c547c8c45b
https://source.android.com/security/bulletin/2022-02-01 CVE-2021-39685 CVE-2021-39686 * tag 'ASB-2022-02-05_4.19-stable' of https://github.com/aosp-mirror/kernel_common: ANDROID: incremental-fs: remove index and incomplete dir on umount Revert "ASoC: dpcm: prevent snd_soc_dpcm use after free" Revert "ANDROID: android-4.19-stable build canary test." ANDROID: android-4.19-stable build canary test. Linux 4.19.227 drm/vmwgfx: Fix stale file descriptors on failed usercopy select: Fix indefinitely sleeping task in poll_schedule_timeout() net: bridge: clear bridge's private skb space on xmit drm/i915: Flush TLBs before releasing backing store Linux 4.19.226 fuse: fix live lock in fuse_iget() fuse: fix bad inode mips,s390,sh,sparc: gup: Work around the "COW can break either way" issue mtd: nand: bbt: Fix corner case in bad block table handling lib82596: Fix IRQ check in sni_82596_probe scripts/dtc: dtx_diff: remove broken example from help text bcmgenet: add WOL IRQ check net_sched: restore "mpu xxx" handling dmaengine: at_xdmac: Fix at_xdmac_lld struct definition dmaengine: at_xdmac: Fix lld view setting dmaengine: at_xdmac: Print debug message after realeasing the lock dmaengine: at_xdmac: Don't start transactions at tx_submit level libcxgb: Don't accidentally set RTO_ONLINK in cxgb_find_route() netns: add schedule point in ops_exit_list() rtc: pxa: fix null pointer dereference net: axienet: fix number of TX ring slots for available check net: axienet: Wait for PhyRstCmplt after core reset af_unix: annote lockless accesses to unix_tot_inflight & gc_in_progress parisc: pdc_stable: Fix memory leak in pdcs_register_pathentries net/fsl: xgmac_mdio: Fix incorrect iounmap when removing module powerpc/fsl/dts: Enable WA for erratum A-009885 on fman3l MDIO buses powerpc/cell: Fix clang -Wimplicit-fallthrough warning dmaengine: stm32-mdma: fix STM32_MDMA_CTBR_TSEL_MASK RDMA/rxe: Fix a typo in opcode name RDMA/hns: Modify the mapping attribute of doorbell to device Documentation: refer to config RANDOMIZE_BASE for kernel address-space randomization media: rcar-csi2: Optimize the selection PHTW register firmware: Update Kconfig help text for Google firmware ARM: dts: Fix vcsi regulator to be always-on for droid4 to prevent hangs drm/radeon: fix error handling in radeon_driver_open_kms regulator: core: Let boot-on regulators be powered off ASoC: dpcm: prevent snd_soc_dpcm use after free crypto: stm32/crc32 - Fix kernel BUG triggered in probe() ext4: don't use the orphan list when migrating an inode ext4: Fix BUG_ON in ext4_bread when write quota data ext4: set csum seed in tmp inode while migrating to extents ext4: make sure quota gets properly shutdown on error ext4: make sure to reset inode lockdep class when quota enabling fails drm/etnaviv: limit submit sizes s390/mm: fix 2KB pgtable release race iwlwifi: mvm: Increase the scan timeout guard to 30 seconds cputime, cpuacct: Include guest time in user time in cpuacct.stat serial: Fix incorrect rs485 polarity on uart open ubifs: Error path in ubifs_remount_rw() seems to wrongly free write buffers rpmsg: core: Clean up resources on announce_create failure. power: bq25890: Enable continuous conversion for ADC at charging ASoC: mediatek: mt8173: fix device_node leak scsi: sr: Don't use GFP_DMA MIPS: Octeon: Fix build errors using clang i2c: designware-pci: Fix to change data types of hcnt and lcnt parameters MIPS: OCTEON: add put_device() after of_find_device_by_node() powerpc: handle kdump appropriately with crash_kexec_post_notifiers option ALSA: seq: Set upper limit of processed events w1: Misuse of get_user()/put_user() reported by sparse i2c: mpc: Correct I2C reset procedure powerpc/smp: Move setup_profiling_timer() under CONFIG_PROFILING i2c: i801: Don't silently correct invalid transfer size powerpc/watchdog: Fix missed watchdog reset due to memory ordering race powerpc/btext: add missing of_node_put powerpc/cell: add missing of_node_put powerpc/powernv: add missing of_node_put powerpc/6xx: add missing of_node_put parisc: Avoid calling faulthandler_disabled() twice serial: core: Keep mctrl register state and cached copy in sync serial: pl010: Drop CR register reset on set_termios regulator: qcom_smd: Align probe function with rpmh-regulator net: gemini: allow any RGMII interface mode net: phy: marvell: configure RGMII delays for 88E1118 dm space map common: add bounds check to sm_ll_lookup_bitmap() dm btree: add a defensive bounds check to insert_at() mac80211: allow non-standard VHT MCS-10/11 net: mdio: Demote probed message to debug print btrfs: remove BUG_ON(!eie) in find_parent_nodes btrfs: remove BUG_ON() in find_parent_nodes() ACPI: battery: Add the ThinkPad "Not Charging" quirk drm/amdgpu: fixup bad vram size on gmc v8 ACPICA: Hardware: Do not flush CPU cache when entering S4 and S5 ACPICA: Executer: Fix the REFCLASS_REFOF case in acpi_ex_opcode_1A_0T_1R() ACPICA: Utilities: Avoid deleting the same object twice in a row ACPICA: actypes.h: Expand the ACPI_ACCESS_ definitions jffs2: GC deadlock reading a page that is used in jffs2_write_begin() um: registers: Rename function names to avoid conflicts and build problems iwlwifi: mvm: Fix calculation of frame length iwlwifi: remove module loading failure message iwlwifi: fix leaks/bad data after failed firmware load ath9k: Fix out-of-bound memcpy in ath9k_hif_usb_rx_stream usb: hub: Add delay for SuperSpeed hub resume to let links transit to U0 arm64: tegra: Adjust length of CCPLEX cluster MMIO region audit: ensure userspace is penalized the same as the kernel when under pressure mmc: core: Fixup storing of OCR for MMC_QUIRK_NONSTD_SDIO media: saa7146: hexium_gemini: Fix a NULL pointer dereference in hexium_attach() media: igorplugusb: receiver overflow should be reported HID: quirks: Allow inverting the absolute X/Y values bpf: Do not WARN in bpf_warn_invalid_xdp_action() net: bonding: debug: avoid printing debug logs when bond is not notifying peers x86/mce: Mark mce_read_aux() noinstr x86/mce: Mark mce_end() noinstr x86/mce: Mark mce_panic() noinstr net-sysfs: update the queue counts in the unregistration path ath10k: Fix tx hanging iwlwifi: mvm: synchronize with FW after multicast commands media: m920x: don't use stack on USB reads media: saa7146: hexium_orion: Fix a NULL pointer dereference in hexium_attach() media: uvcvideo: Increase UVC_CTRL_CONTROL_TIMEOUT to 5 seconds. floppy: Add max size check for user space request usb: uhci: add aspeed ast2600 uhci support rsi: Fix out-of-bounds read in rsi_read_pkt() mwifiex: Fix skb_over_panic in mwifiex_usb_recv() HSI: core: Fix return freed object in hsi_new_client gpiolib: acpi: Do not set the IRQ type if the IRQ is already in use drm/bridge: megachips: Ensure both bridges are probed before registration mlxsw: pci: Add shutdown method in PCI driver media: b2c2: Add missing check in flexcop_pci_isr: HID: apple: Do not reset quirks when the Fn key is not found usb: gadget: f_fs: Use stream_open() for endpoint files drm/nouveau/pmu/gm200-: avoid touching PMU outside of DEVINIT/PREOS/ACR ar5523: Fix null-ptr-deref with unexpected WDCMSG_TARGET_START reply fs: dlm: filter user dlm messages for kernel locks Bluetooth: Fix debugfs entry leak in hci_register_dev() RDMA/cxgb4: Set queue pair state when being queried mips: bcm63xx: add support for clk_set_parent() mips: lantiq: add support for clk_set_parent() misc: lattice-ecp3-config: Fix task hung when firmware load failed ASoC: samsung: idma: Check of ioremap return value ASoC: mediatek: Check for error clk pointer iommu/iova: Fix race between FQ timeout and teardown dmaengine: pxa/mmp: stop referencing config->slave_id ASoC: rt5663: Handle device_property_read_u32_array error codes RDMA/core: Let ib_find_gid() continue search even after empty entry scsi: ufs: Fix race conditions related to driver data iommu/io-pgtable-arm: Fix table descriptor paddr formatting char/mwave: Adjust io port register size ALSA: oss: fix compile error when OSS_DEBUG is enabled ASoC: uniphier: drop selecting non-existing SND_SOC_UNIPHIER_AIO_DMA powerpc/prom_init: Fix improper check of prom_getprop() RDMA/hns: Validate the pkey index ALSA: hda: Add missing rwsem around snd_ctl_remove() calls ALSA: PCM: Add missing rwsem around snd_ctl_remove() calls ALSA: jack: Add missing rwsem around snd_ctl_remove() calls ext4: avoid trim error on fs with small groups net: mcs7830: handle usb read errors properly pcmcia: fix setting of kthread task states can: xilinx_can: xcan_probe(): check for error irq can: softing: softing_startstop(): fix set but not used variable warning tpm: add request_locality before write TPM_INT_ENABLE spi: spi-meson-spifc: Add missing pm_runtime_disable() in meson_spifc_probe Bluetooth: hci_bcm: Check for error irq fsl/fman: Check for null pointer after calling devm_ioremap staging: greybus: audio: Check null pointer ppp: ensure minimum packet size in ppp_write() netfilter: ipt_CLUSTERIP: fix refcount leak in clusterip_tg_check() pcmcia: rsrc_nonstatic: Fix a NULL pointer dereference in nonstatic_find_mem_region() pcmcia: rsrc_nonstatic: Fix a NULL pointer dereference in __nonstatic_find_io_region() x86/mce/inject: Avoid out-of-bounds write when setting flags mmc: meson-mx-sdio: add IRQ check ARM: dts: armada-38x: Add generic compatible to UART nodes usb: ftdi-elan: fix memory leak on device disconnect xfrm: state and policy should fail if XFRMA_IF_ID 0 xfrm: interface with if_id 0 should return error drm/msm/dpu: fix safe status debugfs file media: coda/imx-vdoa: Handle dma_set_coherent_mask error codes media: msi001: fix possible null-ptr-deref in msi001_probe() media: dw2102: Fix use after free crypto: stm32/cryp - fix double pm exit xfrm: fix a small bug in xfrm_sa_len() sched/rt: Try to restart rt period timer when rt runtime exceeded media: si2157: Fix "warm" tuner state detection media: saa7146: mxb: Fix a NULL pointer dereference in mxb_attach() media: dib8000: Fix a memleak in dib8000_init() floppy: Fix hang in watchdog when disk is ejected serial: amba-pl011: do not request memory region twice tty: serial: uartlite: allow 64 bit address drm/radeon/radeon_kms: Fix a NULL pointer dereference in radeon_driver_open_kms() drm/amdgpu: Fix a NULL pointer dereference in amdgpu_connector_lcd_native_mode() arm64: dts: qcom: msm8916: fix MMC controller aliases netfilter: bridge: add support for pppoe filtering media: mtk-vcodec: call v4l2_m2m_ctx_release first when file is released media: si470x-i2c: fix possible memory leak in si470x_i2c_probe() media: rcar-csi2: Correct the selection of hsfreqrange tty: serial: atmel: Call dma_async_issue_pending() tty: serial: atmel: Check return code of dmaengine_submit() crypto: qce - fix uaf on qce_ahash_register_one media: dmxdev: fix UAF when dvb_register_device() fails tee: fix put order in teedev_close_context() Bluetooth: stop proccessing malicious adv data arm64: dts: meson-gxbb-wetek: fix missing GPIO binding media: em28xx: fix memory leak in em28xx_init_dev media: videobuf2: Fix the size printk format wcn36xx: Release DMA channel descriptor allocations wcn36xx: Indicate beacon not connection loss on MISSED_BEACON_IND clk: bcm-2835: Remove rounding up the dividers clk: bcm-2835: Pick the closest clock rate Bluetooth: cmtp: fix possible panic when cmtp_init_sockets() fails drm/panel: innolux-p079zca: Delete panel on attach() failure shmem: fix a race between shmem_unused_huge_shrink and shmem_evict_inode PCI: Add function 1 DMA alias quirk for Marvell 88SE9125 SATA controller lkdtm: Fix content of section containing lkdtm_rodata_do_nothing() can: softing_cs: softingcs_probe(): fix memleak on registration failure media: stk1160: fix control-message timeouts media: pvrusb2: fix control-message timeouts media: redrat3: fix control-message timeouts media: dib0700: fix undefined behavior in tuner shutdown media: s2255: fix control-message timeouts media: cpia2: fix control-message timeouts media: em28xx: fix control-message timeouts media: mceusb: fix control-message timeouts media: flexcop-usb: fix control-message timeouts rtc: cmos: take rtc_lock while reading from CMOS x86/gpu: Reserve stolen memory for first integrated Intel GPU mtd: rawnand: gpmi: Remove explicit default gpmi clock setting for i.MX6 nfc: llcp: fix NULL error pointer dereference on sendmsg() after failed bind() f2fs: fix to do sanity check in is_alive() HID: wacom: Avoid using stale array indicies to read contact count HID: wacom: Ignore the confidence flag when a touch is removed HID: wacom: Reset expected and received contact counts at the same time HID: uhid: Fix worker destroying device without any protection ALSA: hda/realtek - Fix silent output on Gigabyte X570 Aorus Master after reboot from Windows firmware: qemu_fw_cfg: fix kobject leak in probe error path firmware: qemu_fw_cfg: fix NULL-pointer deref on duplicate entries firmware: qemu_fw_cfg: fix sysfs information leak rtlwifi: rtl8192cu: Fix WARNING when calling local_irq_restore() with interrupts enabled media: uvcvideo: fix division by zero at stream start KVM: s390: Clarify SIGP orders versus STOP/RESTART orangefs: Fix the size of a memory allocation in orangefs_bufmap_alloc() kbuild: Add $(KBUILD_HOSTLDFLAGS) to 'has_libelf' test drm/i915: Avoid bitwise vs logical OR warning in snb_wm_latency_quirk() staging: wlan-ng: Avoid bitwise vs logical OR warning in hfa384x_usb_throttlefn() random: fix data race on crng init time random: fix data race on crng_node_pool can: gs_usb: gs_can_start_xmit(): zero-initialize hf->{flags,reserved} can: gs_usb: fix use of uninitialized variable, detach device on reception of invalid USB data mfd: intel-lpss: Fix too early PM enablement in the ACPI ->probe() veth: Do not record rx queue hint in veth_xmit can: bcm: switch timer to HRTIMER_MODE_SOFT and remove hrtimer_tasklet USB: Fix "slab-out-of-bounds Write" bug in usb_hcd_poll_rh_status USB: core: Fix bug in resuming hub's handling of wakeup requests Bluetooth: bfusb: fix division by zero in send path ANDROID: incremental-fs: fix mount_fs issue ANDROID: Add allowed symbols requried from Qualcomm drivers UPSTREAM: drivers core: Use sysfs_emit and sysfs_emit_at for show(device *...) functions UPSTREAM: x86/pci: Fix the function type for check_reserved_t Linux 4.19.225 mISDN: change function names to avoid conflicts net: udp: fix alignment problem in udp4_seq_show() ip6_vti: initialize __ip6_tnl_parm struct in vti6_siocdevprivate scsi: libiscsi: Fix UAF in iscsi_conn_get_param()/iscsi_conn_teardown() usb: mtu3: fix interval value for intr and isoc ipv6: Do cleanup if attribute validation fails in multipath route ipv6: Continue processing multipath route even if gateway attribute is invalid phonet: refcount leak in pep_sock_accep rndis_host: support Hytera digital radios power: reset: ltc2952: Fix use of floating point literals xfs: map unwritten blocks in XFS_IOC_{ALLOC,FREE}SP just like fallocate sch_qfq: prevent shift-out-of-bounds in qfq_init_qdisc ipv6: Check attribute length for RTA_GATEWAY when deleting multipath route ipv6: Check attribute length for RTA_GATEWAY in multipath route i40e: Fix incorrect netdev's real number of RX/TX queues i40e: fix use-after-free in i40e_sync_filters_subtask() mac80211: initialize variable have_higher_than_11mbit RDMA/core: Don't infoleak GRH fields ieee802154: atusb: fix uninit value in atusb_set_extended_addr tracing: Tag trace_percpu_buffer as a percpu pointer tracing: Fix check for trace_percpu_buffer validity in get_trace_buf() Change-Id: If855472ff18be9e734ef3f4d9f84adbd8c8c3883 Signed-off-by: UtsavBalar1231 <utsavbalar1231@gmail.com> Conflicts: drivers/media/dvb-core/dmxdev.c
1174 lines
30 KiB
C
1174 lines
30 KiB
C
/*
|
|
* Copyright © 2006-2009, Intel Corporation.
|
|
*
|
|
* This program is free software; you can redistribute it and/or modify it
|
|
* under the terms and conditions of the GNU General Public License,
|
|
* version 2, as published by the Free Software Foundation.
|
|
*
|
|
* This program is distributed in the hope it will be useful, but WITHOUT
|
|
* ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
|
|
* FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
|
|
* more details.
|
|
*
|
|
* You should have received a copy of the GNU General Public License along with
|
|
* this program; if not, write to the Free Software Foundation, Inc., 59 Temple
|
|
* Place - Suite 330, Boston, MA 02111-1307 USA.
|
|
*
|
|
* Author: Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com>
|
|
*/
|
|
|
|
#include <linux/iova.h>
|
|
#include <linux/module.h>
|
|
#include <linux/slab.h>
|
|
#include <linux/smp.h>
|
|
#include <linux/bitops.h>
|
|
#include <linux/cpu.h>
|
|
|
|
/* The anchor node sits above the top of the usable address space */
|
|
#define IOVA_ANCHOR ~0UL
|
|
|
|
static bool iova_rcache_insert(struct iova_domain *iovad,
|
|
unsigned long pfn,
|
|
unsigned long size);
|
|
static unsigned long iova_rcache_get(struct iova_domain *iovad,
|
|
unsigned long size,
|
|
unsigned long limit_pfn);
|
|
static void init_iova_rcaches(struct iova_domain *iovad);
|
|
static void free_iova_rcaches(struct iova_domain *iovad);
|
|
static void fq_destroy_all_entries(struct iova_domain *iovad);
|
|
static void fq_flush_timeout(struct timer_list *t);
|
|
|
|
void
|
|
init_iova_domain(struct iova_domain *iovad, unsigned long granule,
|
|
unsigned long start_pfn)
|
|
{
|
|
/*
|
|
* IOVA granularity will normally be equal to the smallest
|
|
* supported IOMMU page size; both *must* be capable of
|
|
* representing individual CPU pages exactly.
|
|
*/
|
|
BUG_ON((granule > PAGE_SIZE) || !is_power_of_2(granule));
|
|
|
|
spin_lock_init(&iovad->iova_rbtree_lock);
|
|
iovad->rbroot = RB_ROOT;
|
|
iovad->cached_node = &iovad->anchor.node;
|
|
iovad->cached32_node = &iovad->anchor.node;
|
|
iovad->granule = granule;
|
|
iovad->start_pfn = start_pfn;
|
|
iovad->dma_32bit_pfn = 1UL << (32 - iova_shift(iovad));
|
|
iovad->flush_cb = NULL;
|
|
iovad->fq = NULL;
|
|
iovad->anchor.pfn_lo = iovad->anchor.pfn_hi = IOVA_ANCHOR;
|
|
rb_link_node(&iovad->anchor.node, NULL, &iovad->rbroot.rb_node);
|
|
rb_insert_color(&iovad->anchor.node, &iovad->rbroot);
|
|
iovad->best_fit = false;
|
|
init_iova_rcaches(iovad);
|
|
}
|
|
EXPORT_SYMBOL_GPL(init_iova_domain);
|
|
|
|
bool has_iova_flush_queue(struct iova_domain *iovad)
|
|
{
|
|
return !!iovad->fq;
|
|
}
|
|
|
|
static void free_iova_flush_queue(struct iova_domain *iovad)
|
|
{
|
|
if (!has_iova_flush_queue(iovad))
|
|
return;
|
|
|
|
del_timer_sync(&iovad->fq_timer);
|
|
|
|
fq_destroy_all_entries(iovad);
|
|
|
|
free_percpu(iovad->fq);
|
|
|
|
iovad->fq = NULL;
|
|
iovad->flush_cb = NULL;
|
|
iovad->entry_dtor = NULL;
|
|
}
|
|
|
|
int init_iova_flush_queue(struct iova_domain *iovad,
|
|
iova_flush_cb flush_cb, iova_entry_dtor entry_dtor)
|
|
{
|
|
struct iova_fq __percpu *queue;
|
|
int cpu;
|
|
|
|
atomic64_set(&iovad->fq_flush_start_cnt, 0);
|
|
atomic64_set(&iovad->fq_flush_finish_cnt, 0);
|
|
|
|
queue = alloc_percpu(struct iova_fq);
|
|
if (!queue)
|
|
return -ENOMEM;
|
|
|
|
iovad->flush_cb = flush_cb;
|
|
iovad->entry_dtor = entry_dtor;
|
|
|
|
for_each_possible_cpu(cpu) {
|
|
struct iova_fq *fq;
|
|
|
|
fq = per_cpu_ptr(queue, cpu);
|
|
fq->head = 0;
|
|
fq->tail = 0;
|
|
|
|
spin_lock_init(&fq->lock);
|
|
}
|
|
|
|
smp_wmb();
|
|
|
|
iovad->fq = queue;
|
|
|
|
timer_setup(&iovad->fq_timer, fq_flush_timeout, 0);
|
|
atomic_set(&iovad->fq_timer_on, 0);
|
|
|
|
return 0;
|
|
}
|
|
EXPORT_SYMBOL_GPL(init_iova_flush_queue);
|
|
|
|
static struct rb_node *
|
|
__get_cached_rbnode(struct iova_domain *iovad, unsigned long limit_pfn)
|
|
{
|
|
if (limit_pfn <= iovad->dma_32bit_pfn)
|
|
return iovad->cached32_node;
|
|
|
|
return iovad->cached_node;
|
|
}
|
|
|
|
static void
|
|
__cached_rbnode_insert_update(struct iova_domain *iovad, struct iova *new)
|
|
{
|
|
if (new->pfn_hi < iovad->dma_32bit_pfn)
|
|
iovad->cached32_node = &new->node;
|
|
else
|
|
iovad->cached_node = &new->node;
|
|
}
|
|
|
|
static void
|
|
__cached_rbnode_delete_update(struct iova_domain *iovad, struct iova *free)
|
|
{
|
|
struct iova *cached_iova;
|
|
|
|
cached_iova = rb_entry(iovad->cached32_node, struct iova, node);
|
|
if (free == cached_iova ||
|
|
(free->pfn_hi < iovad->dma_32bit_pfn &&
|
|
free->pfn_lo >= cached_iova->pfn_lo))
|
|
iovad->cached32_node = rb_next(&free->node);
|
|
|
|
cached_iova = rb_entry(iovad->cached_node, struct iova, node);
|
|
if (free->pfn_lo >= cached_iova->pfn_lo)
|
|
iovad->cached_node = rb_next(&free->node);
|
|
}
|
|
|
|
/* Insert the iova into domain rbtree by holding writer lock */
|
|
static void
|
|
iova_insert_rbtree(struct rb_root *root, struct iova *iova,
|
|
struct rb_node *start)
|
|
{
|
|
struct rb_node **new, *parent = NULL;
|
|
|
|
new = (start) ? &start : &(root->rb_node);
|
|
/* Figure out where to put new node */
|
|
while (*new) {
|
|
struct iova *this = rb_entry(*new, struct iova, node);
|
|
|
|
parent = *new;
|
|
|
|
if (iova->pfn_lo < this->pfn_lo)
|
|
new = &((*new)->rb_left);
|
|
else if (iova->pfn_lo > this->pfn_lo)
|
|
new = &((*new)->rb_right);
|
|
else {
|
|
WARN_ON(1); /* this should not happen */
|
|
return;
|
|
}
|
|
}
|
|
/* Add new node and rebalance tree. */
|
|
rb_link_node(&iova->node, parent, new);
|
|
rb_insert_color(&iova->node, root);
|
|
}
|
|
|
|
#ifdef CONFIG_ARM64_DMA_IOMMU_ALIGNMENT
|
|
static unsigned long limit_align(struct iova_domain *iovad,
|
|
unsigned long shift)
|
|
{
|
|
unsigned long max;
|
|
|
|
max = CONFIG_ARM64_DMA_IOMMU_ALIGNMENT + PAGE_SHIFT
|
|
- iova_shift(iovad);
|
|
return min(shift, max);
|
|
}
|
|
#else
|
|
static unsigned long limit_align(struct iova_domain *iovad,
|
|
unsigned long shift)
|
|
{
|
|
return shift;
|
|
}
|
|
#endif
|
|
|
|
static int __alloc_and_insert_iova_range(struct iova_domain *iovad,
|
|
unsigned long size, unsigned long limit_pfn,
|
|
struct iova *new, bool size_aligned)
|
|
{
|
|
struct rb_node *curr, *prev;
|
|
struct iova *curr_iova;
|
|
unsigned long flags;
|
|
unsigned long new_pfn, low_pfn_new;
|
|
unsigned long align_mask = ~0UL;
|
|
unsigned long high_pfn = limit_pfn, low_pfn = iovad->start_pfn;
|
|
|
|
if (size_aligned)
|
|
align_mask <<= limit_align(iovad, fls_long(size - 1));
|
|
|
|
/* Walk the tree backwards */
|
|
spin_lock_irqsave(&iovad->iova_rbtree_lock, flags);
|
|
curr = __get_cached_rbnode(iovad, limit_pfn);
|
|
curr_iova = rb_entry(curr, struct iova, node);
|
|
low_pfn_new = curr_iova->pfn_hi + 1;
|
|
|
|
retry:
|
|
do {
|
|
high_pfn = min(high_pfn, curr_iova->pfn_lo);
|
|
new_pfn = (high_pfn - size) & align_mask;
|
|
prev = curr;
|
|
curr = rb_prev(curr);
|
|
curr_iova = rb_entry(curr, struct iova, node);
|
|
} while (curr && new_pfn <= curr_iova->pfn_hi && new_pfn >= low_pfn);
|
|
|
|
if (high_pfn < size || new_pfn < low_pfn) {
|
|
if (low_pfn == iovad->start_pfn && low_pfn_new < limit_pfn) {
|
|
high_pfn = limit_pfn;
|
|
low_pfn = low_pfn_new;
|
|
curr = &iovad->anchor.node;
|
|
curr_iova = rb_entry(curr, struct iova, node);
|
|
goto retry;
|
|
}
|
|
spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags);
|
|
return -ENOMEM;
|
|
}
|
|
|
|
/* pfn_lo will point to size aligned address if size_aligned is set */
|
|
new->pfn_lo = new_pfn;
|
|
new->pfn_hi = new->pfn_lo + size - 1;
|
|
|
|
/* If we have 'prev', it's a valid place to start the insertion. */
|
|
iova_insert_rbtree(&iovad->rbroot, new, prev);
|
|
__cached_rbnode_insert_update(iovad, new);
|
|
|
|
spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags);
|
|
|
|
|
|
return 0;
|
|
}
|
|
|
|
static int __alloc_and_insert_iova_best_fit(struct iova_domain *iovad,
|
|
unsigned long size, unsigned long limit_pfn,
|
|
struct iova *new, bool size_aligned)
|
|
{
|
|
struct rb_node *curr, *prev;
|
|
struct iova *curr_iova, *prev_iova;
|
|
unsigned long flags;
|
|
unsigned long align_mask = ~0UL;
|
|
struct rb_node *candidate_rb_parent;
|
|
unsigned long new_pfn, candidate_pfn = ~0UL;
|
|
unsigned long gap, candidate_gap = ~0UL;
|
|
|
|
if (size_aligned)
|
|
align_mask <<= limit_align(iovad, fls_long(size - 1));
|
|
|
|
/* Walk the tree backwards */
|
|
spin_lock_irqsave(&iovad->iova_rbtree_lock, flags);
|
|
curr = &iovad->anchor.node;
|
|
prev = rb_prev(curr);
|
|
for (; prev; curr = prev, prev = rb_prev(curr)) {
|
|
curr_iova = rb_entry(curr, struct iova, node);
|
|
prev_iova = rb_entry(prev, struct iova, node);
|
|
|
|
limit_pfn = min(limit_pfn, curr_iova->pfn_lo);
|
|
new_pfn = (limit_pfn - size) & align_mask;
|
|
gap = curr_iova->pfn_lo - prev_iova->pfn_hi - 1;
|
|
if ((limit_pfn >= size) && (new_pfn > prev_iova->pfn_hi)
|
|
&& (gap < candidate_gap)) {
|
|
candidate_gap = gap;
|
|
candidate_pfn = new_pfn;
|
|
candidate_rb_parent = curr;
|
|
if (gap == size)
|
|
goto insert;
|
|
}
|
|
}
|
|
|
|
curr_iova = rb_entry(curr, struct iova, node);
|
|
limit_pfn = min(limit_pfn, curr_iova->pfn_lo);
|
|
new_pfn = (limit_pfn - size) & align_mask;
|
|
gap = curr_iova->pfn_lo - iovad->start_pfn;
|
|
if (limit_pfn >= size && new_pfn >= iovad->start_pfn &&
|
|
gap < candidate_gap) {
|
|
candidate_gap = gap;
|
|
candidate_pfn = new_pfn;
|
|
candidate_rb_parent = curr;
|
|
}
|
|
|
|
insert:
|
|
if (candidate_pfn == ~0UL) {
|
|
spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags);
|
|
return -ENOMEM;
|
|
}
|
|
|
|
/* pfn_lo will point to size aligned address if size_aligned is set */
|
|
new->pfn_lo = candidate_pfn;
|
|
new->pfn_hi = new->pfn_lo + size - 1;
|
|
|
|
/* If we have 'prev', it's a valid place to start the insertion. */
|
|
iova_insert_rbtree(&iovad->rbroot, new, candidate_rb_parent);
|
|
spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags);
|
|
return 0;
|
|
}
|
|
|
|
static struct kmem_cache *iova_cache;
|
|
static unsigned int iova_cache_users;
|
|
static DEFINE_MUTEX(iova_cache_mutex);
|
|
|
|
struct iova *alloc_iova_mem(void)
|
|
{
|
|
return kmem_cache_zalloc(iova_cache, GFP_ATOMIC);
|
|
}
|
|
EXPORT_SYMBOL(alloc_iova_mem);
|
|
|
|
void free_iova_mem(struct iova *iova)
|
|
{
|
|
if (iova->pfn_lo != IOVA_ANCHOR)
|
|
kmem_cache_free(iova_cache, iova);
|
|
}
|
|
EXPORT_SYMBOL(free_iova_mem);
|
|
|
|
int iova_cache_get(void)
|
|
{
|
|
mutex_lock(&iova_cache_mutex);
|
|
if (!iova_cache_users) {
|
|
iova_cache = kmem_cache_create(
|
|
"iommu_iova", sizeof(struct iova), 0,
|
|
SLAB_HWCACHE_ALIGN, NULL);
|
|
if (!iova_cache) {
|
|
mutex_unlock(&iova_cache_mutex);
|
|
printk(KERN_ERR "Couldn't create iova cache\n");
|
|
return -ENOMEM;
|
|
}
|
|
}
|
|
|
|
iova_cache_users++;
|
|
mutex_unlock(&iova_cache_mutex);
|
|
|
|
return 0;
|
|
}
|
|
EXPORT_SYMBOL_GPL(iova_cache_get);
|
|
|
|
void iova_cache_put(void)
|
|
{
|
|
mutex_lock(&iova_cache_mutex);
|
|
if (WARN_ON(!iova_cache_users)) {
|
|
mutex_unlock(&iova_cache_mutex);
|
|
return;
|
|
}
|
|
iova_cache_users--;
|
|
if (!iova_cache_users)
|
|
kmem_cache_destroy(iova_cache);
|
|
mutex_unlock(&iova_cache_mutex);
|
|
}
|
|
EXPORT_SYMBOL_GPL(iova_cache_put);
|
|
|
|
/**
|
|
* alloc_iova - allocates an iova
|
|
* @iovad: - iova domain in question
|
|
* @size: - size of page frames to allocate
|
|
* @limit_pfn: - max limit address
|
|
* @size_aligned: - set if size_aligned address range is required
|
|
* This function allocates an iova in the range iovad->start_pfn to limit_pfn,
|
|
* searching top-down from limit_pfn to iovad->start_pfn. If the size_aligned
|
|
* flag is set then the allocated address iova->pfn_lo will be naturally
|
|
* aligned on roundup_power_of_two(size).
|
|
*/
|
|
struct iova *
|
|
alloc_iova(struct iova_domain *iovad, unsigned long size,
|
|
unsigned long limit_pfn,
|
|
bool size_aligned)
|
|
{
|
|
struct iova *new_iova;
|
|
int ret;
|
|
|
|
new_iova = alloc_iova_mem();
|
|
if (!new_iova)
|
|
return NULL;
|
|
|
|
if (iovad->best_fit) {
|
|
ret = __alloc_and_insert_iova_best_fit(iovad, size,
|
|
limit_pfn + 1, new_iova, size_aligned);
|
|
} else {
|
|
ret = __alloc_and_insert_iova_range(iovad, size, limit_pfn + 1,
|
|
new_iova, size_aligned);
|
|
}
|
|
|
|
if (ret) {
|
|
free_iova_mem(new_iova);
|
|
return NULL;
|
|
}
|
|
|
|
return new_iova;
|
|
}
|
|
EXPORT_SYMBOL_GPL(alloc_iova);
|
|
|
|
static struct iova *
|
|
private_find_iova(struct iova_domain *iovad, unsigned long pfn)
|
|
{
|
|
struct rb_node *node = iovad->rbroot.rb_node;
|
|
|
|
assert_spin_locked(&iovad->iova_rbtree_lock);
|
|
|
|
while (node) {
|
|
struct iova *iova = rb_entry(node, struct iova, node);
|
|
|
|
if (pfn < iova->pfn_lo)
|
|
node = node->rb_left;
|
|
else if (pfn > iova->pfn_hi)
|
|
node = node->rb_right;
|
|
else
|
|
return iova; /* pfn falls within iova's range */
|
|
}
|
|
|
|
return NULL;
|
|
}
|
|
|
|
static void private_free_iova(struct iova_domain *iovad, struct iova *iova)
|
|
{
|
|
assert_spin_locked(&iovad->iova_rbtree_lock);
|
|
__cached_rbnode_delete_update(iovad, iova);
|
|
rb_erase(&iova->node, &iovad->rbroot);
|
|
free_iova_mem(iova);
|
|
}
|
|
|
|
/**
|
|
* find_iova - finds an iova for a given pfn
|
|
* @iovad: - iova domain in question.
|
|
* @pfn: - page frame number
|
|
* This function finds and returns an iova belonging to the
|
|
* given doamin which matches the given pfn.
|
|
*/
|
|
struct iova *find_iova(struct iova_domain *iovad, unsigned long pfn)
|
|
{
|
|
unsigned long flags;
|
|
struct iova *iova;
|
|
|
|
/* Take the lock so that no other thread is manipulating the rbtree */
|
|
spin_lock_irqsave(&iovad->iova_rbtree_lock, flags);
|
|
iova = private_find_iova(iovad, pfn);
|
|
spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags);
|
|
return iova;
|
|
}
|
|
EXPORT_SYMBOL_GPL(find_iova);
|
|
|
|
/**
|
|
* __free_iova - frees the given iova
|
|
* @iovad: iova domain in question.
|
|
* @iova: iova in question.
|
|
* Frees the given iova belonging to the giving domain
|
|
*/
|
|
void
|
|
__free_iova(struct iova_domain *iovad, struct iova *iova)
|
|
{
|
|
unsigned long flags;
|
|
|
|
spin_lock_irqsave(&iovad->iova_rbtree_lock, flags);
|
|
private_free_iova(iovad, iova);
|
|
spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags);
|
|
}
|
|
EXPORT_SYMBOL_GPL(__free_iova);
|
|
|
|
/**
|
|
* free_iova - finds and frees the iova for a given pfn
|
|
* @iovad: - iova domain in question.
|
|
* @pfn: - pfn that is allocated previously
|
|
* This functions finds an iova for a given pfn and then
|
|
* frees the iova from that domain.
|
|
*/
|
|
void
|
|
free_iova(struct iova_domain *iovad, unsigned long pfn)
|
|
{
|
|
struct iova *iova = find_iova(iovad, pfn);
|
|
|
|
if (iova)
|
|
__free_iova(iovad, iova);
|
|
|
|
}
|
|
EXPORT_SYMBOL_GPL(free_iova);
|
|
|
|
/**
|
|
* alloc_iova_fast - allocates an iova from rcache
|
|
* @iovad: - iova domain in question
|
|
* @size: - size of page frames to allocate
|
|
* @limit_pfn: - max limit address
|
|
* @flush_rcache: - set to flush rcache on regular allocation failure
|
|
* This function tries to satisfy an iova allocation from the rcache,
|
|
* and falls back to regular allocation on failure. If regular allocation
|
|
* fails too and the flush_rcache flag is set then the rcache will be flushed.
|
|
*/
|
|
unsigned long
|
|
alloc_iova_fast(struct iova_domain *iovad, unsigned long size,
|
|
unsigned long limit_pfn, bool flush_rcache)
|
|
{
|
|
unsigned long iova_pfn;
|
|
struct iova *new_iova;
|
|
|
|
iova_pfn = iova_rcache_get(iovad, size, limit_pfn + 1);
|
|
if (iova_pfn)
|
|
return iova_pfn;
|
|
|
|
retry:
|
|
new_iova = alloc_iova(iovad, size, limit_pfn, true);
|
|
if (!new_iova) {
|
|
unsigned int cpu;
|
|
|
|
if (!flush_rcache)
|
|
return 0;
|
|
|
|
/* Try replenishing IOVAs by flushing rcache. */
|
|
flush_rcache = false;
|
|
for_each_online_cpu(cpu)
|
|
free_cpu_cached_iovas(cpu, iovad);
|
|
free_global_cached_iovas(iovad);
|
|
goto retry;
|
|
}
|
|
|
|
return new_iova->pfn_lo;
|
|
}
|
|
EXPORT_SYMBOL_GPL(alloc_iova_fast);
|
|
|
|
/**
|
|
* free_iova_fast - free iova pfn range into rcache
|
|
* @iovad: - iova domain in question.
|
|
* @pfn: - pfn that is allocated previously
|
|
* @size: - # of pages in range
|
|
* This functions frees an iova range by trying to put it into the rcache,
|
|
* falling back to regular iova deallocation via free_iova() if this fails.
|
|
*/
|
|
void
|
|
free_iova_fast(struct iova_domain *iovad, unsigned long pfn, unsigned long size)
|
|
{
|
|
if (iova_rcache_insert(iovad, pfn, size))
|
|
return;
|
|
|
|
free_iova(iovad, pfn);
|
|
}
|
|
EXPORT_SYMBOL_GPL(free_iova_fast);
|
|
|
|
#define fq_ring_for_each(i, fq) \
|
|
for ((i) = (fq)->head; (i) != (fq)->tail; (i) = ((i) + 1) % IOVA_FQ_SIZE)
|
|
|
|
static inline bool fq_full(struct iova_fq *fq)
|
|
{
|
|
assert_spin_locked(&fq->lock);
|
|
return (((fq->tail + 1) % IOVA_FQ_SIZE) == fq->head);
|
|
}
|
|
|
|
static inline unsigned fq_ring_add(struct iova_fq *fq)
|
|
{
|
|
unsigned idx = fq->tail;
|
|
|
|
assert_spin_locked(&fq->lock);
|
|
|
|
fq->tail = (idx + 1) % IOVA_FQ_SIZE;
|
|
|
|
return idx;
|
|
}
|
|
|
|
static void fq_ring_free(struct iova_domain *iovad, struct iova_fq *fq)
|
|
{
|
|
u64 counter = atomic64_read(&iovad->fq_flush_finish_cnt);
|
|
unsigned idx;
|
|
|
|
assert_spin_locked(&fq->lock);
|
|
|
|
fq_ring_for_each(idx, fq) {
|
|
|
|
if (fq->entries[idx].counter >= counter)
|
|
break;
|
|
|
|
if (iovad->entry_dtor)
|
|
iovad->entry_dtor(fq->entries[idx].data);
|
|
|
|
free_iova_fast(iovad,
|
|
fq->entries[idx].iova_pfn,
|
|
fq->entries[idx].pages);
|
|
|
|
fq->head = (fq->head + 1) % IOVA_FQ_SIZE;
|
|
}
|
|
}
|
|
|
|
static void iova_domain_flush(struct iova_domain *iovad)
|
|
{
|
|
atomic64_inc(&iovad->fq_flush_start_cnt);
|
|
iovad->flush_cb(iovad);
|
|
atomic64_inc(&iovad->fq_flush_finish_cnt);
|
|
}
|
|
|
|
static void fq_destroy_all_entries(struct iova_domain *iovad)
|
|
{
|
|
int cpu;
|
|
|
|
/*
|
|
* This code runs when the iova_domain is being detroyed, so don't
|
|
* bother to free iovas, just call the entry_dtor on all remaining
|
|
* entries.
|
|
*/
|
|
if (!iovad->entry_dtor)
|
|
return;
|
|
|
|
for_each_possible_cpu(cpu) {
|
|
struct iova_fq *fq = per_cpu_ptr(iovad->fq, cpu);
|
|
int idx;
|
|
|
|
fq_ring_for_each(idx, fq)
|
|
iovad->entry_dtor(fq->entries[idx].data);
|
|
}
|
|
}
|
|
|
|
static void fq_flush_timeout(struct timer_list *t)
|
|
{
|
|
struct iova_domain *iovad = from_timer(iovad, t, fq_timer);
|
|
int cpu;
|
|
|
|
atomic_set(&iovad->fq_timer_on, 0);
|
|
iova_domain_flush(iovad);
|
|
|
|
for_each_possible_cpu(cpu) {
|
|
unsigned long flags;
|
|
struct iova_fq *fq;
|
|
|
|
fq = per_cpu_ptr(iovad->fq, cpu);
|
|
spin_lock_irqsave(&fq->lock, flags);
|
|
fq_ring_free(iovad, fq);
|
|
spin_unlock_irqrestore(&fq->lock, flags);
|
|
}
|
|
}
|
|
|
|
void queue_iova(struct iova_domain *iovad,
|
|
unsigned long pfn, unsigned long pages,
|
|
unsigned long data)
|
|
{
|
|
struct iova_fq *fq = raw_cpu_ptr(iovad->fq);
|
|
unsigned long flags;
|
|
unsigned idx;
|
|
|
|
spin_lock_irqsave(&fq->lock, flags);
|
|
|
|
/*
|
|
* First remove all entries from the flush queue that have already been
|
|
* flushed out on another CPU. This makes the fq_full() check below less
|
|
* likely to be true.
|
|
*/
|
|
fq_ring_free(iovad, fq);
|
|
|
|
if (fq_full(fq)) {
|
|
iova_domain_flush(iovad);
|
|
fq_ring_free(iovad, fq);
|
|
}
|
|
|
|
idx = fq_ring_add(fq);
|
|
|
|
fq->entries[idx].iova_pfn = pfn;
|
|
fq->entries[idx].pages = pages;
|
|
fq->entries[idx].data = data;
|
|
fq->entries[idx].counter = atomic64_read(&iovad->fq_flush_start_cnt);
|
|
|
|
spin_unlock_irqrestore(&fq->lock, flags);
|
|
|
|
/* Avoid false sharing as much as possible. */
|
|
if (!atomic_read(&iovad->fq_timer_on) &&
|
|
!atomic_cmpxchg(&iovad->fq_timer_on, 0, 1))
|
|
mod_timer(&iovad->fq_timer,
|
|
jiffies + msecs_to_jiffies(IOVA_FQ_TIMEOUT));
|
|
}
|
|
EXPORT_SYMBOL_GPL(queue_iova);
|
|
|
|
/**
|
|
* put_iova_domain - destroys the iova doamin
|
|
* @iovad: - iova domain in question.
|
|
* All the iova's in that domain are destroyed.
|
|
*/
|
|
void put_iova_domain(struct iova_domain *iovad)
|
|
{
|
|
struct iova *iova, *tmp;
|
|
|
|
free_iova_flush_queue(iovad);
|
|
free_iova_rcaches(iovad);
|
|
rbtree_postorder_for_each_entry_safe(iova, tmp, &iovad->rbroot, node)
|
|
free_iova_mem(iova);
|
|
}
|
|
EXPORT_SYMBOL_GPL(put_iova_domain);
|
|
|
|
static int
|
|
__is_range_overlap(struct rb_node *node,
|
|
unsigned long pfn_lo, unsigned long pfn_hi)
|
|
{
|
|
struct iova *iova = rb_entry(node, struct iova, node);
|
|
|
|
if ((pfn_lo <= iova->pfn_hi) && (pfn_hi >= iova->pfn_lo))
|
|
return 1;
|
|
return 0;
|
|
}
|
|
|
|
static inline struct iova *
|
|
alloc_and_init_iova(unsigned long pfn_lo, unsigned long pfn_hi)
|
|
{
|
|
struct iova *iova;
|
|
|
|
iova = alloc_iova_mem();
|
|
if (iova) {
|
|
iova->pfn_lo = pfn_lo;
|
|
iova->pfn_hi = pfn_hi;
|
|
}
|
|
|
|
return iova;
|
|
}
|
|
|
|
static struct iova *
|
|
__insert_new_range(struct iova_domain *iovad,
|
|
unsigned long pfn_lo, unsigned long pfn_hi)
|
|
{
|
|
struct iova *iova;
|
|
|
|
iova = alloc_and_init_iova(pfn_lo, pfn_hi);
|
|
if (iova)
|
|
iova_insert_rbtree(&iovad->rbroot, iova, NULL);
|
|
|
|
return iova;
|
|
}
|
|
|
|
static void
|
|
__adjust_overlap_range(struct iova *iova,
|
|
unsigned long *pfn_lo, unsigned long *pfn_hi)
|
|
{
|
|
if (*pfn_lo < iova->pfn_lo)
|
|
iova->pfn_lo = *pfn_lo;
|
|
if (*pfn_hi > iova->pfn_hi)
|
|
*pfn_lo = iova->pfn_hi + 1;
|
|
}
|
|
|
|
/**
|
|
* reserve_iova - reserves an iova in the given range
|
|
* @iovad: - iova domain pointer
|
|
* @pfn_lo: - lower page frame address
|
|
* @pfn_hi:- higher pfn adderss
|
|
* This function allocates reserves the address range from pfn_lo to pfn_hi so
|
|
* that this address is not dished out as part of alloc_iova.
|
|
*/
|
|
struct iova *
|
|
reserve_iova(struct iova_domain *iovad,
|
|
unsigned long pfn_lo, unsigned long pfn_hi)
|
|
{
|
|
struct rb_node *node;
|
|
unsigned long flags;
|
|
struct iova *iova;
|
|
unsigned int overlap = 0;
|
|
|
|
/* Don't allow nonsensical pfns */
|
|
if (WARN_ON((pfn_hi | pfn_lo) > (ULLONG_MAX >> iova_shift(iovad))))
|
|
return NULL;
|
|
|
|
spin_lock_irqsave(&iovad->iova_rbtree_lock, flags);
|
|
for (node = rb_first(&iovad->rbroot); node; node = rb_next(node)) {
|
|
if (__is_range_overlap(node, pfn_lo, pfn_hi)) {
|
|
iova = rb_entry(node, struct iova, node);
|
|
__adjust_overlap_range(iova, &pfn_lo, &pfn_hi);
|
|
if ((pfn_lo >= iova->pfn_lo) &&
|
|
(pfn_hi <= iova->pfn_hi))
|
|
goto finish;
|
|
overlap = 1;
|
|
|
|
} else if (overlap)
|
|
break;
|
|
}
|
|
|
|
/* We are here either because this is the first reserver node
|
|
* or need to insert remaining non overlap addr range
|
|
*/
|
|
iova = __insert_new_range(iovad, pfn_lo, pfn_hi);
|
|
finish:
|
|
|
|
spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags);
|
|
return iova;
|
|
}
|
|
EXPORT_SYMBOL_GPL(reserve_iova);
|
|
|
|
/**
|
|
* copy_reserved_iova - copies the reserved between domains
|
|
* @from: - source doamin from where to copy
|
|
* @to: - destination domin where to copy
|
|
* This function copies reserved iova's from one doamin to
|
|
* other.
|
|
*/
|
|
void
|
|
copy_reserved_iova(struct iova_domain *from, struct iova_domain *to)
|
|
{
|
|
unsigned long flags;
|
|
struct rb_node *node;
|
|
|
|
spin_lock_irqsave(&from->iova_rbtree_lock, flags);
|
|
for (node = rb_first(&from->rbroot); node; node = rb_next(node)) {
|
|
struct iova *iova = rb_entry(node, struct iova, node);
|
|
struct iova *new_iova;
|
|
|
|
if (iova->pfn_lo == IOVA_ANCHOR)
|
|
continue;
|
|
|
|
new_iova = reserve_iova(to, iova->pfn_lo, iova->pfn_hi);
|
|
if (!new_iova)
|
|
printk(KERN_ERR "Reserve iova range %lx@%lx failed\n",
|
|
iova->pfn_lo, iova->pfn_lo);
|
|
}
|
|
spin_unlock_irqrestore(&from->iova_rbtree_lock, flags);
|
|
}
|
|
EXPORT_SYMBOL_GPL(copy_reserved_iova);
|
|
|
|
struct iova *
|
|
split_and_remove_iova(struct iova_domain *iovad, struct iova *iova,
|
|
unsigned long pfn_lo, unsigned long pfn_hi)
|
|
{
|
|
unsigned long flags;
|
|
struct iova *prev = NULL, *next = NULL;
|
|
|
|
spin_lock_irqsave(&iovad->iova_rbtree_lock, flags);
|
|
if (iova->pfn_lo < pfn_lo) {
|
|
prev = alloc_and_init_iova(iova->pfn_lo, pfn_lo - 1);
|
|
if (prev == NULL)
|
|
goto error;
|
|
}
|
|
if (iova->pfn_hi > pfn_hi) {
|
|
next = alloc_and_init_iova(pfn_hi + 1, iova->pfn_hi);
|
|
if (next == NULL)
|
|
goto error;
|
|
}
|
|
|
|
__cached_rbnode_delete_update(iovad, iova);
|
|
rb_erase(&iova->node, &iovad->rbroot);
|
|
|
|
if (prev) {
|
|
iova_insert_rbtree(&iovad->rbroot, prev, NULL);
|
|
iova->pfn_lo = pfn_lo;
|
|
}
|
|
if (next) {
|
|
iova_insert_rbtree(&iovad->rbroot, next, NULL);
|
|
iova->pfn_hi = pfn_hi;
|
|
}
|
|
spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags);
|
|
|
|
return iova;
|
|
|
|
error:
|
|
spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags);
|
|
if (prev)
|
|
free_iova_mem(prev);
|
|
return NULL;
|
|
}
|
|
|
|
/*
|
|
* Magazine caches for IOVA ranges. For an introduction to magazines,
|
|
* see the USENIX 2001 paper "Magazines and Vmem: Extending the Slab
|
|
* Allocator to Many CPUs and Arbitrary Resources" by Bonwick and Adams.
|
|
* For simplicity, we use a static magazine size and don't implement the
|
|
* dynamic size tuning described in the paper.
|
|
*/
|
|
|
|
#define IOVA_MAG_SIZE 128
|
|
|
|
struct iova_magazine {
|
|
unsigned long size;
|
|
unsigned long pfns[IOVA_MAG_SIZE];
|
|
};
|
|
|
|
struct iova_cpu_rcache {
|
|
spinlock_t lock;
|
|
struct iova_magazine *loaded;
|
|
struct iova_magazine *prev;
|
|
};
|
|
|
|
static struct iova_magazine *iova_magazine_alloc(gfp_t flags)
|
|
{
|
|
return kzalloc(sizeof(struct iova_magazine), flags);
|
|
}
|
|
|
|
static void iova_magazine_free(struct iova_magazine *mag)
|
|
{
|
|
kfree(mag);
|
|
}
|
|
|
|
static void
|
|
iova_magazine_free_pfns(struct iova_magazine *mag, struct iova_domain *iovad)
|
|
{
|
|
unsigned long flags;
|
|
int i;
|
|
|
|
if (!mag)
|
|
return;
|
|
|
|
spin_lock_irqsave(&iovad->iova_rbtree_lock, flags);
|
|
|
|
for (i = 0 ; i < mag->size; ++i) {
|
|
struct iova *iova = private_find_iova(iovad, mag->pfns[i]);
|
|
|
|
if (WARN_ON(!iova))
|
|
continue;
|
|
|
|
private_free_iova(iovad, iova);
|
|
}
|
|
|
|
spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags);
|
|
|
|
mag->size = 0;
|
|
}
|
|
|
|
static bool iova_magazine_full(struct iova_magazine *mag)
|
|
{
|
|
return (mag && mag->size == IOVA_MAG_SIZE);
|
|
}
|
|
|
|
static bool iova_magazine_empty(struct iova_magazine *mag)
|
|
{
|
|
return (!mag || mag->size == 0);
|
|
}
|
|
|
|
static unsigned long iova_magazine_pop(struct iova_magazine *mag,
|
|
unsigned long limit_pfn)
|
|
{
|
|
int i;
|
|
unsigned long pfn;
|
|
|
|
BUG_ON(iova_magazine_empty(mag));
|
|
|
|
/* Only fall back to the rbtree if we have no suitable pfns at all */
|
|
for (i = mag->size - 1; mag->pfns[i] > limit_pfn; i--)
|
|
if (i == 0)
|
|
return 0;
|
|
|
|
/* Swap it to pop it */
|
|
pfn = mag->pfns[i];
|
|
mag->pfns[i] = mag->pfns[--mag->size];
|
|
|
|
return pfn;
|
|
}
|
|
|
|
static void iova_magazine_push(struct iova_magazine *mag, unsigned long pfn)
|
|
{
|
|
BUG_ON(iova_magazine_full(mag));
|
|
|
|
mag->pfns[mag->size++] = pfn;
|
|
}
|
|
|
|
static void init_iova_rcaches(struct iova_domain *iovad)
|
|
{
|
|
struct iova_cpu_rcache *cpu_rcache;
|
|
struct iova_rcache *rcache;
|
|
unsigned int cpu;
|
|
int i;
|
|
|
|
for (i = 0; i < IOVA_RANGE_CACHE_MAX_SIZE; ++i) {
|
|
rcache = &iovad->rcaches[i];
|
|
spin_lock_init(&rcache->lock);
|
|
rcache->depot_size = 0;
|
|
rcache->cpu_rcaches = __alloc_percpu(sizeof(*cpu_rcache), cache_line_size());
|
|
if (WARN_ON(!rcache->cpu_rcaches))
|
|
continue;
|
|
for_each_possible_cpu(cpu) {
|
|
cpu_rcache = per_cpu_ptr(rcache->cpu_rcaches, cpu);
|
|
spin_lock_init(&cpu_rcache->lock);
|
|
cpu_rcache->loaded = iova_magazine_alloc(GFP_KERNEL);
|
|
cpu_rcache->prev = iova_magazine_alloc(GFP_KERNEL);
|
|
}
|
|
}
|
|
}
|
|
|
|
/*
|
|
* Try inserting IOVA range starting with 'iova_pfn' into 'rcache', and
|
|
* return true on success. Can fail if rcache is full and we can't free
|
|
* space, and free_iova() (our only caller) will then return the IOVA
|
|
* range to the rbtree instead.
|
|
*/
|
|
static bool __iova_rcache_insert(struct iova_domain *iovad,
|
|
struct iova_rcache *rcache,
|
|
unsigned long iova_pfn)
|
|
{
|
|
struct iova_magazine *mag_to_free = NULL;
|
|
struct iova_cpu_rcache *cpu_rcache;
|
|
bool can_insert = false;
|
|
unsigned long flags;
|
|
|
|
cpu_rcache = raw_cpu_ptr(rcache->cpu_rcaches);
|
|
spin_lock_irqsave(&cpu_rcache->lock, flags);
|
|
|
|
if (!iova_magazine_full(cpu_rcache->loaded)) {
|
|
can_insert = true;
|
|
} else if (!iova_magazine_full(cpu_rcache->prev)) {
|
|
swap(cpu_rcache->prev, cpu_rcache->loaded);
|
|
can_insert = true;
|
|
} else {
|
|
struct iova_magazine *new_mag = iova_magazine_alloc(GFP_ATOMIC);
|
|
|
|
if (new_mag) {
|
|
spin_lock(&rcache->lock);
|
|
if (rcache->depot_size < MAX_GLOBAL_MAGS) {
|
|
rcache->depot[rcache->depot_size++] =
|
|
cpu_rcache->loaded;
|
|
} else {
|
|
mag_to_free = cpu_rcache->loaded;
|
|
}
|
|
spin_unlock(&rcache->lock);
|
|
|
|
cpu_rcache->loaded = new_mag;
|
|
can_insert = true;
|
|
}
|
|
}
|
|
|
|
if (can_insert)
|
|
iova_magazine_push(cpu_rcache->loaded, iova_pfn);
|
|
|
|
spin_unlock_irqrestore(&cpu_rcache->lock, flags);
|
|
|
|
if (mag_to_free) {
|
|
iova_magazine_free_pfns(mag_to_free, iovad);
|
|
iova_magazine_free(mag_to_free);
|
|
}
|
|
|
|
return can_insert;
|
|
}
|
|
|
|
static bool iova_rcache_insert(struct iova_domain *iovad, unsigned long pfn,
|
|
unsigned long size)
|
|
{
|
|
unsigned int log_size = order_base_2(size);
|
|
|
|
if (log_size >= IOVA_RANGE_CACHE_MAX_SIZE)
|
|
return false;
|
|
|
|
return __iova_rcache_insert(iovad, &iovad->rcaches[log_size], pfn);
|
|
}
|
|
|
|
/*
|
|
* Caller wants to allocate a new IOVA range from 'rcache'. If we can
|
|
* satisfy the request, return a matching non-NULL range and remove
|
|
* it from the 'rcache'.
|
|
*/
|
|
static unsigned long __iova_rcache_get(struct iova_rcache *rcache,
|
|
unsigned long limit_pfn)
|
|
{
|
|
struct iova_cpu_rcache *cpu_rcache;
|
|
unsigned long iova_pfn = 0;
|
|
bool has_pfn = false;
|
|
unsigned long flags;
|
|
|
|
cpu_rcache = raw_cpu_ptr(rcache->cpu_rcaches);
|
|
spin_lock_irqsave(&cpu_rcache->lock, flags);
|
|
|
|
if (!iova_magazine_empty(cpu_rcache->loaded)) {
|
|
has_pfn = true;
|
|
} else if (!iova_magazine_empty(cpu_rcache->prev)) {
|
|
swap(cpu_rcache->prev, cpu_rcache->loaded);
|
|
has_pfn = true;
|
|
} else {
|
|
spin_lock(&rcache->lock);
|
|
if (rcache->depot_size > 0) {
|
|
iova_magazine_free(cpu_rcache->loaded);
|
|
cpu_rcache->loaded = rcache->depot[--rcache->depot_size];
|
|
has_pfn = true;
|
|
}
|
|
spin_unlock(&rcache->lock);
|
|
}
|
|
|
|
if (has_pfn)
|
|
iova_pfn = iova_magazine_pop(cpu_rcache->loaded, limit_pfn);
|
|
|
|
spin_unlock_irqrestore(&cpu_rcache->lock, flags);
|
|
|
|
return iova_pfn;
|
|
}
|
|
|
|
/*
|
|
* Try to satisfy IOVA allocation range from rcache. Fail if requested
|
|
* size is too big or the DMA limit we are given isn't satisfied by the
|
|
* top element in the magazine.
|
|
*/
|
|
static unsigned long iova_rcache_get(struct iova_domain *iovad,
|
|
unsigned long size,
|
|
unsigned long limit_pfn)
|
|
{
|
|
unsigned int log_size = order_base_2(size);
|
|
|
|
if (log_size >= IOVA_RANGE_CACHE_MAX_SIZE)
|
|
return 0;
|
|
|
|
return __iova_rcache_get(&iovad->rcaches[log_size], limit_pfn - size);
|
|
}
|
|
|
|
/*
|
|
* free rcache data structures.
|
|
*/
|
|
static void free_iova_rcaches(struct iova_domain *iovad)
|
|
{
|
|
struct iova_rcache *rcache;
|
|
struct iova_cpu_rcache *cpu_rcache;
|
|
unsigned int cpu;
|
|
int i, j;
|
|
|
|
for (i = 0; i < IOVA_RANGE_CACHE_MAX_SIZE; ++i) {
|
|
rcache = &iovad->rcaches[i];
|
|
for_each_possible_cpu(cpu) {
|
|
cpu_rcache = per_cpu_ptr(rcache->cpu_rcaches, cpu);
|
|
iova_magazine_free(cpu_rcache->loaded);
|
|
iova_magazine_free(cpu_rcache->prev);
|
|
}
|
|
free_percpu(rcache->cpu_rcaches);
|
|
for (j = 0; j < rcache->depot_size; ++j)
|
|
iova_magazine_free(rcache->depot[j]);
|
|
}
|
|
}
|
|
|
|
/*
|
|
* free all the IOVA ranges cached by a cpu (used when cpu is unplugged)
|
|
*/
|
|
void free_cpu_cached_iovas(unsigned int cpu, struct iova_domain *iovad)
|
|
{
|
|
struct iova_cpu_rcache *cpu_rcache;
|
|
struct iova_rcache *rcache;
|
|
unsigned long flags;
|
|
int i;
|
|
|
|
for (i = 0; i < IOVA_RANGE_CACHE_MAX_SIZE; ++i) {
|
|
rcache = &iovad->rcaches[i];
|
|
cpu_rcache = per_cpu_ptr(rcache->cpu_rcaches, cpu);
|
|
spin_lock_irqsave(&cpu_rcache->lock, flags);
|
|
iova_magazine_free_pfns(cpu_rcache->loaded, iovad);
|
|
iova_magazine_free_pfns(cpu_rcache->prev, iovad);
|
|
spin_unlock_irqrestore(&cpu_rcache->lock, flags);
|
|
}
|
|
}
|
|
|
|
/*
|
|
* free all the IOVA ranges of global cache
|
|
*/
|
|
void free_global_cached_iovas(struct iova_domain *iovad)
|
|
{
|
|
struct iova_rcache *rcache;
|
|
unsigned long flags;
|
|
int i, j;
|
|
|
|
for (i = 0; i < IOVA_RANGE_CACHE_MAX_SIZE; ++i) {
|
|
rcache = &iovad->rcaches[i];
|
|
spin_lock_irqsave(&rcache->lock, flags);
|
|
for (j = 0; j < rcache->depot_size; ++j) {
|
|
iova_magazine_free_pfns(rcache->depot[j], iovad);
|
|
iova_magazine_free(rcache->depot[j]);
|
|
rcache->depot[j] = NULL;
|
|
}
|
|
rcache->depot_size = 0;
|
|
spin_unlock_irqrestore(&rcache->lock, flags);
|
|
}
|
|
}
|
|
|
|
MODULE_AUTHOR("Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com>");
|
|
MODULE_LICENSE("GPL");
|