msm-4.14/mm/nobootmem.c
Runmin Wang 253c6dff4b Merge remote-tracking branch 'remotes/origin/tmp-39dae59' into msm-next
* remotes/msm-4.9/tmp-39dae59:
  Linux 4.14-rc8
  x86/module: Detect and skip invalid relocations
  objtool: Prevent GCC from merging annotate_unreachable(), take 2
  Revert "x86/mm: Stop calling leave_mm() in idle code"
  Documentation: Add Frank Rowand to list of enforcement statement endorsers
  doc: add Willy Tarreau to the list of enforcement statement endorsers
  tools/headers: Synchronize kernel ABI headers
  objtool: Resync objtool's instruction decoder source code copy with the kernel's latest version
  Input: sparse-keymap - send sync event for KE_SW/KE_VSW
  Input: ar1021_i2c - set INPUT_PROP_DIRECT
  arch/tile: Implement ->set_state_oneshot_stopped()
  Update MIPS email addresses
  x86: CPU: Fix up "cpu MHz" in /proc/cpuinfo
  mm, swap: fix race between swap count continuation operations
  mm/huge_memory.c: deposit page table when copying a PMD migration entry
  initramfs: fix initramfs rebuilds w/ compression after disabling
  fs/hugetlbfs/inode.c: fix hwpoison reserve accounting
  ocfs2: fstrim: Fix start offset of first cluster group during fstrim
  mm, /proc/pid/pagemap: fix soft dirty marking for PMD migration entry
  userfaultfd: hugetlbfs: prevent UFFDIO_COPY to fill beyond the end of i_size
  Documentation: Add Tim Bird to list of enforcement statement endorsers
  net: systemport: Correct IPG length settings
  tcp: do not mangle skb->cb[] in tcp_make_synack()
  fib: fib_dump_info can no longer use __in_dev_get_rtnl
  stmmac: use of_property_read_u32 instead of read_u8
  net_sched: hold netns refcnt for each action
  net_sched: acquire RTNL in tc_action_net_exit()
  powerpc/perf: Fix core-imc hotplug callback failure during imc initialization
  Kbuild: don't pass "-C" to preprocessor when processing linker scripts
  Revert "x86: do not use cpufreq_quick_get() for /proc/cpuinfo "cpu MHz""
  arm64: ensure __dump_instr() checks addr_limit
  KVM: x86: Update APICv on APIC reset
  KVM: VMX: Do not fully reset PI descriptor on vCPU reset
  kvm: Return -ENODEV from update_persistent_clock
  futex: futex_wake_op, do not fail on invalid op
  MIPS: Update email address for Marcin Nowakowski
  License cleanup: add SPDX license identifier to uapi header files with a license
  License cleanup: add SPDX license identifier to uapi header files with no license
  License cleanup: add SPDX GPL-2.0 license identifier to files with no license
  KEYS: fix out-of-bounds read during ASN.1 parsing
  KEYS: trusted: fix writing past end of buffer in trusted_read()
  KEYS: return full count in keyring_read() if buffer is too small
  net: vrf: correct FRA_L3MDEV encode type
  tcp_nv: fix division by zero in tcpnv_acked()
  drm/amdgpu: allow harvesting check for Polaris VCE
  drm/amdgpu: return -ENOENT from uvd 6.0 early init for harvesting
  ARM: add debug ".edata_real" symbol
  MIPS: smp-cmp: Fix vpe_id build error
  MAINTAINERS: Update Pistachio platform maintainers
  MIPS: smp-cmp: Use right include for task_struct
  signal: Fix name of SIGEMT in #if defined() check
  MIPS: Update Goldfish RTC driver maintainer email address
  MIPS: Update RINT emulation maintainer email address
  MIPS: CPS: Fix use of current_cpu_data in preemptible code
  x86/mcelog: Get rid of RCU remnants
  watchdog/hardlockup/perf: Use atomics to track in-use cpu counter
  watchdog/harclockup/perf: Revert a33d44843d45 ("watchdog/hardlockup/perf: Simplify deferred event destroy")
  ARM: 8716/1: pass endianness info to sparse
  drm/i915: Check incoming alignment for unfenced buffers (on i915gm)
  x86/mm: fix use-after-free of vma during userfaultfd fault
  ide:ide-cd: fix kernel panic resulting from missing scsi_req_init
  mmc: dw_mmc: Fix the DTO timeout calculation
  tcp: fix tcp_mtu_probe() vs highest_sack
  ipv6: addrconf: increment ifp refcount before ipv6_del_addr()
  tun/tap: sanitize TUNSETSNDBUF input
  mlxsw: i2c: Fix buffer increment counter for write transaction
  netfilter: nf_reject_ipv4: Fix use-after-free in send_reset
  futex: Fix more put_pi_state() vs. exit_pi_state_list() races
  powerpc/kprobes: Dereference function pointers only if the address does not belong to kernel text
  Revert "powerpc64/elfv1: Only dereference function descriptor for non-text symbols"
  mlxsw: reg: Add high and low temperature thresholds
  MAINTAINERS: Remove Yotam from mlxfw
  MAINTAINERS: Update Yotam's E-mail
  net: hns: set correct return value
  net: lapbether: fix double free
  bpf: remove SK_REDIRECT from UAPI
  net: phy: marvell: Only configure RGMII delays when using RGMII
  MIPS: SMP: Fix deadlock & online race
  MIPS: bpf: Fix a typo in build_one_insn()
  MIPS: microMIPS: Fix incorrect mask in insn_table_MM
  MIPS: Fix CM region target definitions
  MIPS: generic: Fix compilation error from include asm/mips-cpc.h
  MIPS: Fix exception entry when CONFIG_EVA enabled
  irqchip/irq-mvebu-gicp: Add missing spin_lock init
  drm/nouveau/kms/nv50: use the correct state for base channel notifier setup
  MIPS: generic: Fix NI 169445 its build
  Update MIPS email addresses
  tile: pass machine size to sparse
  selftests: lib.mk: print individual test results to console by default
  RDMA/nldev: Enforce device index check for port callback
  Revert "PM / QoS: Fix device resume latency PM QoS"
  Revert "PM / QoS: Fix default runtime_pm device resume latency"
  scsi: qla2xxx: Fix oops in qla2x00_probe_one error path
  xfrm: Fix GSO for IPsec with GRE tunnel.
  ALSA: seq: Fix nested rwsem annotation for lockdep splat
  ALSA: timer: Add missing mutex lock for compat ioctls
  tc-testing: fix arg to ip command: -s -> -n
  net_sched: remove tcf_block_put_deferred()
  l2tp: hold tunnel in pppol2tp_connect()
  drm/i915: Hold rcu_read_lock when iterating over the radixtree (vma idr)
  drm/i915: Hold rcu_read_lock when iterating over the radixtree (objects)
  drm/i915/edp: read edp display control registers unconditionally
  drm/i915: Do not rely on wm preservation for ILK watermarks
  drm/i915: Cancel the modeset retry work during modeset cleanup
  Mark 'ioremap_page_range()' as possibly sleeping
  nvme: Fix setting logical block format when revalidating
  mmc: dw_mmc: Add locking to the CTO timer
  mmc: dw_mmc: Fix the CTO timeout calculation
  mmc: dw_mmc: cancel the CTO timer after a voltage switch
  perf/cgroup: Fix perf cgroup hierarchy support
  PM / QoS: Fix default runtime_pm device resume latency
  Revert "ath10k: fix napi_poll budget overflow"
  ath10k: rebuild crypto header in rx data frames
  cifs: check MaxPathNameComponentLength != 0 before using it
  KVM: arm/arm64: vgic-its: Check GITS_BASER Valid bit before saving tables
  KVM: arm/arm64: vgic-its: Check CBASER/BASER validity before enabling the ITS
  KVM: arm/arm64: vgic-its: Fix vgic_its_restore_collection_table returned value
  KVM: arm/arm64: vgic-its: Fix return value for device table restore
  efi/libstub: arm: omit sorting of the UEFI memory map
  perf tools: Unwind properly location after REJECT
  virtio_blk: Fix an SG_IO regression
  wcn36xx: Remove unnecessary rcu_read_unlock in wcn36xx_bss_info_changed
  ARM: dts: mvebu: pl310-cache disable double-linefill
  xfrm: Clear sk_dst_cache when applying per-socket policy.
  perf symbols: Fix memory corruption because of zero length symbols
  powerpc/64s/radix: Fix preempt imbalance in TLB flush
  netfilter: nft_set_hash: disable fast_ops for 2-len keys
  powerpc: Fix check for copy/paste instructions in alignment handler
  powerpc/perf: Fix IMC allocation routine
  xfrm: Fix xfrm_dst_cache memleak
  ARM: 8715/1: add a private asm/unaligned.h
  clk: uniphier: fix clock data for PXs3
  Documentation: Add my name to kernel enforcement statement
  nvme-rdma: fix possible hang when issuing commands during ctrl removal
  arm/arm64: kvm: Disable branch profiling in HYP code
  arm/arm64: kvm: Move initialization completion message
  arm/arm64: KVM: set right LR register value for 32 bit guest when inject abort
  Documentation: kernel-enforcement-statement.rst: proper sort names
  ASoC: rt5616: fix 0x91 default value
  Documentation: Add Arm Ltd to kernel-enforcement-statement.rst
  arm64: dts: uniphier: add STDMAC clock to EHCI nodes
  ARM: dts: uniphier: add STDMAC clock to EHCI nodes
  mmc: renesas_sdhi: fix kernel panic in _internal_dmac.c
  mmc: tmio: fix swiotlb buffer is full
  Documentation: kernel-enforcement-statement.rst: Remove Red Hat markings
  Documentation: Add myself to the enforcement statement list
  Documentation: Sign kernel enforcement statement
  Add ack for Trond Myklebust to the enforcement statement
  Documentation: update kernel enforcement support list
  Documentation: add my name to supporters
  ASoC: rt5659: connect LOUT Amp with Charge Pump
  ASoC: rt5659: register power bit of LOUT Amp
  KVM: arm64: its: Fix missing dynamic allocation check in scan_its_table
  crypto: x86/chacha20 - satisfy stack validation 2.0
  ASoC: rt5663: Change the dev getting function in rt5663_irq
  ASoC: rt5514: Revert Hotword Model control
  ASoC: topology: Fix a potential memory leak in 'soc_tplg_dapm_widget_denum_create()'
  ASoC: topology: Fix a potential NULL pointer dereference in 'soc_tplg_dapm_widget_denum_create()'
  ASoC: rt5514-spi: check irq status to schedule data copy
  ASoC: adau17x1: Workaround for noise bug in ADC

  Conflicts:
	drivers/gpu/drm/msm/Makefile
	drivers/soc/qcom/Makefile
	drivers/staging/android/ion/Makefile
	include/linux/coresight-stm.h
	include/trace/events/kmem.h

Change-Id: I01f1779762b652b9213924caa3d54f29cf03d285
Signed-off-by: Runmin Wang <runminw@codeaurora.org>
2017-11-06 11:37:20 -08:00

438 lines
11 KiB
C

// SPDX-License-Identifier: GPL-2.0
/*
* bootmem - A boot-time physical memory allocator and configurator
*
* Copyright (C) 1999 Ingo Molnar
* 1999 Kanoj Sarcar, SGI
* 2008 Johannes Weiner
*
* Access to this subsystem has to be serialized externally (which is true
* for the boot process anyway).
*/
#include <linux/init.h>
#include <linux/pfn.h>
#include <linux/slab.h>
#include <linux/export.h>
#include <linux/kmemleak.h>
#include <linux/range.h>
#include <linux/memblock.h>
#include <linux/bootmem.h>
#include <asm/bug.h>
#include <asm/io.h>
#include "internal.h"
#ifndef CONFIG_HAVE_MEMBLOCK
#error CONFIG_HAVE_MEMBLOCK not defined
#endif
#ifndef CONFIG_NEED_MULTIPLE_NODES
struct pglist_data __refdata contig_page_data;
EXPORT_SYMBOL(contig_page_data);
#endif
unsigned long max_low_pfn;
unsigned long min_low_pfn;
unsigned long max_pfn;
unsigned long long max_possible_pfn;
static void * __init __alloc_memory_core_early(int nid, u64 size, u64 align,
u64 goal, u64 limit)
{
void *ptr;
u64 addr;
ulong flags = choose_memblock_flags();
if (limit > memblock.current_limit)
limit = memblock.current_limit;
again:
addr = memblock_find_in_range_node(size, align, goal, limit, nid,
flags);
if (!addr && (flags & MEMBLOCK_MIRROR)) {
flags &= ~MEMBLOCK_MIRROR;
pr_warn("Could not allocate %pap bytes of mirrored memory\n",
&size);
goto again;
}
if (!addr)
return NULL;
if (memblock_reserve(addr, size))
return NULL;
ptr = phys_to_virt(addr);
memset(ptr, 0, size);
/*
* The min_count is set to 0 so that bootmem allocated blocks
* are never reported as leaks.
*/
kmemleak_alloc(ptr, size, 0, 0);
return ptr;
}
/*
* free_bootmem_late - free bootmem pages directly to page allocator
* @addr: starting address of the range
* @size: size of the range in bytes
*
* This is only useful when the bootmem allocator has already been torn
* down, but we are still initializing the system. Pages are given directly
* to the page allocator, no bootmem metadata is updated because it is gone.
*/
void free_bootmem_late(unsigned long addr, unsigned long size)
{
unsigned long cursor, end;
kmemleak_free_part_phys(addr, size);
cursor = PFN_UP(addr);
end = PFN_DOWN(addr + size);
for (; cursor < end; cursor++) {
__free_pages_bootmem(pfn_to_page(cursor), cursor, 0);
totalram_pages++;
}
}
static void __init __free_pages_memory(unsigned long start, unsigned long end)
{
int order;
while (start < end) {
order = min(MAX_ORDER - 1UL, __ffs(start));
while (start + (1UL << order) > end)
order--;
__free_pages_bootmem(pfn_to_page(start), start, order);
start += (1UL << order);
}
}
static unsigned long __init __free_memory_core(phys_addr_t start,
phys_addr_t end)
{
unsigned long start_pfn = PFN_UP(start);
unsigned long end_pfn = min_t(unsigned long,
PFN_DOWN(end), max_low_pfn);
if (start_pfn >= end_pfn)
return 0;
__free_pages_memory(start_pfn, end_pfn);
return end_pfn - start_pfn;
}
static unsigned long __init free_low_memory_core_early(void)
{
unsigned long count = 0;
phys_addr_t start, end;
u64 i;
memblock_clear_hotplug(0, -1);
for_each_reserved_mem_region(i, &start, &end)
reserve_bootmem_region(start, end);
/*
* We need to use NUMA_NO_NODE instead of NODE_DATA(0)->node_id
* because in some case like Node0 doesn't have RAM installed
* low ram will be on Node1
*/
for_each_free_mem_range(i, NUMA_NO_NODE, MEMBLOCK_NONE, &start, &end,
NULL)
count += __free_memory_core(start, end);
return count;
}
static int reset_managed_pages_done __initdata;
void reset_node_managed_pages(pg_data_t *pgdat)
{
struct zone *z;
for (z = pgdat->node_zones; z < pgdat->node_zones + MAX_NR_ZONES; z++)
z->managed_pages = 0;
}
void __init reset_all_zones_managed_pages(void)
{
struct pglist_data *pgdat;
if (reset_managed_pages_done)
return;
for_each_online_pgdat(pgdat)
reset_node_managed_pages(pgdat);
reset_managed_pages_done = 1;
}
/**
* free_all_bootmem - release free pages to the buddy allocator
*
* Returns the number of pages actually released.
*/
unsigned long __init free_all_bootmem(void)
{
unsigned long pages;
reset_all_zones_managed_pages();
pages = free_low_memory_core_early();
totalram_pages += pages;
return pages;
}
/**
* free_bootmem_node - mark a page range as usable
* @pgdat: node the range resides on
* @physaddr: starting address of the range
* @size: size of the range in bytes
*
* Partial pages will be considered reserved and left as they are.
*
* The range must reside completely on the specified node.
*/
void __init free_bootmem_node(pg_data_t *pgdat, unsigned long physaddr,
unsigned long size)
{
memblock_free(physaddr, size);
}
/**
* free_bootmem - mark a page range as usable
* @addr: starting address of the range
* @size: size of the range in bytes
*
* Partial pages will be considered reserved and left as they are.
*
* The range must be contiguous but may span node boundaries.
*/
void __init free_bootmem(unsigned long addr, unsigned long size)
{
memblock_free(addr, size);
}
static void * __init ___alloc_bootmem_nopanic(unsigned long size,
unsigned long align,
unsigned long goal,
unsigned long limit)
{
void *ptr;
if (WARN_ON_ONCE(slab_is_available()))
return kzalloc(size, GFP_NOWAIT);
restart:
ptr = __alloc_memory_core_early(NUMA_NO_NODE, size, align, goal, limit);
if (ptr)
return ptr;
if (goal != 0) {
goal = 0;
goto restart;
}
return NULL;
}
/**
* __alloc_bootmem_nopanic - allocate boot memory without panicking
* @size: size of the request in bytes
* @align: alignment of the region
* @goal: preferred starting address of the region
*
* The goal is dropped if it can not be satisfied and the allocation will
* fall back to memory below @goal.
*
* Allocation may happen on any node in the system.
*
* Returns NULL on failure.
*/
void * __init __alloc_bootmem_nopanic(unsigned long size, unsigned long align,
unsigned long goal)
{
unsigned long limit = -1UL;
return ___alloc_bootmem_nopanic(size, align, goal, limit);
}
static void * __init ___alloc_bootmem(unsigned long size, unsigned long align,
unsigned long goal, unsigned long limit)
{
void *mem = ___alloc_bootmem_nopanic(size, align, goal, limit);
if (mem)
return mem;
/*
* Whoops, we cannot satisfy the allocation request.
*/
pr_alert("bootmem alloc of %lu bytes failed!\n", size);
panic("Out of memory");
return NULL;
}
/**
* __alloc_bootmem - allocate boot memory
* @size: size of the request in bytes
* @align: alignment of the region
* @goal: preferred starting address of the region
*
* The goal is dropped if it can not be satisfied and the allocation will
* fall back to memory below @goal.
*
* Allocation may happen on any node in the system.
*
* The function panics if the request can not be satisfied.
*/
void * __init __alloc_bootmem(unsigned long size, unsigned long align,
unsigned long goal)
{
unsigned long limit = -1UL;
return ___alloc_bootmem(size, align, goal, limit);
}
void * __init ___alloc_bootmem_node_nopanic(pg_data_t *pgdat,
unsigned long size,
unsigned long align,
unsigned long goal,
unsigned long limit)
{
void *ptr;
again:
ptr = __alloc_memory_core_early(pgdat->node_id, size, align,
goal, limit);
if (ptr)
return ptr;
ptr = __alloc_memory_core_early(NUMA_NO_NODE, size, align,
goal, limit);
if (ptr)
return ptr;
if (goal) {
goal = 0;
goto again;
}
return NULL;
}
void * __init __alloc_bootmem_node_nopanic(pg_data_t *pgdat, unsigned long size,
unsigned long align, unsigned long goal)
{
if (WARN_ON_ONCE(slab_is_available()))
return kzalloc_node(size, GFP_NOWAIT, pgdat->node_id);
return ___alloc_bootmem_node_nopanic(pgdat, size, align, goal, 0);
}
static void * __init ___alloc_bootmem_node(pg_data_t *pgdat, unsigned long size,
unsigned long align, unsigned long goal,
unsigned long limit)
{
void *ptr;
ptr = ___alloc_bootmem_node_nopanic(pgdat, size, align, goal, limit);
if (ptr)
return ptr;
pr_alert("bootmem alloc of %lu bytes failed!\n", size);
panic("Out of memory");
return NULL;
}
/**
* __alloc_bootmem_node - allocate boot memory from a specific node
* @pgdat: node to allocate from
* @size: size of the request in bytes
* @align: alignment of the region
* @goal: preferred starting address of the region
*
* The goal is dropped if it can not be satisfied and the allocation will
* fall back to memory below @goal.
*
* Allocation may fall back to any node in the system if the specified node
* can not hold the requested memory.
*
* The function panics if the request can not be satisfied.
*/
void * __init __alloc_bootmem_node(pg_data_t *pgdat, unsigned long size,
unsigned long align, unsigned long goal)
{
if (WARN_ON_ONCE(slab_is_available()))
return kzalloc_node(size, GFP_NOWAIT, pgdat->node_id);
return ___alloc_bootmem_node(pgdat, size, align, goal, 0);
}
void * __init __alloc_bootmem_node_high(pg_data_t *pgdat, unsigned long size,
unsigned long align, unsigned long goal)
{
return __alloc_bootmem_node(pgdat, size, align, goal);
}
/**
* __alloc_bootmem_low - allocate low boot memory
* @size: size of the request in bytes
* @align: alignment of the region
* @goal: preferred starting address of the region
*
* The goal is dropped if it can not be satisfied and the allocation will
* fall back to memory below @goal.
*
* Allocation may happen on any node in the system.
*
* The function panics if the request can not be satisfied.
*/
void * __init __alloc_bootmem_low(unsigned long size, unsigned long align,
unsigned long goal)
{
return ___alloc_bootmem(size, align, goal, ARCH_LOW_ADDRESS_LIMIT);
}
void * __init __alloc_bootmem_low_nopanic(unsigned long size,
unsigned long align,
unsigned long goal)
{
return ___alloc_bootmem_nopanic(size, align, goal,
ARCH_LOW_ADDRESS_LIMIT);
}
/**
* __alloc_bootmem_low_node - allocate low boot memory from a specific node
* @pgdat: node to allocate from
* @size: size of the request in bytes
* @align: alignment of the region
* @goal: preferred starting address of the region
*
* The goal is dropped if it can not be satisfied and the allocation will
* fall back to memory below @goal.
*
* Allocation may fall back to any node in the system if the specified node
* can not hold the requested memory.
*
* The function panics if the request can not be satisfied.
*/
void * __init __alloc_bootmem_low_node(pg_data_t *pgdat, unsigned long size,
unsigned long align, unsigned long goal)
{
if (WARN_ON_ONCE(slab_is_available()))
return kzalloc_node(size, GFP_NOWAIT, pgdat->node_id);
return ___alloc_bootmem_node(pgdat, size, align, goal,
ARCH_LOW_ADDRESS_LIMIT);
}