wmb(vq->weak_barriers);
- vq->vring.avail->idx = cpu_to_virtio16(_vq->vdev, virtio16_to_cpu(_vq->vdev, vq->vring.avail->idx) + 1);
+ vq->avail_idx_shadow++;
+ vq->vring.avail->idx = cpu_to_virtio16(_vq->vdev, vq->avail_idx_shadow);
vq->num_added++;
pr_debug("Added buffer head %i to %p\n", head, vq);
* event. */
virtio_mb(vq->weak_barriers);
- old = virtio16_to_cpu(_vq->vdev, vq->vring.avail->idx) - vq->num_added;
- new = virtio16_to_cpu(_vq->vdev, vq->vring.avail->idx);
+ old = vq->avail_idx_shadow - vq->num_added;
+ new = vq->avail_idx_shadow;
vq->num_added = 0;
#ifdef DEBUG
/* If we expect an interrupt for the next entry, tell host
* by writing event index and flush out the write before
* the read in the next get_buf call. */
- if (!(vq->vring.avail->flags & cpu_to_virtio16(_vq->vdev, VRING_AVAIL_F_NO_INTERRUPT))) {
+ if (!(vq->avail_flags_shadow & VRING_AVAIL_F_NO_INTERRUPT)) {
vring_used_event(&vq->vring) = cpu_to_virtio16(_vq->vdev, vq->last_used_idx);
virtio_mb(vq->weak_barriers);
}
{
struct vring_virtqueue *vq = to_vvq(_vq);
- vq->vring.avail->flags |= cpu_to_virtio16(_vq->vdev, VRING_AVAIL_F_NO_INTERRUPT);
+ if (!(vq->avail_flags_shadow & VRING_AVAIL_F_NO_INTERRUPT)) {
+ vq->avail_flags_shadow |= VRING_AVAIL_F_NO_INTERRUPT;
+ vq->vring.avail->flags = cpu_to_virtio16(_vq->vdev, vq->avail_flags_shadow);
+ }
+
}
EXPORT_SYMBOL_GPL(virtqueue_disable_cb);
/* Depending on the VIRTIO_RING_F_EVENT_IDX feature, we need to
* either clear the flags bit or point the event index at the next
* entry. Always do both to keep code simple. */
- vq->vring.avail->flags &= cpu_to_virtio16(_vq->vdev, ~VRING_AVAIL_F_NO_INTERRUPT);
+ if (vq->avail_flags_shadow & VRING_AVAIL_F_NO_INTERRUPT) {
+ vq->avail_flags_shadow &= ~VRING_AVAIL_F_NO_INTERRUPT;
+ vq->vring.avail->flags = cpu_to_virtio16(_vq->vdev, vq->avail_flags_shadow);
+ }
vring_used_event(&vq->vring) = cpu_to_virtio16(_vq->vdev, last_used_idx = vq->last_used_idx);
END_USE(vq);
return last_used_idx;
/* Depending on the VIRTIO_RING_F_USED_EVENT_IDX feature, we need to
* either clear the flags bit or point the event index at the next
* entry. Always do both to keep code simple. */
- vq->vring.avail->flags &= cpu_to_virtio16(_vq->vdev, ~VRING_AVAIL_F_NO_INTERRUPT);
+ if (vq->avail_flags_shadow & VRING_AVAIL_F_NO_INTERRUPT) {
+ vq->avail_flags_shadow &= ~VRING_AVAIL_F_NO_INTERRUPT;
+ vq->vring.avail->flags = cpu_to_virtio16(_vq->vdev, vq->avail_flags_shadow);
+ }
/* TODO: tune this threshold */
- bufs = (u16)(virtio16_to_cpu(_vq->vdev, vq->vring.avail->idx) - vq->last_used_idx) * 3 / 4;
+ bufs = (u16)(vq->avail_idx_shadow - vq->last_used_idx) * 3 / 4;
vring_used_event(&vq->vring) = cpu_to_virtio16(_vq->vdev, vq->last_used_idx + bufs);
virtio_mb(vq->weak_barriers);
if (unlikely((u16)(virtio16_to_cpu(_vq->vdev, vq->vring.used->idx) - vq->last_used_idx) > bufs)) {
/* detach_buf clears data, so grab it now. */
buf = vq->data[i];
detach_buf(vq, i);
- vq->vring.avail->idx = cpu_to_virtio16(_vq->vdev, virtio16_to_cpu(_vq->vdev, vq->vring.avail->idx) - 1);
+ vq->avail_idx_shadow--;
+ vq->vring.avail->idx = cpu_to_virtio16(_vq->vdev, vq->avail_idx_shadow);
END_USE(vq);
return buf;
}
vq->weak_barriers = weak_barriers;
vq->broken = false;
vq->last_used_idx = 0;
+ vq->avail_flags_shadow = 0;
+ vq->avail_idx_shadow = 0;
vq->num_added = 0;
list_add_tail(&vq->vq.list, &vdev->vqs);
#ifdef DEBUG
vq->event = virtio_has_feature(vdev, VIRTIO_RING_F_EVENT_IDX);
/* No callback? Tell other side not to bother us. */
- if (!callback)
- vq->vring.avail->flags |= cpu_to_virtio16(vdev, VRING_AVAIL_F_NO_INTERRUPT);
+ if (!callback) {
+ vq->avail_flags_shadow |= VRING_AVAIL_F_NO_INTERRUPT;
+ vq->vring.avail->flags = cpu_to_virtio16(vdev, vq->avail_flags_shadow);
+ }
/* Put everything in free lists. */
vq->free_head = 0;
struct ext4_crypto_ctx *ctx;
struct page *ciphertext_page = NULL;
struct bio *bio;
- ext4_lblk_t lblk = ex->ee_block;
+ ext4_lblk_t lblk = le32_to_cpu(ex->ee_block);
ext4_fsblk_t pblk = ext4_ext_pblock(ex);
unsigned int len = ext4_ext_get_actual_len(ex);
int ret, err = 0;
#include <linux/seqlock.h>
#include <linux/mutex.h>
#include <linux/timer.h>
+#include <linux/version.h>
#include <linux/wait.h>
#include <linux/blockgroup_lock.h>
#include <linux/percpu_counter.h>
<= (EXT4_GOOD_OLD_INODE_SIZE + \
(einode)->i_extra_isize)) \
+/*
+ * We use an encoding that preserves the times for extra epoch "00":
+ *
+ * extra msb of adjust for signed
+ * epoch 32-bit 32-bit tv_sec to
+ * bits time decoded 64-bit tv_sec 64-bit tv_sec valid time range
+ * 0 0 1 -0x80000000..-0x00000001 0x000000000 1901-12-13..1969-12-31
+ * 0 0 0 0x000000000..0x07fffffff 0x000000000 1970-01-01..2038-01-19
+ * 0 1 1 0x080000000..0x0ffffffff 0x100000000 2038-01-19..2106-02-07
+ * 0 1 0 0x100000000..0x17fffffff 0x100000000 2106-02-07..2174-02-25
+ * 1 0 1 0x180000000..0x1ffffffff 0x200000000 2174-02-25..2242-03-16
+ * 1 0 0 0x200000000..0x27fffffff 0x200000000 2242-03-16..2310-04-04
+ * 1 1 1 0x280000000..0x2ffffffff 0x300000000 2310-04-04..2378-04-22
+ * 1 1 0 0x300000000..0x37fffffff 0x300000000 2378-04-22..2446-05-10
+ *
+ * Note that previous versions of the kernel on 64-bit systems would
+ * incorrectly use extra epoch bits 1,1 for dates between 1901 and
+ * 1970. e2fsck will correct this, assuming that it is run on the
+ * affected filesystem before 2242.
+ */
+
static inline __le32 ext4_encode_extra_time(struct timespec *time)
{
- return cpu_to_le32((sizeof(time->tv_sec) > 4 ?
- (time->tv_sec >> 32) & EXT4_EPOCH_MASK : 0) |
- ((time->tv_nsec << EXT4_EPOCH_BITS) & EXT4_NSEC_MASK));
+ u32 extra = sizeof(time->tv_sec) > 4 ?
+ ((time->tv_sec - (s32)time->tv_sec) >> 32) & EXT4_EPOCH_MASK : 0;
+ return cpu_to_le32(extra | (time->tv_nsec << EXT4_EPOCH_BITS));
}
static inline void ext4_decode_extra_time(struct timespec *time, __le32 extra)
{
- if (sizeof(time->tv_sec) > 4)
- time->tv_sec |= (__u64)(le32_to_cpu(extra) & EXT4_EPOCH_MASK)
- << 32;
- time->tv_nsec = (le32_to_cpu(extra) & EXT4_NSEC_MASK) >> EXT4_EPOCH_BITS;
+ if (unlikely(sizeof(time->tv_sec) > 4 &&
+ (extra & cpu_to_le32(EXT4_EPOCH_MASK)))) {
+#if LINUX_VERSION_CODE < KERNEL_VERSION(4,20,0)
+ /* Handle legacy encoding of pre-1970 dates with epoch
+ * bits 1,1. We assume that by kernel version 4.20,
+ * everyone will have run fsck over the affected
+ * filesystems to correct the problem. (This
+ * backwards compatibility may be removed before this
+ * time, at the discretion of the ext4 developers.)
+ */
+ u64 extra_bits = le32_to_cpu(extra) & EXT4_EPOCH_MASK;
+ if (extra_bits == 3 && ((time->tv_sec) & 0x80000000) != 0)
+ extra_bits = 0;
+ time->tv_sec += extra_bits << 32;
+#else
+ time->tv_sec += (u64)(le32_to_cpu(extra) & EXT4_EPOCH_MASK) << 32;
+#endif
+ }
+ time->tv_nsec = (le32_to_cpu(extra) & EXT4_NSEC_MASK) >> EXT4_EPOCH_BITS;
}
#define EXT4_INODE_SET_XTIME(xtime, inode, raw_inode) \
/* Symlink is encrypted */
sd = (struct ext4_encrypted_symlink_data *)caddr;
cstr.name = sd->encrypted_path;
- cstr.len = le32_to_cpu(sd->len);
+ cstr.len = le16_to_cpu(sd->len);
if ((cstr.len +
sizeof(struct ext4_encrypted_symlink_data) - 1) >
max_size) {
return single_open(file, ext4_seq_##name##_show, PDE_DATA(inode)); \
} \
\
-const struct file_operations ext4_seq_##name##_fops = { \
+static const struct file_operations ext4_seq_##name##_fops = { \
.owner = THIS_MODULE, \
.open = name##_open, \
.read = seq_read, \
}
/* Fast check whether buffer is already attached to the required transaction */
-static bool jbd2_write_access_granted(handle_t *handle, struct buffer_head *bh)
+static bool jbd2_write_access_granted(handle_t *handle, struct buffer_head *bh,
+ bool undo)
{
struct journal_head *jh;
bool ret = false;
jh = READ_ONCE(bh->b_private);
if (!jh)
goto out;
+ /* For undo access buffer must have data copied */
+ if (undo && !jh->b_committed_data)
+ goto out;
if (jh->b_transaction != handle->h_transaction &&
jh->b_next_transaction != handle->h_transaction)
goto out;
struct journal_head *jh;
int rc;
- if (jbd2_write_access_granted(handle, bh))
+ if (jbd2_write_access_granted(handle, bh, false))
return 0;
jh = jbd2_journal_add_journal_head(bh);
char *committed_data = NULL;
JBUFFER_TRACE(jh, "entry");
- if (jbd2_write_access_granted(handle, bh))
+ if (jbd2_write_access_granted(handle, bh, true))
return 0;
jh = jbd2_journal_add_journal_head(bh);
if (!buffer_dirty(bh)) {
/* bdflush has written it. We can drop it now */
+ __jbd2_journal_remove_checkpoint(jh);
goto zap_buffer;
}
/* The orphan record's transaction has
* committed. We can cleanse this buffer */
clear_buffer_jbddirty(bh);
+ __jbd2_journal_remove_checkpoint(jh);
goto zap_buffer;
}
}
* Copyright 2001 Red Hat, Inc.
* Based on code from mm/memory.c Copyright Linus Torvalds and others.
*
- * Copyright 2011 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ * Copyright 2011 Red Hat, Inc., Peter Zijlstra
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* Jump label support
*
* Copyright (C) 2009-2012 Jason Baron <jbaron@redhat.com>
- * Copyright (C) 2011-2012 Peter Zijlstra <pzijlstr@redhat.com>
+ * Copyright (C) 2011-2012 Red Hat, Inc., Peter Zijlstra
*
* DEPRECATED API:
*
ATA_FLAG_SLAVE_POSS = (1 << 0), /* host supports slave dev */
/* (doesn't imply presence) */
ATA_FLAG_SATA = (1 << 1),
+ ATA_FLAG_NO_LOG_PAGE = (1 << 5), /* do not issue log page read */
ATA_FLAG_NO_ATAPI = (1 << 6), /* No ATAPI support */
ATA_FLAG_PIO_DMA = (1 << 7), /* PIO cmds via DMA */
ATA_FLAG_PIO_LBA48 = (1 << 8), /* Host DMA engine is LBA28 only */
* Runtime locking correctness validator
*
* Copyright (C) 2006,2007 Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
- * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra
*
* see Documentation/locking/lockdep-design.txt for more details.
*/
* if there is no cgroup event for the current CPU context.
*/
static inline struct perf_cgroup *
-perf_cgroup_from_task(struct task_struct *task)
+perf_cgroup_from_task(struct task_struct *task, struct perf_event_context *ctx)
{
- return container_of(task_css(task, perf_event_cgrp_id),
+ return container_of(task_css_check(task, perf_event_cgrp_id,
+ ctx ? lockdep_is_held(&ctx->lock)
+ : true),
struct perf_cgroup, css);
}
#endif /* CONFIG_CGROUP_PERF */
/*
* FLoating proportions
*
- * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra
*
* This file contains the public data structure and API definitions.
*/
* Authors:
* Srikar Dronamraju
* Jim Keniston
- * Copyright (C) 2011-2012 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ * Copyright (C) 2011-2012 Red Hat, Inc., Peter Zijlstra
*/
#include <linux/errno.h>
*
* Copyright (C) 2008 Thomas Gleixner <tglx@linutronix.de>
* Copyright (C) 2008-2011 Red Hat, Inc., Ingo Molnar
- * Copyright (C) 2008-2011 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ * Copyright (C) 2008-2011 Red Hat, Inc., Peter Zijlstra
* Copyright © 2009 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com>
*
* For licensing details see kernel-base/COPYING
*
* Copyright (C) 2008 Thomas Gleixner <tglx@linutronix.de>
* Copyright (C) 2008-2011 Red Hat, Inc., Ingo Molnar
- * Copyright (C) 2008-2011 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ * Copyright (C) 2008-2011 Red Hat, Inc., Peter Zijlstra
* Copyright © 2009 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com>
*
* For licensing details see kernel-base/COPYING
if (!is_cgroup_event(event))
return;
- cgrp = perf_cgroup_from_task(current);
+ cgrp = perf_cgroup_from_task(current, event->ctx);
/*
* Do not update time when cgroup is not active
*/
if (!task || !ctx->nr_cgroups)
return;
- cgrp = perf_cgroup_from_task(task);
+ cgrp = perf_cgroup_from_task(task, ctx);
info = this_cpu_ptr(cgrp->info);
info->timestamp = ctx->timestamp;
}
* we reschedule only in the presence of cgroup
* constrained events.
*/
- rcu_read_lock();
list_for_each_entry_rcu(pmu, &pmus, entry) {
cpuctx = this_cpu_ptr(pmu->pmu_cpu_context);
* set cgrp before ctxsw in to allow
* event_filter_match() to not have to pass
* task around
+ * we pass the cpuctx->ctx to perf_cgroup_from_task()
+ * because cgorup events are only per-cpu
*/
- cpuctx->cgrp = perf_cgroup_from_task(task);
+ cpuctx->cgrp = perf_cgroup_from_task(task, &cpuctx->ctx);
cpu_ctx_sched_in(cpuctx, EVENT_ALL, task);
}
perf_pmu_enable(cpuctx->ctx.pmu);
}
}
- rcu_read_unlock();
-
local_irq_restore(flags);
}
struct perf_cgroup *cgrp1;
struct perf_cgroup *cgrp2 = NULL;
+ rcu_read_lock();
/*
* we come here when we know perf_cgroup_events > 0
+ * we do not need to pass the ctx here because we know
+ * we are holding the rcu lock
*/
- cgrp1 = perf_cgroup_from_task(task);
+ cgrp1 = perf_cgroup_from_task(task, NULL);
/*
* next is NULL when called from perf_event_enable_on_exec()
* that will systematically cause a cgroup_switch()
*/
if (next)
- cgrp2 = perf_cgroup_from_task(next);
+ cgrp2 = perf_cgroup_from_task(next, NULL);
/*
* only schedule out current cgroup events if we know
*/
if (cgrp1 != cgrp2)
perf_cgroup_switch(task, PERF_CGROUP_SWOUT);
+
+ rcu_read_unlock();
}
static inline void perf_cgroup_sched_in(struct task_struct *prev,
struct perf_cgroup *cgrp1;
struct perf_cgroup *cgrp2 = NULL;
+ rcu_read_lock();
/*
* we come here when we know perf_cgroup_events > 0
+ * we do not need to pass the ctx here because we know
+ * we are holding the rcu lock
*/
- cgrp1 = perf_cgroup_from_task(task);
+ cgrp1 = perf_cgroup_from_task(task, NULL);
/* prev can never be NULL */
- cgrp2 = perf_cgroup_from_task(prev);
+ cgrp2 = perf_cgroup_from_task(prev, NULL);
/*
* only need to schedule in cgroup events if we are changing
*/
if (cgrp1 != cgrp2)
perf_cgroup_switch(task, PERF_CGROUP_SWIN);
+
+ rcu_read_unlock();
}
static inline int perf_cgroup_connect(int fd, struct perf_event *event,
goto retry;
}
- __perf_event_period(&pe);
+ if (event->attr.freq) {
+ event->attr.sample_freq = value;
+ } else {
+ event->attr.sample_period = value;
+ event->hw.sample_period = value;
+ }
+
+ local64_set(&event->hw.period_left, 0);
raw_spin_unlock_irq(&ctx->lock);
return 0;
}
}
+static void
+perf_event_aux_task_ctx(perf_event_aux_output_cb output, void *data,
+ struct perf_event_context *task_ctx)
+{
+ rcu_read_lock();
+ preempt_disable();
+ perf_event_aux_ctx(task_ctx, output, data);
+ preempt_enable();
+ rcu_read_unlock();
+}
+
static void
perf_event_aux(perf_event_aux_output_cb output, void *data,
struct perf_event_context *task_ctx)
struct pmu *pmu;
int ctxn;
+ /*
+ * If we have task_ctx != NULL we only notify
+ * the task context itself. The task_ctx is set
+ * only for EXIT events before releasing task
+ * context.
+ */
+ if (task_ctx) {
+ perf_event_aux_task_ctx(output, data, task_ctx);
+ return;
+ }
+
rcu_read_lock();
list_for_each_entry_rcu(pmu, &pmus, entry) {
cpuctx = get_cpu_ptr(pmu->pmu_cpu_context);
if (cpuctx->unique_pmu != pmu)
goto next;
perf_event_aux_ctx(&cpuctx->ctx, output, data);
- if (task_ctx)
- goto next;
ctxn = pmu->task_ctx_nr;
if (ctxn < 0)
goto next;
next:
put_cpu_ptr(pmu->pmu_cpu_context);
}
-
- if (task_ctx) {
- preempt_disable();
- perf_event_aux_ctx(task_ctx, output, data);
- preempt_enable();
- }
rcu_read_unlock();
}
struct perf_event_context *child_ctx, *clone_ctx = NULL;
unsigned long flags;
- if (likely(!child->perf_event_ctxp[ctxn])) {
- perf_event_task(child, NULL, 0);
+ if (likely(!child->perf_event_ctxp[ctxn]))
return;
- }
local_irq_save(flags);
/*
for_each_task_context_nr(ctxn)
perf_event_exit_task_context(child, ctxn);
+
+ /*
+ * The perf_event_exit_task_context calls perf_event_task
+ * with child's task_ctx, which generates EXIT events for
+ * child contexts and sets child->perf_event_ctxp[] to NULL.
+ * At this point we need to send EXIT events to cpu contexts.
+ */
+ perf_event_task(child, NULL, 0);
}
static void perf_free_event(struct perf_event *event,
static int __perf_cgroup_move(void *info)
{
struct task_struct *task = info;
+ rcu_read_lock();
perf_cgroup_switch(task, PERF_CGROUP_SWOUT | PERF_CGROUP_SWIN);
+ rcu_read_unlock();
return 0;
}
*
* Copyright (C) 2008 Thomas Gleixner <tglx@linutronix.de>
* Copyright (C) 2008-2011 Red Hat, Inc., Ingo Molnar
- * Copyright (C) 2008-2011 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ * Copyright (C) 2008-2011 Red Hat, Inc., Peter Zijlstra
* Copyright © 2009 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com>
*
* For licensing details see kernel-base/COPYING
* Authors:
* Srikar Dronamraju
* Jim Keniston
- * Copyright (C) 2011-2012 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ * Copyright (C) 2011-2012 Red Hat, Inc., Peter Zijlstra
*/
#include <linux/kernel.h>
/*
- * Copyright (C) 2010 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ * Copyright (C) 2010 Red Hat, Inc., Peter Zijlstra
*
* Provides a framework for enqueueing and running callbacks from hardirq
* context. The enqueueing is NMI-safe.
* jump label support
*
* Copyright (C) 2009 Jason Baron <jbaron@redhat.com>
- * Copyright (C) 2011 Peter Zijlstra <pzijlstr@redhat.com>
+ * Copyright (C) 2011 Peter Zijlstra
*
*/
#include <linux/memory.h>
* Started by Ingo Molnar:
*
* Copyright (C) 2006,2007 Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
- * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra
*
* this code maps all the lock dependencies as they occur in a live kernel
* and will warn about the following classes of locking bugs:
* Started by Ingo Molnar:
*
* Copyright (C) 2006,2007 Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
- * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra
*
* Code for /proc/lockdep and /proc/lockdep_stats:
*
/*
* sched_clock for unstable cpu clocks
*
- * Copyright (C) 2008 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ * Copyright (C) 2008 Red Hat, Inc., Peter Zijlstra
*
* Updates and enhancements:
* Copyright (C) 2008 Red Hat, Inc. Steven Rostedt <srostedt@redhat.com>
* Copyright (C) 2007, Thomas Gleixner <tglx@linutronix.de>
*
* Adaptive scheduling granularity, math enhancements by Peter Zijlstra
- * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra
*/
#include <linux/latencytop.h>
/*
* trace event based perf event profiling/tracing
*
- * Copyright (C) 2009 Red Hat Inc, Peter Zijlstra <pzijlstr@redhat.com>
+ * Copyright (C) 2009 Red Hat Inc, Peter Zijlstra
* Copyright (C) 2009-2010 Frederic Weisbecker <fweisbec@gmail.com>
*/
*
* Copyright (c) 2007-2008 Joern Engel <joern@logfs.org>
* Bits and pieces stolen from Peter Zijlstra's code, which is
- * Copyright 2007, Red Hat Inc. Peter Zijlstra <pzijlstr@redhat.com>
+ * Copyright 2007, Red Hat Inc. Peter Zijlstra
* GPLv2
*
* see http://programming.kicks-ass.net/kernel-patches/vma_lookup/btree.patch
/*
* Floating proportions
*
- * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra
*
* Description:
*
* mm/page-writeback.c
*
* Copyright (C) 2002, Linus Torvalds.
- * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra
*
* Contains functions related to writing back dirty pages at the
* address_space level.
(void) (&_min1 == &_min2); \
_min1 < _min2 ? _min1 : _min2; })
+/* TODO: empty stubs for now. Broken but enough for virtio_ring.c */
+#define list_add_tail(a, b) do {} while (0)
+#define list_del(a) do {} while (0)
+#define list_for_each_entry(a, b, c) while (0)
+/* end of stubs */
+
#endif /* KERNEL_H */
#include <linux/scatterlist.h>
#include <linux/kernel.h>
-/* TODO: empty stubs for now. Broken but enough for virtio_ring.c */
-#define list_add_tail(a, b) do {} while (0)
-#define list_del(a) do {} while (0)
-#define list_for_each_entry(a, b, c) while (0)
-/* end of stubs */
-
struct virtio_device {
void *dev;
u64 features;
#define virtio_has_feature(dev, feature) \
(__virtio_test_bit((dev), feature))
+static inline bool virtio_is_little_endian(struct virtio_device *vdev)
+{
+ return virtio_has_feature(vdev, VIRTIO_F_VERSION_1) ||
+ virtio_legacy_is_little_endian();
+}
+
+/* Memory accessors */
static inline u16 virtio16_to_cpu(struct virtio_device *vdev, __virtio16 val)
{
- return __virtio16_to_cpu(virtio_has_feature(vdev, VIRTIO_F_VERSION_1), val);
+ return __virtio16_to_cpu(virtio_is_little_endian(vdev), val);
}
static inline __virtio16 cpu_to_virtio16(struct virtio_device *vdev, u16 val)
{
- return __cpu_to_virtio16(virtio_has_feature(vdev, VIRTIO_F_VERSION_1), val);
+ return __cpu_to_virtio16(virtio_is_little_endian(vdev), val);
}
static inline u32 virtio32_to_cpu(struct virtio_device *vdev, __virtio32 val)
{
- return __virtio32_to_cpu(virtio_has_feature(vdev, VIRTIO_F_VERSION_1), val);
+ return __virtio32_to_cpu(virtio_is_little_endian(vdev), val);
}
static inline __virtio32 cpu_to_virtio32(struct virtio_device *vdev, u32 val)
{
- return __cpu_to_virtio32(virtio_has_feature(vdev, VIRTIO_F_VERSION_1), val);
+ return __cpu_to_virtio32(virtio_is_little_endian(vdev), val);
}
static inline u64 virtio64_to_cpu(struct virtio_device *vdev, __virtio64 val)
{
- return __virtio64_to_cpu(virtio_has_feature(vdev, VIRTIO_F_VERSION_1), val);
+ return __virtio64_to_cpu(virtio_is_little_endian(vdev), val);
}
static inline __virtio64 cpu_to_virtio64(struct virtio_device *vdev, u64 val)
{
- return __cpu_to_virtio64(virtio_has_feature(vdev, VIRTIO_F_VERSION_1), val);
+ return __cpu_to_virtio64(virtio_is_little_endian(vdev), val);
}
-