mirror of
https://github.com/rd-stuffs/msm-4.14.git
synced 2025-02-20 11:45:48 +08:00
* 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>
861 lines
21 KiB
C
861 lines
21 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/bug.h>
|
|
#include <linux/io.h>
|
|
#include <linux/bootmem.h>
|
|
|
|
#include "internal.h"
|
|
|
|
#ifndef CONFIG_NEED_MULTIPLE_NODES
|
|
struct pglist_data __refdata contig_page_data = {
|
|
.bdata = &bootmem_node_data[0]
|
|
};
|
|
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;
|
|
|
|
bootmem_data_t bootmem_node_data[MAX_NUMNODES] __initdata;
|
|
|
|
static struct list_head bdata_list __initdata = LIST_HEAD_INIT(bdata_list);
|
|
|
|
static int bootmem_debug;
|
|
|
|
static int __init bootmem_debug_setup(char *buf)
|
|
{
|
|
bootmem_debug = 1;
|
|
return 0;
|
|
}
|
|
early_param("bootmem_debug", bootmem_debug_setup);
|
|
|
|
#define bdebug(fmt, args...) ({ \
|
|
if (unlikely(bootmem_debug)) \
|
|
pr_info("bootmem::%s " fmt, \
|
|
__func__, ## args); \
|
|
})
|
|
|
|
static unsigned long __init bootmap_bytes(unsigned long pages)
|
|
{
|
|
unsigned long bytes = DIV_ROUND_UP(pages, BITS_PER_BYTE);
|
|
|
|
return ALIGN(bytes, sizeof(long));
|
|
}
|
|
|
|
/**
|
|
* bootmem_bootmap_pages - calculate bitmap size in pages
|
|
* @pages: number of pages the bitmap has to represent
|
|
*/
|
|
unsigned long __init bootmem_bootmap_pages(unsigned long pages)
|
|
{
|
|
unsigned long bytes = bootmap_bytes(pages);
|
|
|
|
return PAGE_ALIGN(bytes) >> PAGE_SHIFT;
|
|
}
|
|
|
|
/*
|
|
* link bdata in order
|
|
*/
|
|
static void __init link_bootmem(bootmem_data_t *bdata)
|
|
{
|
|
bootmem_data_t *ent;
|
|
|
|
list_for_each_entry(ent, &bdata_list, list) {
|
|
if (bdata->node_min_pfn < ent->node_min_pfn) {
|
|
list_add_tail(&bdata->list, &ent->list);
|
|
return;
|
|
}
|
|
}
|
|
|
|
list_add_tail(&bdata->list, &bdata_list);
|
|
}
|
|
|
|
/*
|
|
* Called once to set up the allocator itself.
|
|
*/
|
|
static unsigned long __init init_bootmem_core(bootmem_data_t *bdata,
|
|
unsigned long mapstart, unsigned long start, unsigned long end)
|
|
{
|
|
unsigned long mapsize;
|
|
|
|
mminit_validate_memmodel_limits(&start, &end);
|
|
bdata->node_bootmem_map = phys_to_virt(PFN_PHYS(mapstart));
|
|
bdata->node_min_pfn = start;
|
|
bdata->node_low_pfn = end;
|
|
link_bootmem(bdata);
|
|
|
|
/*
|
|
* Initially all pages are reserved - setup_arch() has to
|
|
* register free RAM areas explicitly.
|
|
*/
|
|
mapsize = bootmap_bytes(end - start);
|
|
memset(bdata->node_bootmem_map, 0xff, mapsize);
|
|
|
|
bdebug("nid=%td start=%lx map=%lx end=%lx mapsize=%lx\n",
|
|
bdata - bootmem_node_data, start, mapstart, end, mapsize);
|
|
|
|
return mapsize;
|
|
}
|
|
|
|
/**
|
|
* init_bootmem_node - register a node as boot memory
|
|
* @pgdat: node to register
|
|
* @freepfn: pfn where the bitmap for this node is to be placed
|
|
* @startpfn: first pfn on the node
|
|
* @endpfn: first pfn after the node
|
|
*
|
|
* Returns the number of bytes needed to hold the bitmap for this node.
|
|
*/
|
|
unsigned long __init init_bootmem_node(pg_data_t *pgdat, unsigned long freepfn,
|
|
unsigned long startpfn, unsigned long endpfn)
|
|
{
|
|
return init_bootmem_core(pgdat->bdata, freepfn, startpfn, endpfn);
|
|
}
|
|
|
|
/**
|
|
* init_bootmem - register boot memory
|
|
* @start: pfn where the bitmap is to be placed
|
|
* @pages: number of available physical pages
|
|
*
|
|
* Returns the number of bytes needed to hold the bitmap.
|
|
*/
|
|
unsigned long __init init_bootmem(unsigned long start, unsigned long pages)
|
|
{
|
|
max_low_pfn = pages;
|
|
min_low_pfn = start;
|
|
return init_bootmem_core(NODE_DATA(0)->bdata, start, 0, pages);
|
|
}
|
|
|
|
/*
|
|
* free_bootmem_late - free bootmem pages directly to page allocator
|
|
* @addr: starting physical 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 physaddr, unsigned long size)
|
|
{
|
|
unsigned long cursor, end;
|
|
|
|
kmemleak_free_part_phys(physaddr, size);
|
|
|
|
cursor = PFN_UP(physaddr);
|
|
end = PFN_DOWN(physaddr + size);
|
|
|
|
for (; cursor < end; cursor++) {
|
|
__free_pages_bootmem(pfn_to_page(cursor), cursor, 0);
|
|
totalram_pages++;
|
|
}
|
|
}
|
|
|
|
static unsigned long __init free_all_bootmem_core(bootmem_data_t *bdata)
|
|
{
|
|
struct page *page;
|
|
unsigned long *map, start, end, pages, cur, count = 0;
|
|
|
|
if (!bdata->node_bootmem_map)
|
|
return 0;
|
|
|
|
map = bdata->node_bootmem_map;
|
|
start = bdata->node_min_pfn;
|
|
end = bdata->node_low_pfn;
|
|
|
|
bdebug("nid=%td start=%lx end=%lx\n",
|
|
bdata - bootmem_node_data, start, end);
|
|
|
|
while (start < end) {
|
|
unsigned long idx, vec;
|
|
unsigned shift;
|
|
|
|
idx = start - bdata->node_min_pfn;
|
|
shift = idx & (BITS_PER_LONG - 1);
|
|
/*
|
|
* vec holds at most BITS_PER_LONG map bits,
|
|
* bit 0 corresponds to start.
|
|
*/
|
|
vec = ~map[idx / BITS_PER_LONG];
|
|
|
|
if (shift) {
|
|
vec >>= shift;
|
|
if (end - start >= BITS_PER_LONG)
|
|
vec |= ~map[idx / BITS_PER_LONG + 1] <<
|
|
(BITS_PER_LONG - shift);
|
|
}
|
|
/*
|
|
* If we have a properly aligned and fully unreserved
|
|
* BITS_PER_LONG block of pages in front of us, free
|
|
* it in one go.
|
|
*/
|
|
if (IS_ALIGNED(start, BITS_PER_LONG) && vec == ~0UL) {
|
|
int order = ilog2(BITS_PER_LONG);
|
|
|
|
__free_pages_bootmem(pfn_to_page(start), start, order);
|
|
count += BITS_PER_LONG;
|
|
start += BITS_PER_LONG;
|
|
} else {
|
|
cur = start;
|
|
|
|
start = ALIGN(start + 1, BITS_PER_LONG);
|
|
while (vec && cur != start) {
|
|
if (vec & 1) {
|
|
page = pfn_to_page(cur);
|
|
__free_pages_bootmem(page, cur, 0);
|
|
count++;
|
|
}
|
|
vec >>= 1;
|
|
++cur;
|
|
}
|
|
}
|
|
}
|
|
|
|
cur = bdata->node_min_pfn;
|
|
page = virt_to_page(bdata->node_bootmem_map);
|
|
pages = bdata->node_low_pfn - bdata->node_min_pfn;
|
|
pages = bootmem_bootmap_pages(pages);
|
|
count += pages;
|
|
while (pages--)
|
|
__free_pages_bootmem(page++, cur++, 0);
|
|
bdata->node_bootmem_map = NULL;
|
|
|
|
bdebug("nid=%td released=%lx\n", bdata - bootmem_node_data, count);
|
|
|
|
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 total_pages = 0;
|
|
bootmem_data_t *bdata;
|
|
|
|
reset_all_zones_managed_pages();
|
|
|
|
list_for_each_entry(bdata, &bdata_list, list)
|
|
total_pages += free_all_bootmem_core(bdata);
|
|
|
|
totalram_pages += total_pages;
|
|
|
|
return total_pages;
|
|
}
|
|
|
|
static void __init __free(bootmem_data_t *bdata,
|
|
unsigned long sidx, unsigned long eidx)
|
|
{
|
|
unsigned long idx;
|
|
|
|
bdebug("nid=%td start=%lx end=%lx\n", bdata - bootmem_node_data,
|
|
sidx + bdata->node_min_pfn,
|
|
eidx + bdata->node_min_pfn);
|
|
|
|
if (WARN_ON(bdata->node_bootmem_map == NULL))
|
|
return;
|
|
|
|
if (bdata->hint_idx > sidx)
|
|
bdata->hint_idx = sidx;
|
|
|
|
for (idx = sidx; idx < eidx; idx++)
|
|
if (!test_and_clear_bit(idx, bdata->node_bootmem_map))
|
|
BUG();
|
|
}
|
|
|
|
static int __init __reserve(bootmem_data_t *bdata, unsigned long sidx,
|
|
unsigned long eidx, int flags)
|
|
{
|
|
unsigned long idx;
|
|
int exclusive = flags & BOOTMEM_EXCLUSIVE;
|
|
|
|
bdebug("nid=%td start=%lx end=%lx flags=%x\n",
|
|
bdata - bootmem_node_data,
|
|
sidx + bdata->node_min_pfn,
|
|
eidx + bdata->node_min_pfn,
|
|
flags);
|
|
|
|
if (WARN_ON(bdata->node_bootmem_map == NULL))
|
|
return 0;
|
|
|
|
for (idx = sidx; idx < eidx; idx++)
|
|
if (test_and_set_bit(idx, bdata->node_bootmem_map)) {
|
|
if (exclusive) {
|
|
__free(bdata, sidx, idx);
|
|
return -EBUSY;
|
|
}
|
|
bdebug("silent double reserve of PFN %lx\n",
|
|
idx + bdata->node_min_pfn);
|
|
}
|
|
return 0;
|
|
}
|
|
|
|
static int __init mark_bootmem_node(bootmem_data_t *bdata,
|
|
unsigned long start, unsigned long end,
|
|
int reserve, int flags)
|
|
{
|
|
unsigned long sidx, eidx;
|
|
|
|
bdebug("nid=%td start=%lx end=%lx reserve=%d flags=%x\n",
|
|
bdata - bootmem_node_data, start, end, reserve, flags);
|
|
|
|
BUG_ON(start < bdata->node_min_pfn);
|
|
BUG_ON(end > bdata->node_low_pfn);
|
|
|
|
sidx = start - bdata->node_min_pfn;
|
|
eidx = end - bdata->node_min_pfn;
|
|
|
|
if (reserve)
|
|
return __reserve(bdata, sidx, eidx, flags);
|
|
else
|
|
__free(bdata, sidx, eidx);
|
|
return 0;
|
|
}
|
|
|
|
static int __init mark_bootmem(unsigned long start, unsigned long end,
|
|
int reserve, int flags)
|
|
{
|
|
unsigned long pos;
|
|
bootmem_data_t *bdata;
|
|
|
|
pos = start;
|
|
list_for_each_entry(bdata, &bdata_list, list) {
|
|
int err;
|
|
unsigned long max;
|
|
|
|
if (pos < bdata->node_min_pfn ||
|
|
pos >= bdata->node_low_pfn) {
|
|
BUG_ON(pos != start);
|
|
continue;
|
|
}
|
|
|
|
max = min(bdata->node_low_pfn, end);
|
|
|
|
err = mark_bootmem_node(bdata, pos, max, reserve, flags);
|
|
if (reserve && err) {
|
|
mark_bootmem(start, pos, 0, 0);
|
|
return err;
|
|
}
|
|
|
|
if (max == end)
|
|
return 0;
|
|
pos = bdata->node_low_pfn;
|
|
}
|
|
BUG();
|
|
}
|
|
|
|
/**
|
|
* 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)
|
|
{
|
|
unsigned long start, end;
|
|
|
|
kmemleak_free_part_phys(physaddr, size);
|
|
|
|
start = PFN_UP(physaddr);
|
|
end = PFN_DOWN(physaddr + size);
|
|
|
|
mark_bootmem_node(pgdat->bdata, start, end, 0, 0);
|
|
}
|
|
|
|
/**
|
|
* free_bootmem - mark a page range as usable
|
|
* @addr: starting physical 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 physaddr, unsigned long size)
|
|
{
|
|
unsigned long start, end;
|
|
|
|
kmemleak_free_part_phys(physaddr, size);
|
|
|
|
start = PFN_UP(physaddr);
|
|
end = PFN_DOWN(physaddr + size);
|
|
|
|
mark_bootmem(start, end, 0, 0);
|
|
}
|
|
|
|
/**
|
|
* reserve_bootmem_node - mark a page range as reserved
|
|
* @pgdat: node the range resides on
|
|
* @physaddr: starting address of the range
|
|
* @size: size of the range in bytes
|
|
* @flags: reservation flags (see linux/bootmem.h)
|
|
*
|
|
* Partial pages will be reserved.
|
|
*
|
|
* The range must reside completely on the specified node.
|
|
*/
|
|
int __init reserve_bootmem_node(pg_data_t *pgdat, unsigned long physaddr,
|
|
unsigned long size, int flags)
|
|
{
|
|
unsigned long start, end;
|
|
|
|
start = PFN_DOWN(physaddr);
|
|
end = PFN_UP(physaddr + size);
|
|
|
|
return mark_bootmem_node(pgdat->bdata, start, end, 1, flags);
|
|
}
|
|
|
|
/**
|
|
* reserve_bootmem - mark a page range as reserved
|
|
* @addr: starting address of the range
|
|
* @size: size of the range in bytes
|
|
* @flags: reservation flags (see linux/bootmem.h)
|
|
*
|
|
* Partial pages will be reserved.
|
|
*
|
|
* The range must be contiguous but may span node boundaries.
|
|
*/
|
|
int __init reserve_bootmem(unsigned long addr, unsigned long size,
|
|
int flags)
|
|
{
|
|
unsigned long start, end;
|
|
|
|
start = PFN_DOWN(addr);
|
|
end = PFN_UP(addr + size);
|
|
|
|
return mark_bootmem(start, end, 1, flags);
|
|
}
|
|
|
|
static unsigned long __init align_idx(struct bootmem_data *bdata,
|
|
unsigned long idx, unsigned long step)
|
|
{
|
|
unsigned long base = bdata->node_min_pfn;
|
|
|
|
/*
|
|
* Align the index with respect to the node start so that the
|
|
* combination of both satisfies the requested alignment.
|
|
*/
|
|
|
|
return ALIGN(base + idx, step) - base;
|
|
}
|
|
|
|
static unsigned long __init align_off(struct bootmem_data *bdata,
|
|
unsigned long off, unsigned long align)
|
|
{
|
|
unsigned long base = PFN_PHYS(bdata->node_min_pfn);
|
|
|
|
/* Same as align_idx for byte offsets */
|
|
|
|
return ALIGN(base + off, align) - base;
|
|
}
|
|
|
|
static void * __init alloc_bootmem_bdata(struct bootmem_data *bdata,
|
|
unsigned long size, unsigned long align,
|
|
unsigned long goal, unsigned long limit)
|
|
{
|
|
unsigned long fallback = 0;
|
|
unsigned long min, max, start, sidx, midx, step;
|
|
|
|
bdebug("nid=%td size=%lx [%lu pages] align=%lx goal=%lx limit=%lx\n",
|
|
bdata - bootmem_node_data, size, PAGE_ALIGN(size) >> PAGE_SHIFT,
|
|
align, goal, limit);
|
|
|
|
BUG_ON(!size);
|
|
BUG_ON(align & (align - 1));
|
|
BUG_ON(limit && goal + size > limit);
|
|
|
|
if (!bdata->node_bootmem_map)
|
|
return NULL;
|
|
|
|
min = bdata->node_min_pfn;
|
|
max = bdata->node_low_pfn;
|
|
|
|
goal >>= PAGE_SHIFT;
|
|
limit >>= PAGE_SHIFT;
|
|
|
|
if (limit && max > limit)
|
|
max = limit;
|
|
if (max <= min)
|
|
return NULL;
|
|
|
|
step = max(align >> PAGE_SHIFT, 1UL);
|
|
|
|
if (goal && min < goal && goal < max)
|
|
start = ALIGN(goal, step);
|
|
else
|
|
start = ALIGN(min, step);
|
|
|
|
sidx = start - bdata->node_min_pfn;
|
|
midx = max - bdata->node_min_pfn;
|
|
|
|
if (bdata->hint_idx > sidx) {
|
|
/*
|
|
* Handle the valid case of sidx being zero and still
|
|
* catch the fallback below.
|
|
*/
|
|
fallback = sidx + 1;
|
|
sidx = align_idx(bdata, bdata->hint_idx, step);
|
|
}
|
|
|
|
while (1) {
|
|
int merge;
|
|
void *region;
|
|
unsigned long eidx, i, start_off, end_off;
|
|
find_block:
|
|
sidx = find_next_zero_bit(bdata->node_bootmem_map, midx, sidx);
|
|
sidx = align_idx(bdata, sidx, step);
|
|
eidx = sidx + PFN_UP(size);
|
|
|
|
if (sidx >= midx || eidx > midx)
|
|
break;
|
|
|
|
for (i = sidx; i < eidx; i++)
|
|
if (test_bit(i, bdata->node_bootmem_map)) {
|
|
sidx = align_idx(bdata, i, step);
|
|
if (sidx == i)
|
|
sidx += step;
|
|
goto find_block;
|
|
}
|
|
|
|
if (bdata->last_end_off & (PAGE_SIZE - 1) &&
|
|
PFN_DOWN(bdata->last_end_off) + 1 == sidx)
|
|
start_off = align_off(bdata, bdata->last_end_off, align);
|
|
else
|
|
start_off = PFN_PHYS(sidx);
|
|
|
|
merge = PFN_DOWN(start_off) < sidx;
|
|
end_off = start_off + size;
|
|
|
|
bdata->last_end_off = end_off;
|
|
bdata->hint_idx = PFN_UP(end_off);
|
|
|
|
/*
|
|
* Reserve the area now:
|
|
*/
|
|
if (__reserve(bdata, PFN_DOWN(start_off) + merge,
|
|
PFN_UP(end_off), BOOTMEM_EXCLUSIVE))
|
|
BUG();
|
|
|
|
region = phys_to_virt(PFN_PHYS(bdata->node_min_pfn) +
|
|
start_off);
|
|
memset(region, 0, size);
|
|
/*
|
|
* The min_count is set to 0 so that bootmem allocated blocks
|
|
* are never reported as leaks.
|
|
*/
|
|
kmemleak_alloc(region, size, 0, 0);
|
|
return region;
|
|
}
|
|
|
|
if (fallback) {
|
|
sidx = align_idx(bdata, fallback - 1, step);
|
|
fallback = 0;
|
|
goto find_block;
|
|
}
|
|
|
|
return NULL;
|
|
}
|
|
|
|
static void * __init alloc_bootmem_core(unsigned long size,
|
|
unsigned long align,
|
|
unsigned long goal,
|
|
unsigned long limit)
|
|
{
|
|
bootmem_data_t *bdata;
|
|
void *region;
|
|
|
|
if (WARN_ON_ONCE(slab_is_available()))
|
|
return kzalloc(size, GFP_NOWAIT);
|
|
|
|
list_for_each_entry(bdata, &bdata_list, list) {
|
|
if (goal && bdata->node_low_pfn <= PFN_DOWN(goal))
|
|
continue;
|
|
if (limit && bdata->node_min_pfn >= PFN_DOWN(limit))
|
|
break;
|
|
|
|
region = alloc_bootmem_bdata(bdata, size, align, goal, limit);
|
|
if (region)
|
|
return region;
|
|
}
|
|
|
|
return NULL;
|
|
}
|
|
|
|
static void * __init ___alloc_bootmem_nopanic(unsigned long size,
|
|
unsigned long align,
|
|
unsigned long goal,
|
|
unsigned long limit)
|
|
{
|
|
void *ptr;
|
|
|
|
restart:
|
|
ptr = alloc_bootmem_core(size, align, goal, limit);
|
|
if (ptr)
|
|
return ptr;
|
|
if (goal) {
|
|
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 = 0;
|
|
|
|
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 = 0;
|
|
|
|
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;
|
|
|
|
if (WARN_ON_ONCE(slab_is_available()))
|
|
return kzalloc_node(size, GFP_NOWAIT, pgdat->node_id);
|
|
again:
|
|
|
|
/* do not panic in alloc_bootmem_bdata() */
|
|
if (limit && goal + size > limit)
|
|
limit = 0;
|
|
|
|
ptr = alloc_bootmem_bdata(pgdat->bdata, size, align, goal, limit);
|
|
if (ptr)
|
|
return ptr;
|
|
|
|
ptr = alloc_bootmem_core(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)
|
|
{
|
|
return ___alloc_bootmem_node_nopanic(pgdat, size, align, goal, 0);
|
|
}
|
|
|
|
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, 0);
|
|
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)
|
|
{
|
|
#ifdef MAX_DMA32_PFN
|
|
unsigned long end_pfn;
|
|
|
|
if (WARN_ON_ONCE(slab_is_available()))
|
|
return kzalloc_node(size, GFP_NOWAIT, pgdat->node_id);
|
|
|
|
/* update goal according ...MAX_DMA32_PFN */
|
|
end_pfn = pgdat_end_pfn(pgdat);
|
|
|
|
if (end_pfn > MAX_DMA32_PFN + (128 >> (20 - PAGE_SHIFT)) &&
|
|
(goal >> PAGE_SHIFT) < MAX_DMA32_PFN) {
|
|
void *ptr;
|
|
unsigned long new_goal;
|
|
|
|
new_goal = MAX_DMA32_PFN << PAGE_SHIFT;
|
|
ptr = alloc_bootmem_bdata(pgdat->bdata, size, align,
|
|
new_goal, 0);
|
|
if (ptr)
|
|
return ptr;
|
|
}
|
|
#endif
|
|
|
|
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);
|
|
}
|