summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
-rw-r--r--.mailmap4
-rw-r--r--Documentation/devicetree/bindings/input/mediatek,mt6779-keypad.yaml2
-rw-r--r--MAINTAINERS68
-rw-r--r--Makefile2
-rw-r--r--arch/arm64/include/asm/el2_setup.h2
-rw-r--r--arch/arm64/include/asm/kvm_arm.h3
-rw-r--r--arch/arm64/include/asm/vdso/gettimeofday.h13
-rw-r--r--arch/arm64/kvm/hyp/include/hyp/switch.h13
-rw-r--r--arch/arm64/kvm/hyp/nvhe/mem_protect.c2
-rw-r--r--arch/arm64/kvm/hyp/vgic-v3-sr.c36
-rw-r--r--arch/arm64/kvm/mmu.c13
-rw-r--r--arch/arm64/kvm/sys_regs.c6
-rw-r--r--arch/mips/include/asm/idle.h5
-rw-r--r--arch/mips/include/asm/ptrace.h3
-rw-r--r--arch/mips/kernel/genex.S71
-rw-r--r--arch/mips/kernel/idle.c7
-rw-r--r--arch/mips/kernel/smp-cps.c4
-rw-r--r--arch/mips/kernel/traps.c10
-rw-r--r--arch/riscv/kvm/vcpu.c2
-rw-r--r--arch/x86/include/asm/microcode.h2
-rw-r--r--arch/x86/kernel/cpu/microcode/amd.c6
-rw-r--r--arch/x86/kernel/cpu/microcode/core.c58
-rw-r--r--arch/x86/kernel/cpu/microcode/intel.c2
-rw-r--r--arch/x86/kernel/cpu/microcode/internal.h1
-rw-r--r--arch/x86/kernel/head32.c4
-rw-r--r--arch/x86/kernel/vmlinux.lds.S10
-rw-r--r--arch/x86/kvm/mmu.h3
-rw-r--r--arch/x86/kvm/mmu/mmu.c70
-rw-r--r--arch/x86/kvm/smm.c1
-rw-r--r--arch/x86/kvm/svm/sev.c32
-rw-r--r--arch/x86/kvm/svm/svm.c75
-rw-r--r--arch/x86/kvm/svm/svm.h2
-rw-r--r--arch/x86/kvm/x86.c4
-rw-r--r--drivers/clocksource/i8253.c4
-rw-r--r--drivers/input/joystick/magellan.c2
-rw-r--r--drivers/input/joystick/xpad.c49
-rw-r--r--drivers/input/keyboard/mtk-pmic-keys.c4
-rw-r--r--drivers/input/misc/hisi_powerkey.c2
-rw-r--r--drivers/input/misc/sparcspkr.c22
-rw-r--r--drivers/input/mouse/synaptics.c5
-rw-r--r--drivers/input/touchscreen/cyttsp5.c7
-rw-r--r--drivers/input/touchscreen/stmpe-ts.c7
-rw-r--r--fs/nilfs2/the_nilfs.c3
-rw-r--r--fs/ocfs2/alloc.c1
-rw-r--r--fs/ocfs2/journal.c80
-rw-r--r--fs/ocfs2/journal.h1
-rw-r--r--fs/ocfs2/ocfs2.h17
-rw-r--r--fs/ocfs2/quota_local.c9
-rw-r--r--fs/ocfs2/suballoc.c38
-rw-r--r--fs/ocfs2/suballoc.h1
-rw-r--r--fs/ocfs2/super.c3
-rw-r--r--fs/userfaultfd.c28
-rw-r--r--include/linux/timekeeper_internal.h8
-rw-r--r--include/linux/vmalloc.h1
-rw-r--r--kernel/time/timekeeping.c50
-rw-r--r--kernel/time/vsyscall.c4
-rw-r--r--mm/huge_memory.c11
-rw-r--r--mm/hugetlb.c6
-rw-r--r--mm/internal.h27
-rw-r--r--mm/memblock.c9
-rw-r--r--mm/mm_init.c2
-rw-r--r--mm/swapfile.c23
-rw-r--r--mm/vmalloc.c31
-rw-r--r--tools/testing/selftests/kvm/arm64/set_id_regs.c8
-rw-r--r--tools/testing/selftests/mm/compaction_test.c19
-rw-r--r--tools/testing/selftests/mm/guard-regions.c16
-rw-r--r--tools/testing/selftests/mm/pkey-powerpc.h14
-rw-r--r--tools/testing/selftests/mm/pkey_util.c1
68 files changed, 747 insertions, 302 deletions
diff --git a/.mailmap b/.mailmap
index 9afde79e1936..1c70e51c789d 100644
--- a/.mailmap
+++ b/.mailmap
@@ -447,6 +447,8 @@ Luca Ceresoli <luca.ceresoli@bootlin.com> <luca@lucaceresoli.net>
Luca Weiss <luca@lucaweiss.eu> <luca@z3ntu.xyz>
Lukasz Luba <lukasz.luba@arm.com> <l.luba@partner.samsung.com>
Luo Jie <quic_luoj@quicinc.com> <luoj@codeaurora.org>
+Lance Yang <lance.yang@linux.dev> <ioworker0@gmail.com>
+Lance Yang <lance.yang@linux.dev> <mingzhe.yang@ly.com>
Maciej W. Rozycki <macro@mips.com> <macro@imgtec.com>
Maciej W. Rozycki <macro@orcam.me.uk> <macro@linux-mips.org>
Maharaja Kennadyrajan <quic_mkenna@quicinc.com> <mkenna@codeaurora.org>
@@ -483,6 +485,7 @@ Matthias Fuchs <socketcan@esd.eu> <matthias.fuchs@esd.eu>
Matthieu Baerts <matttbe@kernel.org> <matthieu.baerts@tessares.net>
Matthieu CASTET <castet.matthieu@free.fr>
Matti Vaittinen <mazziesaccount@gmail.com> <matti.vaittinen@fi.rohmeurope.com>
+Mattijs Korpershoek <mkorpershoek@kernel.org> <mkorpershoek@baylibre.com>
Matt Ranostay <matt@ranostay.sg> <matt.ranostay@konsulko.com>
Matt Ranostay <matt@ranostay.sg> <matt@ranostay.consulting>
Matt Ranostay <matt@ranostay.sg> Matthew Ranostay <mranostay@embeddedalley.com>
@@ -749,6 +752,7 @@ Tvrtko Ursulin <tursulin@ursulin.net> <tvrtko@ursulin.net>
Tycho Andersen <tycho@tycho.pizza> <tycho@tycho.ws>
Tzung-Bi Shih <tzungbi@kernel.org> <tzungbi@google.com>
Uwe Kleine-König <ukleinek@informatik.uni-freiburg.de>
+Uwe Kleine-König <u.kleine-koenig@baylibre.com> <ukleinek@baylibre.com>
Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Uwe Kleine-König <ukleinek@strlen.de>
Uwe Kleine-König <ukl@pengutronix.de>
diff --git a/Documentation/devicetree/bindings/input/mediatek,mt6779-keypad.yaml b/Documentation/devicetree/bindings/input/mediatek,mt6779-keypad.yaml
index 517a4ac1bea3..e365413732e7 100644
--- a/Documentation/devicetree/bindings/input/mediatek,mt6779-keypad.yaml
+++ b/Documentation/devicetree/bindings/input/mediatek,mt6779-keypad.yaml
@@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
title: Mediatek's Keypad Controller
maintainers:
- - Mattijs Korpershoek <mkorpershoek@baylibre.com>
+ - Mattijs Korpershoek <mkorpershoek@kernel.org>
allOf:
- $ref: /schemas/input/matrix-keymap.yaml#
diff --git a/MAINTAINERS b/MAINTAINERS
index afceb58f76cb..f21f1dabb5fe 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -15072,7 +15072,7 @@ F: Documentation/devicetree/bindings/media/mediatek-jpeg-*.yaml
F: drivers/media/platform/mediatek/jpeg/
MEDIATEK KEYPAD DRIVER
-M: Mattijs Korpershoek <mkorpershoek@baylibre.com>
+M: Mattijs Korpershoek <mkorpershoek@kernel.org>
S: Supported
F: Documentation/devicetree/bindings/input/mediatek,mt6779-keypad.yaml
F: drivers/input/keyboard/mt6779-keypad.c
@@ -15495,24 +15495,45 @@ F: Documentation/mm/
F: include/linux/gfp.h
F: include/linux/gfp_types.h
F: include/linux/memfd.h
-F: include/linux/memory.h
F: include/linux/memory_hotplug.h
F: include/linux/memory-tiers.h
F: include/linux/mempolicy.h
F: include/linux/mempool.h
F: include/linux/memremap.h
-F: include/linux/mm.h
-F: include/linux/mm_*.h
F: include/linux/mmzone.h
F: include/linux/mmu_notifier.h
F: include/linux/pagewalk.h
-F: include/linux/rmap.h
F: include/trace/events/ksm.h
F: mm/
F: tools/mm/
F: tools/testing/selftests/mm/
N: include/linux/page[-_]*
+MEMORY MANAGEMENT - CORE
+M: Andrew Morton <akpm@linux-foundation.org>
+M: David Hildenbrand <david@redhat.com>
+R: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
+R: Liam R. Howlett <Liam.Howlett@oracle.com>
+R: Vlastimil Babka <vbabka@suse.cz>
+R: Mike Rapoport <rppt@kernel.org>
+R: Suren Baghdasaryan <surenb@google.com>
+R: Michal Hocko <mhocko@suse.com>
+L: linux-mm@kvack.org
+S: Maintained
+W: http://www.linux-mm.org
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
+F: include/linux/memory.h
+F: include/linux/mm.h
+F: include/linux/mm_*.h
+F: include/linux/mmdebug.h
+F: include/linux/pagewalk.h
+F: mm/Kconfig
+F: mm/debug.c
+F: mm/init-mm.c
+F: mm/memory.c
+F: mm/pagewalk.c
+F: mm/util.c
+
MEMORY MANAGEMENT - EXECMEM
M: Andrew Morton <akpm@linux-foundation.org>
M: Mike Rapoport <rppt@kernel.org>
@@ -15546,6 +15567,19 @@ F: mm/page_alloc.c
F: include/linux/gfp.h
F: include/linux/compaction.h
+MEMORY MANAGEMENT - RMAP (REVERSE MAPPING)
+M: Andrew Morton <akpm@linux-foundation.org>
+M: David Hildenbrand <david@redhat.com>
+M: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
+R: Rik van Riel <riel@surriel.com>
+R: Liam R. Howlett <Liam.Howlett@oracle.com>
+R: Vlastimil Babka <vbabka@suse.cz>
+R: Harry Yoo <harry.yoo@oracle.com>
+L: linux-mm@kvack.org
+S: Maintained
+F: include/linux/rmap.h
+F: mm/rmap.c
+
MEMORY MANAGEMENT - SECRETMEM
M: Andrew Morton <akpm@linux-foundation.org>
M: Mike Rapoport <rppt@kernel.org>
@@ -15554,6 +15588,30 @@ S: Maintained
F: include/linux/secretmem.h
F: mm/secretmem.c
+MEMORY MANAGEMENT - THP (TRANSPARENT HUGE PAGE)
+M: Andrew Morton <akpm@linux-foundation.org>
+M: David Hildenbrand <david@redhat.com>
+R: Zi Yan <ziy@nvidia.com>
+R: Baolin Wang <baolin.wang@linux.alibaba.com>
+R: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
+R: Liam R. Howlett <Liam.Howlett@oracle.com>
+R: Nico Pache <npache@redhat.com>
+R: Ryan Roberts <ryan.roberts@arm.com>
+R: Dev Jain <dev.jain@arm.com>
+L: linux-mm@kvack.org
+S: Maintained
+W: http://www.linux-mm.org
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
+F: Documentation/admin-guide/mm/transhuge.rst
+F: include/linux/huge_mm.h
+F: include/linux/khugepaged.h
+F: include/trace/events/huge_memory.h
+F: mm/huge_memory.c
+F: mm/khugepaged.c
+F: tools/testing/selftests/mm/khugepaged.c
+F: tools/testing/selftests/mm/split_huge_page_test.c
+F: tools/testing/selftests/mm/transhuge-stress.c
+
MEMORY MANAGEMENT - USERFAULTFD
M: Andrew Morton <akpm@linux-foundation.org>
R: Peter Xu <peterx@redhat.com>
diff --git a/Makefile b/Makefile
index b29cc321ffd9..64c514f4bc19 100644
--- a/Makefile
+++ b/Makefile
@@ -2,7 +2,7 @@
VERSION = 6
PATCHLEVEL = 15
SUBLEVEL = 0
-EXTRAVERSION = -rc5
+EXTRAVERSION = -rc6
NAME = Baby Opossum Posse
# *DOCUMENTATION*
diff --git a/arch/arm64/include/asm/el2_setup.h b/arch/arm64/include/asm/el2_setup.h
index ebceaae3c749..d40e427ddad9 100644
--- a/arch/arm64/include/asm/el2_setup.h
+++ b/arch/arm64/include/asm/el2_setup.h
@@ -52,7 +52,7 @@
mrs x0, id_aa64mmfr1_el1
ubfx x0, x0, #ID_AA64MMFR1_EL1_HCX_SHIFT, #4
cbz x0, .Lskip_hcrx_\@
- mov_q x0, HCRX_HOST_FLAGS
+ mov_q x0, (HCRX_EL2_MSCEn | HCRX_EL2_TCR2En | HCRX_EL2_EnFPM)
/* Enable GCS if supported */
mrs_s x1, SYS_ID_AA64PFR1_EL1
diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index 974d72b5905b..e9c8a581e16f 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -100,9 +100,8 @@
HCR_FMO | HCR_IMO | HCR_PTW | HCR_TID3 | HCR_TID1)
#define HCR_HOST_NVHE_FLAGS (HCR_RW | HCR_API | HCR_APK | HCR_ATA)
#define HCR_HOST_NVHE_PROTECTED_FLAGS (HCR_HOST_NVHE_FLAGS | HCR_TSC)
-#define HCR_HOST_VHE_FLAGS (HCR_RW | HCR_TGE | HCR_E2H)
+#define HCR_HOST_VHE_FLAGS (HCR_RW | HCR_TGE | HCR_E2H | HCR_AMO | HCR_IMO | HCR_FMO)
-#define HCRX_HOST_FLAGS (HCRX_EL2_MSCEn | HCRX_EL2_TCR2En | HCRX_EL2_EnFPM)
#define MPAMHCR_HOST_FLAGS 0
/* TCR_EL2 Registers bits */
diff --git a/arch/arm64/include/asm/vdso/gettimeofday.h b/arch/arm64/include/asm/vdso/gettimeofday.h
index 92a2b59a9f3d..3322c7047d84 100644
--- a/arch/arm64/include/asm/vdso/gettimeofday.h
+++ b/arch/arm64/include/asm/vdso/gettimeofday.h
@@ -99,6 +99,19 @@ static __always_inline u64 __arch_get_hw_counter(s32 clock_mode,
return res;
}
+#if IS_ENABLED(CONFIG_CC_IS_GCC) && IS_ENABLED(CONFIG_PAGE_SIZE_64KB)
+static __always_inline const struct vdso_time_data *__arch_get_vdso_u_time_data(void)
+{
+ const struct vdso_time_data *ret = &vdso_u_time_data;
+
+ /* Work around invalid absolute relocations */
+ OPTIMIZER_HIDE_VAR(ret);
+
+ return ret;
+}
+#define __arch_get_vdso_u_time_data __arch_get_vdso_u_time_data
+#endif /* IS_ENABLED(CONFIG_CC_IS_GCC) && IS_ENABLED(CONFIG_PAGE_SIZE_64KB) */
+
#endif /* !__ASSEMBLY__ */
#endif /* __ASM_VDSO_GETTIMEOFDAY_H */
diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h
index b741ea6aefa5..96f625dc7256 100644
--- a/arch/arm64/kvm/hyp/include/hyp/switch.h
+++ b/arch/arm64/kvm/hyp/include/hyp/switch.h
@@ -235,6 +235,8 @@ static inline void __deactivate_traps_mpam(void)
static inline void __activate_traps_common(struct kvm_vcpu *vcpu)
{
+ struct kvm_cpu_context *hctxt = host_data_ptr(host_ctxt);
+
/* Trap on AArch32 cp15 c15 (impdef sysregs) accesses (EL1 or EL0) */
write_sysreg(1 << 15, hstr_el2);
@@ -245,11 +247,8 @@ static inline void __activate_traps_common(struct kvm_vcpu *vcpu)
* EL1 instead of being trapped to EL2.
*/
if (system_supports_pmuv3()) {
- struct kvm_cpu_context *hctxt;
-
write_sysreg(0, pmselr_el0);
- hctxt = host_data_ptr(host_ctxt);
ctxt_sys_reg(hctxt, PMUSERENR_EL0) = read_sysreg(pmuserenr_el0);
write_sysreg(ARMV8_PMU_USERENR_MASK, pmuserenr_el0);
vcpu_set_flag(vcpu, PMUSERENR_ON_CPU);
@@ -269,6 +268,7 @@ static inline void __activate_traps_common(struct kvm_vcpu *vcpu)
hcrx &= ~clr;
}
+ ctxt_sys_reg(hctxt, HCRX_EL2) = read_sysreg_s(SYS_HCRX_EL2);
write_sysreg_s(hcrx, SYS_HCRX_EL2);
}
@@ -278,19 +278,18 @@ static inline void __activate_traps_common(struct kvm_vcpu *vcpu)
static inline void __deactivate_traps_common(struct kvm_vcpu *vcpu)
{
+ struct kvm_cpu_context *hctxt = host_data_ptr(host_ctxt);
+
write_sysreg(*host_data_ptr(host_debug_state.mdcr_el2), mdcr_el2);
write_sysreg(0, hstr_el2);
if (system_supports_pmuv3()) {
- struct kvm_cpu_context *hctxt;
-
- hctxt = host_data_ptr(host_ctxt);
write_sysreg(ctxt_sys_reg(hctxt, PMUSERENR_EL0), pmuserenr_el0);
vcpu_clear_flag(vcpu, PMUSERENR_ON_CPU);
}
if (cpus_have_final_cap(ARM64_HAS_HCX))
- write_sysreg_s(HCRX_HOST_FLAGS, SYS_HCRX_EL2);
+ write_sysreg_s(ctxt_sys_reg(hctxt, HCRX_EL2), SYS_HCRX_EL2);
__deactivate_traps_hfgxtr(vcpu);
__deactivate_traps_mpam();
diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
index 2a5284f749b4..e80f3ebd3e2a 100644
--- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c
+++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
@@ -503,7 +503,7 @@ int host_stage2_set_owner_locked(phys_addr_t addr, u64 size, u8 owner_id)
{
int ret;
- if (!addr_is_memory(addr))
+ if (!range_is_memory(addr, addr + size))
return -EPERM;
ret = host_stage2_try(kvm_pgtable_stage2_set_owner, &host_mmu.pgt,
diff --git a/arch/arm64/kvm/hyp/vgic-v3-sr.c b/arch/arm64/kvm/hyp/vgic-v3-sr.c
index ed363aa3027e..50aa8dbcae75 100644
--- a/arch/arm64/kvm/hyp/vgic-v3-sr.c
+++ b/arch/arm64/kvm/hyp/vgic-v3-sr.c
@@ -429,23 +429,27 @@ u64 __vgic_v3_get_gic_config(void)
/*
* To check whether we have a MMIO-based (GICv2 compatible)
* CPU interface, we need to disable the system register
- * view. To do that safely, we have to prevent any interrupt
- * from firing (which would be deadly).
+ * view.
*
- * Note that this only makes sense on VHE, as interrupts are
- * already masked for nVHE as part of the exception entry to
- * EL2.
- */
- if (has_vhe())
- flags = local_daif_save();
-
- /*
* Table 11-2 "Permitted ICC_SRE_ELx.SRE settings" indicates
* that to be able to set ICC_SRE_EL1.SRE to 0, all the
* interrupt overrides must be set. You've got to love this.
+ *
+ * As we always run VHE with HCR_xMO set, no extra xMO
+ * manipulation is required in that case.
+ *
+ * To safely disable SRE, we have to prevent any interrupt
+ * from firing (which would be deadly). This only makes sense
+ * on VHE, as interrupts are already masked for nVHE as part
+ * of the exception entry to EL2.
*/
- sysreg_clear_set(hcr_el2, 0, HCR_AMO | HCR_FMO | HCR_IMO);
- isb();
+ if (has_vhe()) {
+ flags = local_daif_save();
+ } else {
+ sysreg_clear_set(hcr_el2, 0, HCR_AMO | HCR_FMO | HCR_IMO);
+ isb();
+ }
+
write_gicreg(0, ICC_SRE_EL1);
isb();
@@ -453,11 +457,13 @@ u64 __vgic_v3_get_gic_config(void)
write_gicreg(sre, ICC_SRE_EL1);
isb();
- sysreg_clear_set(hcr_el2, HCR_AMO | HCR_FMO | HCR_IMO, 0);
- isb();
- if (has_vhe())
+ if (has_vhe()) {
local_daif_restore(flags);
+ } else {
+ sysreg_clear_set(hcr_el2, HCR_AMO | HCR_FMO | HCR_IMO, 0);
+ isb();
+ }
val = (val & ICC_SRE_EL1_SRE) ? 0 : (1ULL << 63);
val |= read_gicreg(ICH_VTR_EL2);
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 754f2fe0cc67..eeda92330ade 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -1501,6 +1501,11 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
return -EFAULT;
}
+ if (!is_protected_kvm_enabled())
+ memcache = &vcpu->arch.mmu_page_cache;
+ else
+ memcache = &vcpu->arch.pkvm_memcache;
+
/*
* Permission faults just need to update the existing leaf entry,
* and so normally don't require allocations from the memcache. The
@@ -1510,13 +1515,11 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
if (!fault_is_perm || (logging_active && write_fault)) {
int min_pages = kvm_mmu_cache_min_pages(vcpu->arch.hw_mmu);
- if (!is_protected_kvm_enabled()) {
- memcache = &vcpu->arch.mmu_page_cache;
+ if (!is_protected_kvm_enabled())
ret = kvm_mmu_topup_memory_cache(memcache, min_pages);
- } else {
- memcache = &vcpu->arch.pkvm_memcache;
+ else
ret = topup_hyp_memcache(memcache, min_pages);
- }
+
if (ret)
return ret;
}
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 005ad28f7306..5dde9285afc8 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -1945,6 +1945,12 @@ static int set_id_aa64pfr0_el1(struct kvm_vcpu *vcpu,
if ((hw_val & mpam_mask) == (user_val & mpam_mask))
user_val &= ~ID_AA64PFR0_EL1_MPAM_MASK;
+ /* Fail the guest's request to disable the AA64 ISA at EL{0,1,2} */
+ if (!FIELD_GET(ID_AA64PFR0_EL1_EL0, user_val) ||
+ !FIELD_GET(ID_AA64PFR0_EL1_EL1, user_val) ||
+ (vcpu_has_nv(vcpu) && !FIELD_GET(ID_AA64PFR0_EL1_EL2, user_val)))
+ return -EINVAL;
+
return set_id_reg(vcpu, rd, user_val);
}
diff --git a/arch/mips/include/asm/idle.h b/arch/mips/include/asm/idle.h
index 0992cad9c632..c7d75807d13f 100644
--- a/arch/mips/include/asm/idle.h
+++ b/arch/mips/include/asm/idle.h
@@ -6,11 +6,10 @@
#include <linux/linkage.h>
extern void (*cpu_wait)(void);
-extern void r4k_wait(void);
-extern asmlinkage void __r4k_wait(void);
+extern asmlinkage void r4k_wait(void);
extern void r4k_wait_irqoff(void);
-static inline int using_rollback_handler(void)
+static inline int using_skipover_handler(void)
{
return cpu_wait == r4k_wait;
}
diff --git a/arch/mips/include/asm/ptrace.h b/arch/mips/include/asm/ptrace.h
index 85fa9962266a..ef72c46b5568 100644
--- a/arch/mips/include/asm/ptrace.h
+++ b/arch/mips/include/asm/ptrace.h
@@ -65,7 +65,8 @@ static inline void instruction_pointer_set(struct pt_regs *regs,
/* Query offset/name of register from its name/offset */
extern int regs_query_register_offset(const char *name);
-#define MAX_REG_OFFSET (offsetof(struct pt_regs, __last))
+#define MAX_REG_OFFSET \
+ (offsetof(struct pt_regs, __last) - sizeof(unsigned long))
/**
* regs_get_register() - get register value from its offset
diff --git a/arch/mips/kernel/genex.S b/arch/mips/kernel/genex.S
index a572ce36a24f..08c0a01d9a29 100644
--- a/arch/mips/kernel/genex.S
+++ b/arch/mips/kernel/genex.S
@@ -104,48 +104,59 @@ handle_vcei:
__FINIT
- .align 5 /* 32 byte rollback region */
-LEAF(__r4k_wait)
- .set push
- .set noreorder
- /* start of rollback region */
- LONG_L t0, TI_FLAGS($28)
- nop
- andi t0, _TIF_NEED_RESCHED
- bnez t0, 1f
- nop
- nop
- nop
-#ifdef CONFIG_CPU_MICROMIPS
- nop
- nop
- nop
- nop
-#endif
+ .section .cpuidle.text,"ax"
+ /* Align to 32 bytes for the maximum idle interrupt region size. */
+ .align 5
+LEAF(r4k_wait)
+ /* Keep the ISA bit clear for calculations on local labels here. */
+0: .fill 0
+ /* Start of idle interrupt region. */
+ local_irq_enable
+ /*
+ * If an interrupt lands here, before going idle on the next
+ * instruction, we must *NOT* go idle since the interrupt could
+ * have set TIF_NEED_RESCHED or caused a timer to need resched.
+ * Fall through -- see skipover_handler below -- and have the
+ * idle loop take care of things.
+ */
+1: .fill 0
+ /* The R2 EI/EHB sequence takes 8 bytes, otherwise pad up. */
+ .if 1b - 0b > 32
+ .error "overlong idle interrupt region"
+ .elseif 1b - 0b > 8
+ .align 4
+ .endif
+2: .fill 0
+ .equ r4k_wait_idle_size, 2b - 0b
+ /* End of idle interrupt region; size has to be a power of 2. */
.set MIPS_ISA_ARCH_LEVEL_RAW
+r4k_wait_insn:
wait
- /* end of rollback region (the region size must be power of two) */
-1:
+r4k_wait_exit:
+ .set mips0
+ local_irq_disable
jr ra
- nop
- .set pop
- END(__r4k_wait)
+ END(r4k_wait)
+ .previous
- .macro BUILD_ROLLBACK_PROLOGUE handler
- FEXPORT(rollback_\handler)
+ .macro BUILD_SKIPOVER_PROLOGUE handler
+ FEXPORT(skipover_\handler)
.set push
.set noat
MFC0 k0, CP0_EPC
- PTR_LA k1, __r4k_wait
- ori k0, 0x1f /* 32 byte rollback region */
- xori k0, 0x1f
+ /* Subtract/add 2 to let the ISA bit propagate through the mask. */
+ PTR_LA k1, r4k_wait_insn - 2
+ ori k0, r4k_wait_idle_size - 2
+ .set noreorder
bne k0, k1, \handler
+ PTR_ADDIU k0, r4k_wait_exit - r4k_wait_insn + 2
+ .set reorder
MTC0 k0, CP0_EPC
.set pop
.endm
.align 5
-BUILD_ROLLBACK_PROLOGUE handle_int
+BUILD_SKIPOVER_PROLOGUE handle_int
NESTED(handle_int, PT_SIZE, sp)
.cfi_signal_frame
#ifdef CONFIG_TRACE_IRQFLAGS
@@ -265,7 +276,7 @@ NESTED(except_vec_ejtag_debug, 0, sp)
* This prototype is copied to ebase + n*IntCtl.VS and patched
* to invoke the handler
*/
-BUILD_ROLLBACK_PROLOGUE except_vec_vi
+BUILD_SKIPOVER_PROLOGUE except_vec_vi
NESTED(except_vec_vi, 0, sp)
SAVE_SOME docfi=1
SAVE_AT docfi=1
diff --git a/arch/mips/kernel/idle.c b/arch/mips/kernel/idle.c
index 5abc8b7340f8..80e8a04a642e 100644
--- a/arch/mips/kernel/idle.c
+++ b/arch/mips/kernel/idle.c
@@ -35,13 +35,6 @@ static void __cpuidle r3081_wait(void)
write_c0_conf(cfg | R30XX_CONF_HALT);
}
-void __cpuidle r4k_wait(void)
-{
- raw_local_irq_enable();
- __r4k_wait();
- raw_local_irq_disable();
-}
-
/*
* This variant is preferable as it allows testing need_resched and going to
* sleep depending on the outcome atomically. Unfortunately the "It is
diff --git a/arch/mips/kernel/smp-cps.c b/arch/mips/kernel/smp-cps.c
index e85bd087467e..cc26d56f3ab6 100644
--- a/arch/mips/kernel/smp-cps.c
+++ b/arch/mips/kernel/smp-cps.c
@@ -332,6 +332,8 @@ static void __init cps_prepare_cpus(unsigned int max_cpus)
mips_cps_cluster_bootcfg = kcalloc(nclusters,
sizeof(*mips_cps_cluster_bootcfg),
GFP_KERNEL);
+ if (!mips_cps_cluster_bootcfg)
+ goto err_out;
if (nclusters > 1)
mips_cm_update_property();
@@ -348,6 +350,8 @@ static void __init cps_prepare_cpus(unsigned int max_cpus)
mips_cps_cluster_bootcfg[cl].core_power =
kcalloc(BITS_TO_LONGS(ncores), sizeof(unsigned long),
GFP_KERNEL);
+ if (!mips_cps_cluster_bootcfg[cl].core_power)
+ goto err_out;
/* Allocate VPE boot configuration structs */
for (c = 0; c < ncores; c++) {
diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c
index 39e248d0ed59..8ec1e185b35c 100644
--- a/arch/mips/kernel/traps.c
+++ b/arch/mips/kernel/traps.c
@@ -77,7 +77,7 @@
#include "access-helper.h"
extern void check_wait(void);
-extern asmlinkage void rollback_handle_int(void);
+extern asmlinkage void skipover_handle_int(void);
extern asmlinkage void handle_int(void);
extern asmlinkage void handle_adel(void);
extern asmlinkage void handle_ades(void);
@@ -2066,7 +2066,7 @@ void *set_vi_handler(int n, vi_handler_t addr)
{
extern const u8 except_vec_vi[];
extern const u8 except_vec_vi_ori[], except_vec_vi_end[];
- extern const u8 rollback_except_vec_vi[];
+ extern const u8 skipover_except_vec_vi[];
unsigned long handler;
unsigned long old_handler = vi_handlers[n];
int srssets = current_cpu_data.srsets;
@@ -2095,7 +2095,7 @@ void *set_vi_handler(int n, vi_handler_t addr)
change_c0_srsmap(0xf << n*4, 0 << n*4);
}
- vec_start = using_rollback_handler() ? rollback_except_vec_vi :
+ vec_start = using_skipover_handler() ? skipover_except_vec_vi :
except_vec_vi;
#if defined(CONFIG_CPU_MICROMIPS) || defined(CONFIG_CPU_BIG_ENDIAN)
ori_offset = except_vec_vi_ori - vec_start + 2;
@@ -2426,8 +2426,8 @@ void __init trap_init(void)
if (board_be_init)
board_be_init();
- set_except_vector(EXCCODE_INT, using_rollback_handler() ?
- rollback_handle_int : handle_int);
+ set_except_vector(EXCCODE_INT, using_skipover_handler() ?
+ skipover_handle_int : handle_int);
set_except_vector(EXCCODE_MOD, handle_tlbm);
set_except_vector(EXCCODE_TLBL, handle_tlbl);
set_except_vector(EXCCODE_TLBS, handle_tlbs);
diff --git a/arch/riscv/kvm/vcpu.c b/arch/riscv/kvm/vcpu.c
index 60d684c76c58..02635bac91f1 100644
--- a/arch/riscv/kvm/vcpu.c
+++ b/arch/riscv/kvm/vcpu.c
@@ -77,6 +77,8 @@ static void kvm_riscv_reset_vcpu(struct kvm_vcpu *vcpu)
memcpy(cntx, reset_cntx, sizeof(*cntx));
spin_unlock(&vcpu->arch.reset_cntx_lock);
+ memset(&vcpu->arch.smstateen_csr, 0, sizeof(vcpu->arch.smstateen_csr));
+
kvm_riscv_vcpu_fp_reset(vcpu);
kvm_riscv_vcpu_vector_reset(vcpu);
diff --git a/arch/x86/include/asm/microcode.h b/arch/x86/include/asm/microcode.h
index 695e569159c1..be7cddc414e4 100644
--- a/arch/x86/include/asm/microcode.h
+++ b/arch/x86/include/asm/microcode.h
@@ -17,10 +17,12 @@ struct ucode_cpu_info {
void load_ucode_bsp(void);
void load_ucode_ap(void);
void microcode_bsp_resume(void);
+bool __init microcode_loader_disabled(void);
#else
static inline void load_ucode_bsp(void) { }
static inline void load_ucode_ap(void) { }
static inline void microcode_bsp_resume(void) { }
+static inline bool __init microcode_loader_disabled(void) { return false; }
#endif
extern unsigned long initrd_start_early;
diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c
index 4a10d35e70aa..96cb992d50ef 100644
--- a/arch/x86/kernel/cpu/microcode/amd.c
+++ b/arch/x86/kernel/cpu/microcode/amd.c
@@ -1098,15 +1098,17 @@ static enum ucode_state load_microcode_amd(u8 family, const u8 *data, size_t siz
static int __init save_microcode_in_initrd(void)
{
- unsigned int cpuid_1_eax = native_cpuid_eax(1);
struct cpuinfo_x86 *c = &boot_cpu_data;
struct cont_desc desc = { 0 };
+ unsigned int cpuid_1_eax;
enum ucode_state ret;
struct cpio_data cp;
- if (dis_ucode_ldr || c->x86_vendor != X86_VENDOR_AMD || c->x86 < 0x10)
+ if (microcode_loader_disabled() || c->x86_vendor != X86_VENDOR_AMD || c->x86 < 0x10)
return 0;
+ cpuid_1_eax = native_cpuid_eax(1);
+
if (!find_blobs_in_containers(&cp))
return -EINVAL;
diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c
index b3658d11e7b6..079f046ee26d 100644
--- a/arch/x86/kernel/cpu/microcode/core.c
+++ b/arch/x86/kernel/cpu/microcode/core.c
@@ -41,8 +41,8 @@
#include "internal.h"
-static struct microcode_ops *microcode_ops;
-bool dis_ucode_ldr = true;
+static struct microcode_ops *microcode_ops;
+static bool dis_ucode_ldr = false;
bool force_minrev = IS_ENABLED(CONFIG_MICROCODE_LATE_FORCE_MINREV);
module_param(force_minrev, bool, S_IRUSR | S_IWUSR);
@@ -84,6 +84,9 @@ static bool amd_check_current_patch_level(void)
u32 lvl, dummy, i;
u32 *levels;
+ if (x86_cpuid_vendor() != X86_VENDOR_AMD)
+ return false;
+
native_rdmsr(MSR_AMD64_PATCH_LEVEL, lvl, dummy);
levels = final_levels;
@@ -95,27 +98,29 @@ static bool amd_check_current_patch_level(void)
return false;
}
-static bool __init check_loader_disabled_bsp(void)
+bool __init microcode_loader_disabled(void)
{
- static const char *__dis_opt_str = "dis_ucode_ldr";
- const char *cmdline = boot_command_line;
- const char *option = __dis_opt_str;
+ if (dis_ucode_ldr)
+ return true;
/*
- * CPUID(1).ECX[31]: reserved for hypervisor use. This is still not
- * completely accurate as xen pv guests don't see that CPUID bit set but
- * that's good enough as they don't land on the BSP path anyway.
+ * Disable when:
+ *
+ * 1) The CPU does not support CPUID.
+ *
+ * 2) Bit 31 in CPUID[1]:ECX is clear
+ * The bit is reserved for hypervisor use. This is still not
+ * completely accurate as XEN PV guests don't see that CPUID bit
+ * set, but that's good enough as they don't land on the BSP
+ * path anyway.
+ *
+ * 3) Certain AMD patch levels are not allowed to be
+ * overwritten.
*/
- if (native_cpuid_ecx(1) & BIT(31))
- return true;
-
- if (x86_cpuid_vendor() == X86_VENDOR_AMD) {
- if (amd_check_current_patch_level())
- return true;
- }
-
- if (cmdline_find_option_bool(cmdline, option) <= 0)
- dis_ucode_ldr = false;
+ if (!have_cpuid_p() ||
+ native_cpuid_ecx(1) & BIT(31) ||
+ amd_check_current_patch_level())
+ dis_ucode_ldr = true;
return dis_ucode_ldr;
}
@@ -125,7 +130,10 @@ void __init load_ucode_bsp(void)
unsigned int cpuid_1_eax;
bool intel = true;
- if (!have_cpuid_p())
+ if (cmdline_find_option_bool(boot_command_line, "dis_ucode_ldr") > 0)
+ dis_ucode_ldr = true;
+
+ if (microcode_loader_disabled())
return;
cpuid_1_eax = native_cpuid_eax(1);
@@ -146,9 +154,6 @@ void __init load_ucode_bsp(void)
return;
}
- if (check_loader_disabled_bsp())
- return;
-
if (intel)
load_ucode_intel_bsp(&early_data);
else
@@ -159,6 +164,11 @@ void load_ucode_ap(void)
{
unsigned int cpuid_1_eax;
+ /*
+ * Can't use microcode_loader_disabled() here - .init section
+ * hell. It doesn't have to either - the BSP variant must've
+ * parsed cmdline already anyway.
+ */
if (dis_ucode_ldr)
return;
@@ -810,7 +820,7 @@ static int __init microcode_init(void)
struct cpuinfo_x86 *c = &boot_cpu_data;
int error;
- if (dis_ucode_ldr)
+ if (microcode_loader_disabled())
return -EINVAL;
if (c->x86_vendor == X86_VENDOR_INTEL)
diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c
index 819199bc0119..2a397da43923 100644
--- a/arch/x86/kernel/cpu/microcode/intel.c
+++ b/arch/x86/kernel/cpu/microcode/intel.c
@@ -389,7 +389,7 @@ static int __init save_builtin_microcode(void)
if (xchg(&ucode_patch_va, NULL) != UCODE_BSP_LOADED)
return 0;
- if (dis_ucode_ldr || boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
+ if (microcode_loader_disabled() || boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
return 0;
uci.mc = get_microcode_blob(&uci, true);
diff --git a/arch/x86/kernel/cpu/microcode/internal.h b/arch/x86/kernel/cpu/microcode/internal.h
index 5df621752fef..50a9702ae4e2 100644
--- a/arch/x86/kernel/cpu/microcode/internal.h
+++ b/arch/x86/kernel/cpu/microcode/internal.h
@@ -94,7 +94,6 @@ static inline unsigned int x86_cpuid_family(void)
return x86_family(eax);
}
-extern bool dis_ucode_ldr;
extern bool force_minrev;
#ifdef CONFIG_CPU_SUP_AMD
diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c
index de001b2146ab..375f2d7f1762 100644
--- a/arch/x86/kernel/head32.c
+++ b/arch/x86/kernel/head32.c
@@ -145,10 +145,6 @@ void __init __no_stack_protector mk_early_pgtbl_32(void)
*ptr = (unsigned long)ptep + PAGE_OFFSET;
#ifdef CONFIG_MICROCODE_INITRD32
- /* Running on a hypervisor? */
- if (native_cpuid_ecx(1) & BIT(31))
- return;
-
params = (struct boot_params *)__pa_nodebug(&boot_params);
if (!params->hdr.ramdisk_size || !params->hdr.ramdisk_image)
return;
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index ccdc45e5b759..aa4d0221583c 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -466,10 +466,18 @@ SECTIONS
}
/*
- * The ASSERT() sink to . is intentional, for binutils 2.14 compatibility:
+ * COMPILE_TEST kernels can be large - CONFIG_KASAN, for example, can cause
+ * this. Let's assume that nobody will be running a COMPILE_TEST kernel and
+ * let's assert that fuller build coverage is more valuable than being able to
+ * run a COMPILE_TEST kernel.
+ */
+#ifndef CONFIG_COMPILE_TEST
+/*
+ * The ASSERT() sync to . is intentional, for binutils 2.14 compatibility:
*/
. = ASSERT((_end - LOAD_OFFSET <= KERNEL_IMAGE_SIZE),
"kernel image bigger than KERNEL_IMAGE_SIZE");
+#endif
/* needed for Clang - see arch/x86/entry/entry.S */
PROVIDE(__ref_stack_chk_guard = __stack_chk_guard);
diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h
index 050a0e229a4d..f2b36d32ef40 100644
--- a/arch/x86/kvm/mmu.h
+++ b/arch/x86/kvm/mmu.h
@@ -104,6 +104,9 @@ void kvm_mmu_track_write(struct kvm_vcpu *vcpu, gpa_t gpa, const u8 *new,
static inline int kvm_mmu_reload(struct kvm_vcpu *vcpu)
{
+ if (kvm_check_request(KVM_REQ_MMU_FREE_OBSOLETE_ROOTS, vcpu))
+ kvm_mmu_free_obsolete_roots(vcpu);
+
/*
* Checking root.hpa is sufficient even when KVM has mirror root.
* We can have either:
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 63bb77ee1bb1..8d1b632e33d2 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -5974,6 +5974,7 @@ void kvm_mmu_free_obsolete_roots(struct kvm_vcpu *vcpu)
__kvm_mmu_free_obsolete_roots(vcpu->kvm, &vcpu->arch.root_mmu);
__kvm_mmu_free_obsolete_roots(vcpu->kvm, &vcpu->arch.guest_mmu);
}
+EXPORT_SYMBOL_GPL(kvm_mmu_free_obsolete_roots);
static u64 mmu_pte_write_fetch_gpte(struct kvm_vcpu *vcpu, gpa_t *gpa,
int *bytes)
@@ -7669,9 +7670,30 @@ void kvm_mmu_pre_destroy_vm(struct kvm *kvm)
}
#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES
+static bool hugepage_test_mixed(struct kvm_memory_slot *slot, gfn_t gfn,
+ int level)
+{
+ return lpage_info_slot(gfn, slot, level)->disallow_lpage & KVM_LPAGE_MIXED_FLAG;
+}
+
+static void hugepage_clear_mixed(struct kvm_memory_slot *slot, gfn_t gfn,
+ int level)
+{
+ lpage_info_slot(gfn, slot, level)->disallow_lpage &= ~KVM_LPAGE_MIXED_FLAG;
+}
+
+static void hugepage_set_mixed(struct kvm_memory_slot *slot, gfn_t gfn,
+ int level)
+{
+ lpage_info_slot(gfn, slot, level)->disallow_lpage |= KVM_LPAGE_MIXED_FLAG;
+}
+
bool kvm_arch_pre_set_memory_attributes(struct kvm *kvm,
struct kvm_gfn_range *range)
{
+ struct kvm_memory_slot *slot = range->slot;
+ int level;
+
/*
* Zap SPTEs even if the slot can't be mapped PRIVATE. KVM x86 only
* supports KVM_MEMORY_ATTRIBUTE_PRIVATE, and so it *seems* like KVM
@@ -7686,6 +7708,38 @@ bool kvm_arch_pre_set_memory_attributes(struct kvm *kvm,
if (WARN_ON_ONCE(!kvm_arch_has_private_mem(kvm)))
return false;
+ if (WARN_ON_ONCE(range->end <= range->start))
+ return false;
+
+ /*
+ * If the head and tail pages of the range currently allow a hugepage,
+ * i.e. reside fully in the slot and don't have mixed attributes, then
+ * add each corresponding hugepage range to the ongoing invalidation,
+ * e.g. to prevent KVM from creating a hugepage in response to a fault
+ * for a gfn whose attributes aren't changing. Note, only the range
+ * of gfns whose attributes are being modified needs to be explicitly
+ * unmapped, as that will unmap any existing hugepages.
+ */
+ for (level = PG_LEVEL_2M; level <= KVM_MAX_HUGEPAGE_LEVEL; level++) {
+ gfn_t start = gfn_round_for_level(range->start, level);
+ gfn_t end = gfn_round_for_level(range->end - 1, level);
+ gfn_t nr_pages = KVM_PAGES_PER_HPAGE(level);
+
+ if ((start != range->start || start + nr_pages > range->end) &&
+ start >= slot->base_gfn &&
+ start + nr_pages <= slot->base_gfn + slot->npages &&
+ !hugepage_test_mixed(slot, start, level))
+ kvm_mmu_invalidate_range_add(kvm, start, start + nr_pages);
+
+ if (end == start)
+ continue;
+
+ if ((end + nr_pages) > range->end &&
+ (end + nr_pages) <= (slot->base_gfn + slot->npages) &&
+ !hugepage_test_mixed(slot, end, level))
+ kvm_mmu_invalidate_range_add(kvm, end, end + nr_pages);
+ }
+
/* Unmap the old attribute page. */
if (range->arg.attributes & KVM_MEMORY_ATTRIBUTE_PRIVATE)
range->attr_filter = KVM_FILTER_SHARED;
@@ -7695,23 +7749,7 @@ bool kvm_arch_pre_set_memory_attributes(struct kvm *kvm,
return kvm_unmap_gfn_range(kvm, range);
}
-static bool hugepage_test_mixed(struct kvm_memory_slot *slot, gfn_t gfn,
- int level)
-{
- return lpage_info_slot(gfn, slot, level)->disallow_lpage & KVM_LPAGE_MIXED_FLAG;
-}
-
-static void hugepage_clear_mixed(struct kvm_memory_slot *slot, gfn_t gfn,
- int level)
-{
- lpage_info_slot(gfn, slot, level)->disallow_lpage &= ~KVM_LPAGE_MIXED_FLAG;
-}
-static void hugepage_set_mixed(struct kvm_memory_slot *slot, gfn_t gfn,
- int level)
-{
- lpage_info_slot(gfn, slot, level)->disallow_lpage |= KVM_LPAGE_MIXED_FLAG;
-}
static bool hugepage_has_attrs(struct kvm *kvm, struct kvm_memory_slot *slot,
gfn_t gfn, int level, unsigned long attrs)
diff --git a/arch/x86/kvm/smm.c b/arch/x86/kvm/smm.c
index 699e551ec93b..9864c057187d 100644
--- a/arch/x86/kvm/smm.c
+++ b/arch/x86/kvm/smm.c
@@ -131,6 +131,7 @@ void kvm_smm_changed(struct kvm_vcpu *vcpu, bool entering_smm)
kvm_mmu_reset_context(vcpu);
}
+EXPORT_SYMBOL_GPL(kvm_smm_changed);
void process_smi(struct kvm_vcpu *vcpu)
{
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index 0bc708ee2788..a7a7dc507336 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -3173,9 +3173,14 @@ skip_vmsa_free:
kvfree(svm->sev_es.ghcb_sa);
}
+static u64 kvm_ghcb_get_sw_exit_code(struct vmcb_control_area *control)
+{
+ return (((u64)control->exit_code_hi) << 32) | control->exit_code;
+}
+
static void dump_ghcb(struct vcpu_svm *svm)
{
- struct ghcb *ghcb = svm->sev_es.ghcb;
+ struct vmcb_control_area *control = &svm->vmcb->control;
unsigned int nbits;
/* Re-use the dump_invalid_vmcb module parameter */
@@ -3184,18 +3189,24 @@ static void dump_ghcb(struct vcpu_svm *svm)
return;
}
- nbits = sizeof(ghcb->save.valid_bitmap) * 8;
+ nbits = sizeof(svm->sev_es.valid_bitmap) * 8;
- pr_err("GHCB (GPA=%016llx):\n", svm->vmcb->control.ghcb_gpa);
+ /*
+ * Print KVM's snapshot of the GHCB values that were (unsuccessfully)
+ * used to handle the exit. If the guest has since modified the GHCB
+ * itself, dumping the raw GHCB won't help debug why KVM was unable to
+ * handle the VMGEXIT that KVM observed.
+ */
+ pr_err("GHCB (GPA=%016llx) snapshot:\n", svm->vmcb->control.ghcb_gpa);
pr_err("%-20s%016llx is_valid: %u\n", "sw_exit_code",
- ghcb->save.sw_exit_code, ghcb_sw_exit_code_is_valid(ghcb));
+ kvm_ghcb_get_sw_exit_code(control), kvm_ghcb_sw_exit_code_is_valid(svm));
pr_err("%-20s%016llx is_valid: %u\n", "sw_exit_info_1",
- ghcb->save.sw_exit_info_1, ghcb_sw_exit_info_1_is_valid(ghcb));
+ control->exit_info_1, kvm_ghcb_sw_exit_info_1_is_valid(svm));
pr_err("%-20s%016llx is_valid: %u\n", "sw_exit_info_2",
- ghcb->save.sw_exit_info_2, ghcb_sw_exit_info_2_is_valid(ghcb));
+ control->exit_info_2, kvm_ghcb_sw_exit_info_2_is_valid(svm));
pr_err("%-20s%016llx is_valid: %u\n", "sw_scratch",
- ghcb->save.sw_scratch, ghcb_sw_scratch_is_valid(ghcb));
- pr_err("%-20s%*pb\n", "valid_bitmap", nbits, ghcb->save.valid_bitmap);
+ svm->sev_es.sw_scratch, kvm_ghcb_sw_scratch_is_valid(svm));
+ pr_err("%-20s%*pb\n", "valid_bitmap", nbits, svm->sev_es.valid_bitmap);
}
static void sev_es_sync_to_ghcb(struct vcpu_svm *svm)
@@ -3266,11 +3277,6 @@ static void sev_es_sync_from_ghcb(struct vcpu_svm *svm)
memset(ghcb->save.valid_bitmap, 0, sizeof(ghcb->save.valid_bitmap));
}
-static u64 kvm_ghcb_get_sw_exit_code(struct vmcb_control_area *control)
-{
- return (((u64)control->exit_code_hi) << 32) | control->exit_code;
-}
-
static int sev_es_validate_vmgexit(struct vcpu_svm *svm)
{
struct vmcb_control_area *control = &svm->vmcb->control;
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index d5d0c5c3300b..a89c271a1951 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -607,9 +607,6 @@ static void svm_disable_virtualization_cpu(void)
kvm_cpu_svm_disable();
amd_pmu_disable_virt();
-
- if (cpu_feature_enabled(X86_FEATURE_SRSO_BP_SPEC_REDUCE))
- msr_clear_bit(MSR_ZEN4_BP_CFG, MSR_ZEN4_BP_CFG_BP_SPEC_REDUCE_BIT);
}
static int svm_enable_virtualization_cpu(void)
@@ -687,9 +684,6 @@ static int svm_enable_virtualization_cpu(void)
rdmsr(MSR_TSC_AUX, sev_es_host_save_area(sd)->tsc_aux, msr_hi);
}
- if (cpu_feature_enabled(X86_FEATURE_SRSO_BP_SPEC_REDUCE))
- msr_set_bit(MSR_ZEN4_BP_CFG, MSR_ZEN4_BP_CFG_BP_SPEC_REDUCE_BIT);
-
return 0;
}
@@ -1518,6 +1512,63 @@ static void svm_vcpu_free(struct kvm_vcpu *vcpu)
__free_pages(virt_to_page(svm->msrpm), get_order(MSRPM_SIZE));
}
+#ifdef CONFIG_CPU_MITIGATIONS
+static DEFINE_SPINLOCK(srso_lock);
+static atomic_t srso_nr_vms;
+
+static void svm_srso_clear_bp_spec_reduce(void *ign)
+{
+ struct svm_cpu_data *sd = this_cpu_ptr(&svm_data);
+
+ if (!sd->bp_spec_reduce_set)
+ return;
+
+ msr_clear_bit(MSR_ZEN4_BP_CFG, MSR_ZEN4_BP_CFG_BP_SPEC_REDUCE_BIT);
+ sd->bp_spec_reduce_set = false;
+}
+
+static void svm_srso_vm_destroy(void)
+{
+ if (!cpu_feature_enabled(X86_FEATURE_SRSO_BP_SPEC_REDUCE))
+ return;
+
+ if (atomic_dec_return(&srso_nr_vms))
+ return;
+
+ guard(spinlock)(&srso_lock);
+
+ /*
+ * Verify a new VM didn't come along, acquire the lock, and increment
+ * the count before this task acquired the lock.
+ */
+ if (atomic_read(&srso_nr_vms))
+ return;
+
+ on_each_cpu(svm_srso_clear_bp_spec_reduce, NULL, 1);
+}
+
+static void svm_srso_vm_init(void)
+{
+ if (!cpu_feature_enabled(X86_FEATURE_SRSO_BP_SPEC_REDUCE))
+ return;
+
+ /*
+ * Acquire the lock on 0 => 1 transitions to ensure a potential 1 => 0
+ * transition, i.e. destroying the last VM, is fully complete, e.g. so
+ * that a delayed IPI doesn't clear BP_SPEC_REDUCE after a vCPU runs.
+ */
+ if (atomic_inc_not_zero(&srso_nr_vms))
+ return;
+
+ guard(spinlock)(&srso_lock);
+
+ atomic_inc(&srso_nr_vms);
+}
+#else
+static void svm_srso_vm_init(void) { }
+static void svm_srso_vm_destroy(void) { }
+#endif
+
static void svm_prepare_switch_to_guest(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
@@ -1550,6 +1601,11 @@ static void svm_prepare_switch_to_guest(struct kvm_vcpu *vcpu)
(!boot_cpu_has(X86_FEATURE_V_TSC_AUX) || !sev_es_guest(vcpu->kvm)))
kvm_set_user_return_msr(tsc_aux_uret_slot, svm->tsc_aux, -1ull);
+ if (cpu_feature_enabled(X86_FEATURE_SRSO_BP_SPEC_REDUCE) &&
+ !sd->bp_spec_reduce_set) {
+ sd->bp_spec_reduce_set = true;
+ msr_set_bit(MSR_ZEN4_BP_CFG, MSR_ZEN4_BP_CFG_BP_SPEC_REDUCE_BIT);
+ }
svm->guest_state_loaded = true;
}
@@ -2231,6 +2287,10 @@ static int shutdown_interception(struct kvm_vcpu *vcpu)
*/
if (!sev_es_guest(vcpu->kvm)) {
clear_page(svm->vmcb);
+#ifdef CONFIG_KVM_SMM
+ if (is_smm(vcpu))
+ kvm_smm_changed(vcpu, false);
+#endif
kvm_vcpu_reset(vcpu, true);
}
@@ -5036,6 +5096,8 @@ static void svm_vm_destroy(struct kvm *kvm)
{
avic_vm_destroy(kvm);
sev_vm_destroy(kvm);
+
+ svm_srso_vm_destroy();
}
static int svm_vm_init(struct kvm *kvm)
@@ -5061,6 +5123,7 @@ static int svm_vm_init(struct kvm *kvm)
return ret;
}
+ svm_srso_vm_init();
return 0;
}
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index d4490eaed55d..f16b068c4228 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -335,6 +335,8 @@ struct svm_cpu_data {
u32 next_asid;
u32 min_asid;
+ bool bp_spec_reduce_set;
+
struct vmcb *save_area;
unsigned long save_area_pa;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index df5b99ea1f18..9896fd574bfc 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -4597,7 +4597,7 @@ static bool kvm_is_vm_type_supported(unsigned long type)
return type < 32 && (kvm_caps.supported_vm_types & BIT(type));
}
-static inline u32 kvm_sync_valid_fields(struct kvm *kvm)
+static inline u64 kvm_sync_valid_fields(struct kvm *kvm)
{
return kvm && kvm->arch.has_protected_state ? 0 : KVM_SYNC_X86_VALID_FIELDS;
}
@@ -11493,7 +11493,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
{
struct kvm_queued_exception *ex = &vcpu->arch.exception;
struct kvm_run *kvm_run = vcpu->run;
- u32 sync_valid_fields;
+ u64 sync_valid_fields;
int r;
r = kvm_mmu_post_init_vm(vcpu->kvm);
diff --git a/drivers/clocksource/i8253.c b/drivers/clocksource/i8253.c
index 39f7c2d736d1..b603c25f3dfa 100644
--- a/drivers/clocksource/i8253.c
+++ b/drivers/clocksource/i8253.c
@@ -103,7 +103,7 @@ int __init clocksource_i8253_init(void)
#ifdef CONFIG_CLKEVT_I8253
void clockevent_i8253_disable(void)
{
- raw_spin_lock(&i8253_lock);
+ guard(raw_spinlock_irqsave)(&i8253_lock);
/*
* Writing the MODE register should stop the counter, according to
@@ -132,8 +132,6 @@ void clockevent_i8253_disable(void)
outb_p(0, PIT_CH0);
outb_p(0x30, PIT_MODE);
-
- raw_spin_unlock(&i8253_lock);
}
static int pit_shutdown(struct clock_event_device *evt)
diff --git a/drivers/input/joystick/magellan.c b/drivers/input/joystick/magellan.c
index d73389af4dd5..7622638e5bb8 100644
--- a/drivers/input/joystick/magellan.c
+++ b/drivers/input/joystick/magellan.c
@@ -48,7 +48,7 @@ struct magellan {
static int magellan_crunch_nibbles(unsigned char *data, int count)
{
- static unsigned char nibbles[16] __nonstring = "0AB3D56GH9:K<MN?";
+ static const unsigned char nibbles[16] __nonstring = "0AB3D56GH9:K<MN?";
do {
if (data[count] == nibbles[data[count] & 0xf])
diff --git a/drivers/input/joystick/xpad.c b/drivers/input/joystick/xpad.c
index c33e6f33265b..57a5ff3d1992 100644
--- a/drivers/input/joystick/xpad.c
+++ b/drivers/input/joystick/xpad.c
@@ -77,12 +77,13 @@
* xbox d-pads should map to buttons, as is required for DDR pads
* but we map them to axes when possible to simplify things
*/
-#define MAP_DPAD_TO_BUTTONS (1 << 0)
-#define MAP_TRIGGERS_TO_BUTTONS (1 << 1)
-#define MAP_STICKS_TO_NULL (1 << 2)
-#define MAP_SELECT_BUTTON (1 << 3)
-#define MAP_PADDLES (1 << 4)
-#define MAP_PROFILE_BUTTON (1 << 5)
+#define MAP_DPAD_TO_BUTTONS BIT(0)
+#define MAP_TRIGGERS_TO_BUTTONS BIT(1)
+#define MAP_STICKS_TO_NULL BIT(2)
+#define MAP_SHARE_BUTTON BIT(3)
+#define MAP_PADDLES BIT(4)
+#define MAP_PROFILE_BUTTON BIT(5)
+#define MAP_SHARE_OFFSET BIT(6)
#define DANCEPAD_MAP_CONFIG (MAP_DPAD_TO_BUTTONS | \
MAP_TRIGGERS_TO_BUTTONS | MAP_STICKS_TO_NULL)
@@ -135,14 +136,14 @@ static const struct xpad_device {
{ 0x03f0, 0x048D, "HyperX Clutch", 0, XTYPE_XBOX360 }, /* wireless */
{ 0x03f0, 0x0495, "HyperX Clutch Gladiate", 0, XTYPE_XBOXONE },
{ 0x03f0, 0x07A0, "HyperX Clutch Gladiate RGB", 0, XTYPE_XBOXONE },
- { 0x03f0, 0x08B6, "HyperX Clutch Gladiate", 0, XTYPE_XBOXONE }, /* v2 */
+ { 0x03f0, 0x08B6, "HyperX Clutch Gladiate", MAP_SHARE_BUTTON, XTYPE_XBOXONE }, /* v2 */
{ 0x03f0, 0x09B4, "HyperX Clutch Tanto", 0, XTYPE_XBOXONE },
{ 0x044f, 0x0f00, "Thrustmaster Wheel", 0, XTYPE_XBOX },
{ 0x044f, 0x0f03, "Thrustmaster Wheel", 0, XTYPE_XBOX },
{ 0x044f, 0x0f07, "Thrustmaster, Inc. Controller", 0, XTYPE_XBOX },
- { 0x044f, 0xd01e, "ThrustMaster, Inc. ESWAP X 2 ELDEN RING EDITION", 0, XTYPE_XBOXONE },
{ 0x044f, 0x0f10, "Thrustmaster Modena GT Wheel", 0, XTYPE_XBOX },
{ 0x044f, 0xb326, "Thrustmaster Gamepad GP XID", 0, XTYPE_XBOX360 },
+ { 0x044f, 0xd01e, "ThrustMaster, Inc. ESWAP X 2 ELDEN RING EDITION", 0, XTYPE_XBOXONE },
{ 0x045e, 0x0202, "Microsoft X-Box pad v1 (US)", 0, XTYPE_XBOX },
{ 0x045e, 0x0285, "Microsoft X-Box pad (Japan)", 0, XTYPE_XBOX },
{ 0x045e, 0x0287, "Microsoft Xbox Controller S", 0, XTYPE_XBOX },
@@ -159,7 +160,7 @@ static const struct xpad_device {
{ 0x045e, 0x0719, "Xbox 360 Wireless Receiver", MAP_DPAD_TO_BUTTONS, XTYPE_XBOX360W },
{ 0x045e, 0x0b00, "Microsoft X-Box One Elite 2 pad", MAP_PADDLES, XTYPE_XBOXONE },
{ 0x045e, 0x0b0a, "Microsoft X-Box Adaptive Controller", MAP_PROFILE_BUTTON, XTYPE_XBOXONE },
- { 0x045e, 0x0b12, "Microsoft Xbox Series S|X Controller", MAP_SELECT_BUTTON, XTYPE_XBOXONE },
+ { 0x045e, 0x0b12, "Microsoft Xbox Series S|X Controller", MAP_SHARE_BUTTON | MAP_SHARE_OFFSET, XTYPE_XBOXONE },
{ 0x046d, 0xc21d, "Logitech Gamepad F310", 0, XTYPE_XBOX360 },
{ 0x046d, 0xc21e, "Logitech Gamepad F510", 0, XTYPE_XBOX360 },
{ 0x046d, 0xc21f, "Logitech Gamepad F710", 0, XTYPE_XBOX360 },
@@ -205,13 +206,13 @@ static const struct xpad_device {
{ 0x0738, 0x9871, "Mad Catz Portable Drum", 0, XTYPE_XBOX360 },
{ 0x0738, 0xb726, "Mad Catz Xbox controller - MW2", 0, XTYPE_XBOX360 },
{ 0x0738, 0xb738, "Mad Catz MVC2TE Stick 2", MAP_TRIGGERS_TO_BUTTONS, XTYPE_XBOX360 },
- { 0x0738, 0xbeef, "Mad Catz JOYTECH NEO SE Advanced GamePad", XTYPE_XBOX360 },
+ { 0x0738, 0xbeef, "Mad Catz JOYTECH NEO SE Advanced GamePad", 0, XTYPE_XBOX360 },
{ 0x0738, 0xcb02, "Saitek Cyborg Rumble Pad - PC/Xbox 360", 0, XTYPE_XBOX360 },
{ 0x0738, 0xcb03, "Saitek P3200 Rumble Pad - PC/Xbox 360", 0, XTYPE_XBOX360 },
{ 0x0738, 0xcb29, "Saitek Aviator Stick AV8R02", 0, XTYPE_XBOX360 },
{ 0x0738, 0xf738, "Super SFIV FightStick TE S", 0, XTYPE_XBOX360 },
{ 0x07ff, 0xffff, "Mad Catz GamePad", 0, XTYPE_XBOX360 },
- { 0x0b05, 0x1a38, "ASUS ROG RAIKIRI", 0, XTYPE_XBOXONE },
+ { 0x0b05, 0x1a38, "ASUS ROG RAIKIRI", MAP_SHARE_BUTTON, XTYPE_XBOXONE },
{ 0x0b05, 0x1abb, "ASUS ROG RAIKIRI PRO", 0, XTYPE_XBOXONE },
{ 0x0c12, 0x0005, "Intec wireless", 0, XTYPE_XBOX },
{ 0x0c12, 0x8801, "Nyko Xbox Controller", 0, XTYPE_XBOX },
@@ -240,7 +241,7 @@ static const struct xpad_device {
{ 0x0e6f, 0x0146, "Rock Candy Wired Controller for Xbox One", 0, XTYPE_XBOXONE },
{ 0x0e6f, 0x0147, "PDP Marvel Xbox One Controller", 0, XTYPE_XBOXONE },
{ 0x0e6f, 0x015c, "PDP Xbox One Arcade Stick", MAP_TRIGGERS_TO_BUTTONS, XTYPE_XBOXONE },
- { 0x0e6f, 0x015d, "PDP Mirror's Edge Official Wired Controller for Xbox One", XTYPE_XBOXONE },
+ { 0x0e6f, 0x015d, "PDP Mirror's Edge Official Wired Controller for Xbox One", 0, XTYPE_XBOXONE },
{ 0x0e6f, 0x0161, "PDP Xbox One Controller", 0, XTYPE_XBOXONE },
{ 0x0e6f, 0x0162, "PDP Xbox One Controller", 0, XTYPE_XBOXONE },
{ 0x0e6f, 0x0163, "PDP Xbox One Controller", 0, XTYPE_XBOXONE },
@@ -281,6 +282,7 @@ static const struct xpad_device {
{ 0x0f0d, 0x00dc, "HORIPAD FPS for Nintendo Switch", MAP_TRIGGERS_TO_BUTTONS, XTYPE_XBOX360 },
{ 0x0f0d, 0x0151, "Hori Racing Wheel Overdrive for Xbox Series X", 0, XTYPE_XBOXONE },
{ 0x0f0d, 0x0152, "Hori Racing Wheel Overdrive for Xbox Series X", 0, XTYPE_XBOXONE },
+ { 0x0f0d, 0x01b2, "HORI Taiko No Tatsujin Drum Controller", MAP_SHARE_BUTTON, XTYPE_XBOXONE },
{ 0x0f30, 0x010b, "Philips Recoil", 0, XTYPE_XBOX },
{ 0x0f30, 0x0202, "Joytech Advanced Controller", 0, XTYPE_XBOX },
{ 0x0f30, 0x8888, "BigBen XBMiniPad Controller", 0, XTYPE_XBOX },
@@ -353,6 +355,8 @@ static const struct xpad_device {
{ 0x20d6, 0x2001, "BDA Xbox Series X Wired Controller", 0, XTYPE_XBOXONE },
{ 0x20d6, 0x2009, "PowerA Enhanced Wired Controller for Xbox Series X|S", 0, XTYPE_XBOXONE },
{ 0x20d6, 0x281f, "PowerA Wired Controller For Xbox 360", 0, XTYPE_XBOX360 },
+ { 0x20d6, 0x400b, "PowerA FUSION Pro 4 Wired Controller", MAP_SHARE_BUTTON, XTYPE_XBOXONE },
+ { 0x20d6, 0x890b, "PowerA MOGA XP-Ultra Controller", MAP_SHARE_BUTTON, XTYPE_XBOXONE },
{ 0x2345, 0xe00b, "Machenike G5 Pro Controller", 0, XTYPE_XBOX360 },
{ 0x24c6, 0x5000, "Razer Atrox Arcade Stick", MAP_TRIGGERS_TO_BUTTONS, XTYPE_XBOX360 },
{ 0x24c6, 0x5300, "PowerA MINI PROEX Controller", 0, XTYPE_XBOX360 },
@@ -384,13 +388,16 @@ static const struct xpad_device {
{ 0x294b, 0x3404, "Snakebyte GAMEPAD RGB X", 0, XTYPE_XBOXONE },
{ 0x2993, 0x2001, "TECNO Pocket Go", 0, XTYPE_XBOX360 },
{ 0x2dc8, 0x2000, "8BitDo Pro 2 Wired Controller fox Xbox", 0, XTYPE_XBOXONE },
+ { 0x2dc8, 0x200f, "8BitDo Ultimate 3-mode Controller for Xbox", MAP_SHARE_BUTTON, XTYPE_XBOXONE },
{ 0x2dc8, 0x3106, "8BitDo Ultimate Wireless / Pro 2 Wired Controller", 0, XTYPE_XBOX360 },
{ 0x2dc8, 0x3109, "8BitDo Ultimate Wireless Bluetooth", 0, XTYPE_XBOX360 },
{ 0x2dc8, 0x310a, "8BitDo Ultimate 2C Wireless Controller", 0, XTYPE_XBOX360 },
+ { 0x2dc8, 0x310b, "8BitDo Ultimate 2 Wireless Controller", 0, XTYPE_XBOX360 },
{ 0x2dc8, 0x6001, "8BitDo SN30 Pro", 0, XTYPE_XBOX360 },
+ { 0x2e24, 0x0423, "Hyperkin DuchesS Xbox One pad", MAP_SHARE_BUTTON, XTYPE_XBOXONE },
{ 0x2e24, 0x0652, "Hyperkin Duke X-Box One pad", 0, XTYPE_XBOXONE },
{ 0x2e24, 0x1688, "Hyperkin X91 X-Box One pad", 0, XTYPE_XBOXONE },
- { 0x2e95, 0x0504, "SCUF Gaming Controller", MAP_SELECT_BUTTON, XTYPE_XBOXONE },
+ { 0x2e95, 0x0504, "SCUF Gaming Controller", MAP_SHARE_BUTTON, XTYPE_XBOXONE },
{ 0x31e3, 0x1100, "Wooting One", 0, XTYPE_XBOX360 },
{ 0x31e3, 0x1200, "Wooting Two", 0, XTYPE_XBOX360 },
{ 0x31e3, 0x1210, "Wooting Lekker", 0, XTYPE_XBOX360 },
@@ -714,8 +721,10 @@ static const struct xboxone_init_packet xboxone_init_packets[] = {
XBOXONE_INIT_PKT(0x045e, 0x0b00, xboxone_s_init),
XBOXONE_INIT_PKT(0x045e, 0x0b00, extra_input_packet_init),
XBOXONE_INIT_PKT(0x0e6f, 0x0000, xboxone_pdp_led_on),
+ XBOXONE_INIT_PKT(0x0f0d, 0x01b2, xboxone_pdp_led_on),
XBOXONE_INIT_PKT(0x20d6, 0xa01a, xboxone_pdp_led_on),
XBOXONE_INIT_PKT(0x0e6f, 0x0000, xboxone_pdp_auth),
+ XBOXONE_INIT_PKT(0x0f0d, 0x01b2, xboxone_pdp_auth),
XBOXONE_INIT_PKT(0x20d6, 0xa01a, xboxone_pdp_auth),
XBOXONE_INIT_PKT(0x24c6, 0x541a, xboxone_rumblebegin_init),
XBOXONE_INIT_PKT(0x24c6, 0x542a, xboxone_rumblebegin_init),
@@ -1027,7 +1036,7 @@ static void xpad360w_process_packet(struct usb_xpad *xpad, u16 cmd, unsigned cha
* The report format was gleaned from
* https://github.com/kylelemons/xbox/blob/master/xbox.go
*/
-static void xpadone_process_packet(struct usb_xpad *xpad, u16 cmd, unsigned char *data)
+static void xpadone_process_packet(struct usb_xpad *xpad, u16 cmd, unsigned char *data, u32 len)
{
struct input_dev *dev = xpad->dev;
bool do_sync = false;
@@ -1068,8 +1077,12 @@ static void xpadone_process_packet(struct usb_xpad *xpad, u16 cmd, unsigned char
/* menu/view buttons */
input_report_key(dev, BTN_START, data[4] & BIT(2));
input_report_key(dev, BTN_SELECT, data[4] & BIT(3));
- if (xpad->mapping & MAP_SELECT_BUTTON)
- input_report_key(dev, KEY_RECORD, data[22] & BIT(0));
+ if (xpad->mapping & MAP_SHARE_BUTTON) {
+ if (xpad->mapping & MAP_SHARE_OFFSET)
+ input_report_key(dev, KEY_RECORD, data[len - 26] & BIT(0));
+ else
+ input_report_key(dev, KEY_RECORD, data[len - 18] & BIT(0));
+ }
/* buttons A,B,X,Y */
input_report_key(dev, BTN_A, data[4] & BIT(4));
@@ -1217,7 +1230,7 @@ static void xpad_irq_in(struct urb *urb)
xpad360w_process_packet(xpad, 0, xpad->idata);
break;
case XTYPE_XBOXONE:
- xpadone_process_packet(xpad, 0, xpad->idata);
+ xpadone_process_packet(xpad, 0, xpad->idata, urb->actual_length);
break;
default:
xpad_process_packet(xpad, 0, xpad->idata);
@@ -1944,7 +1957,7 @@ static int xpad_init_input(struct usb_xpad *xpad)
xpad->xtype == XTYPE_XBOXONE) {
for (i = 0; xpad360_btn[i] >= 0; i++)
input_set_capability(input_dev, EV_KEY, xpad360_btn[i]);
- if (xpad->mapping & MAP_SELECT_BUTTON)
+ if (xpad->mapping & MAP_SHARE_BUTTON)
input_set_capability(input_dev, EV_KEY, KEY_RECORD);
} else {
for (i = 0; xpad_btn[i] >= 0; i++)
diff --git a/drivers/input/keyboard/mtk-pmic-keys.c b/drivers/input/keyboard/mtk-pmic-keys.c
index 5ad6be914160..061d48350df6 100644
--- a/drivers/input/keyboard/mtk-pmic-keys.c
+++ b/drivers/input/keyboard/mtk-pmic-keys.c
@@ -147,8 +147,8 @@ static void mtk_pmic_keys_lp_reset_setup(struct mtk_pmic_keys *keys,
u32 value, mask;
int error;
- kregs_home = keys->keys[MTK_PMIC_HOMEKEY_INDEX].regs;
- kregs_pwr = keys->keys[MTK_PMIC_PWRKEY_INDEX].regs;
+ kregs_home = &regs->keys_regs[MTK_PMIC_HOMEKEY_INDEX];
+ kregs_pwr = &regs->keys_regs[MTK_PMIC_PWRKEY_INDEX];
error = of_property_read_u32(keys->dev->of_node, "power-off-time-sec",
&long_press_debounce);
diff --git a/drivers/input/misc/hisi_powerkey.c b/drivers/input/misc/hisi_powerkey.c
index d3c293a95d32..d315017324d9 100644
--- a/drivers/input/misc/hisi_powerkey.c
+++ b/drivers/input/misc/hisi_powerkey.c
@@ -30,7 +30,7 @@ static irqreturn_t hi65xx_power_press_isr(int irq, void *q)
{
struct input_dev *input = q;
- pm_wakeup_event(input->dev.parent, MAX_HELD_TIME);
+ pm_wakeup_dev_event(input->dev.parent, MAX_HELD_TIME, true);
input_report_key(input, KEY_POWER, 1);
input_sync(input);
diff --git a/drivers/input/misc/sparcspkr.c b/drivers/input/misc/sparcspkr.c
index 8d7303fc13bc..1cfadd73829f 100644
--- a/drivers/input/misc/sparcspkr.c
+++ b/drivers/input/misc/sparcspkr.c
@@ -74,9 +74,14 @@ static int bbc_spkr_event(struct input_dev *dev, unsigned int type, unsigned int
return -1;
switch (code) {
- case SND_BELL: if (value) value = 1000;
- case SND_TONE: break;
- default: return -1;
+ case SND_BELL:
+ if (value)
+ value = 1000;
+ break;
+ case SND_TONE:
+ break;
+ default:
+ return -1;
}
if (value > 20 && value < 32767)
@@ -109,9 +114,14 @@ static int grover_spkr_event(struct input_dev *dev, unsigned int type, unsigned
return -1;
switch (code) {
- case SND_BELL: if (value) value = 1000;
- case SND_TONE: break;
- default: return -1;
+ case SND_BELL:
+ if (value)
+ value = 1000;
+ break;
+ case SND_TONE:
+ break;
+ default:
+ return -1;
}
if (value > 20 && value < 32767)
diff --git a/drivers/input/mouse/synaptics.c b/drivers/input/mouse/synaptics.c
index 309c360aab55..c5c88a75a019 100644
--- a/drivers/input/mouse/synaptics.c
+++ b/drivers/input/mouse/synaptics.c
@@ -164,6 +164,7 @@ static const char * const topbuttonpad_pnp_ids[] = {
#ifdef CONFIG_MOUSE_PS2_SYNAPTICS_SMBUS
static const char * const smbus_pnp_ids[] = {
/* all of the topbuttonpad_pnp_ids are valid, we just add some extras */
+ "DLL060d", /* Dell Precision M3800 */
"LEN0048", /* X1 Carbon 3 */
"LEN0046", /* X250 */
"LEN0049", /* Yoga 11e */
@@ -190,11 +191,15 @@ static const char * const smbus_pnp_ids[] = {
"LEN2054", /* E480 */
"LEN2055", /* E580 */
"LEN2068", /* T14 Gen 1 */
+ "SYN1221", /* TUXEDO InfinityBook Pro 14 v5 */
+ "SYN3003", /* HP EliteBook 850 G1 */
"SYN3015", /* HP EliteBook 840 G2 */
"SYN3052", /* HP EliteBook 840 G4 */
"SYN3221", /* HP 15-ay000 */
"SYN323d", /* HP Spectre X360 13-w013dx */
"SYN3257", /* HP Envy 13-ad105ng */
+ "TOS01f6", /* Dynabook Portege X30L-G */
+ "TOS0213", /* Dynabook Portege X30-D */
NULL
};
#endif
diff --git a/drivers/input/touchscreen/cyttsp5.c b/drivers/input/touchscreen/cyttsp5.c
index eafe5a9b8964..071b7c9bf566 100644
--- a/drivers/input/touchscreen/cyttsp5.c
+++ b/drivers/input/touchscreen/cyttsp5.c
@@ -580,7 +580,7 @@ static int cyttsp5_power_control(struct cyttsp5 *ts, bool on)
int rc;
SET_CMD_REPORT_TYPE(cmd[0], 0);
- SET_CMD_REPORT_ID(cmd[0], HID_POWER_SLEEP);
+ SET_CMD_REPORT_ID(cmd[0], state);
SET_CMD_OPCODE(cmd[1], HID_CMD_SET_POWER);
rc = cyttsp5_write(ts, HID_COMMAND_REG, cmd, sizeof(cmd));
@@ -870,13 +870,16 @@ static int cyttsp5_probe(struct device *dev, struct regmap *regmap, int irq,
ts->input->phys = ts->phys;
input_set_drvdata(ts->input, ts);
- /* Reset the gpio to be in a reset state */
+ /* Assert gpio to be in a reset state */
ts->reset_gpio = devm_gpiod_get_optional(dev, "reset", GPIOD_OUT_HIGH);
if (IS_ERR(ts->reset_gpio)) {
error = PTR_ERR(ts->reset_gpio);
dev_err(dev, "Failed to request reset gpio, error %d\n", error);
return error;
}
+
+ fsleep(10); /* Ensure long-enough reset pulse (minimum 10us). */
+
gpiod_set_value_cansleep(ts->reset_gpio, 0);
/* Need a delay to have device up */
diff --git a/drivers/input/touchscreen/stmpe-ts.c b/drivers/input/touchscreen/stmpe-ts.c
index a94a1997f96b..af0fb38bcfdc 100644
--- a/drivers/input/touchscreen/stmpe-ts.c
+++ b/drivers/input/touchscreen/stmpe-ts.c
@@ -366,12 +366,7 @@ static struct platform_driver stmpe_ts_driver = {
};
module_platform_driver(stmpe_ts_driver);
-static const struct of_device_id stmpe_ts_ids[] = {
- { .compatible = "st,stmpe-ts", },
- { },
-};
-MODULE_DEVICE_TABLE(of, stmpe_ts_ids);
-
+MODULE_ALIAS("platform:stmpe-ts");
MODULE_AUTHOR("Luotao Fu <l.fu@pengutronix.de>");
MODULE_DESCRIPTION("STMPEXXX touchscreen driver");
MODULE_LICENSE("GPL");
diff --git a/fs/nilfs2/the_nilfs.c b/fs/nilfs2/the_nilfs.c
index cb01ea81724d..d0bcf744c553 100644
--- a/fs/nilfs2/the_nilfs.c
+++ b/fs/nilfs2/the_nilfs.c
@@ -705,8 +705,6 @@ int init_nilfs(struct the_nilfs *nilfs, struct super_block *sb)
int blocksize;
int err;
- down_write(&nilfs->ns_sem);
-
blocksize = sb_min_blocksize(sb, NILFS_MIN_BLOCK_SIZE);
if (!blocksize) {
nilfs_err(sb, "unable to set blocksize");
@@ -779,7 +777,6 @@ int init_nilfs(struct the_nilfs *nilfs, struct super_block *sb)
set_nilfs_init(nilfs);
err = 0;
out:
- up_write(&nilfs->ns_sem);
return err;
failed_sbh:
diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c
index b8ac85b548c7..821cb7874685 100644
--- a/fs/ocfs2/alloc.c
+++ b/fs/ocfs2/alloc.c
@@ -6918,6 +6918,7 @@ static int ocfs2_grab_folios(struct inode *inode, loff_t start, loff_t end,
if (IS_ERR(folios[numfolios])) {
ret = PTR_ERR(folios[numfolios]);
mlog_errno(ret);
+ folios[numfolios] = NULL;
goto out;
}
diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c
index c7a9729dc9d0..e5f58ff2175f 100644
--- a/fs/ocfs2/journal.c
+++ b/fs/ocfs2/journal.c
@@ -174,7 +174,7 @@ int ocfs2_recovery_init(struct ocfs2_super *osb)
struct ocfs2_recovery_map *rm;
mutex_init(&osb->recovery_lock);
- osb->disable_recovery = 0;
+ osb->recovery_state = OCFS2_REC_ENABLED;
osb->recovery_thread_task = NULL;
init_waitqueue_head(&osb->recovery_event);
@@ -190,31 +190,53 @@ int ocfs2_recovery_init(struct ocfs2_super *osb)
return 0;
}
-/* we can't grab the goofy sem lock from inside wait_event, so we use
- * memory barriers to make sure that we'll see the null task before
- * being woken up */
static int ocfs2_recovery_thread_running(struct ocfs2_super *osb)
{
- mb();
return osb->recovery_thread_task != NULL;
}
-void ocfs2_recovery_exit(struct ocfs2_super *osb)
+static void ocfs2_recovery_disable(struct ocfs2_super *osb,
+ enum ocfs2_recovery_state state)
{
- struct ocfs2_recovery_map *rm;
-
- /* disable any new recovery threads and wait for any currently
- * running ones to exit. Do this before setting the vol_state. */
mutex_lock(&osb->recovery_lock);
- osb->disable_recovery = 1;
+ /*
+ * If recovery thread is not running, we can directly transition to
+ * final state.
+ */
+ if (!ocfs2_recovery_thread_running(osb)) {
+ osb->recovery_state = state + 1;
+ goto out_lock;
+ }
+ osb->recovery_state = state;
+ /* Wait for recovery thread to acknowledge state transition */
+ wait_event_cmd(osb->recovery_event,
+ !ocfs2_recovery_thread_running(osb) ||
+ osb->recovery_state >= state + 1,
+ mutex_unlock(&osb->recovery_lock),
+ mutex_lock(&osb->recovery_lock));
+out_lock:
mutex_unlock(&osb->recovery_lock);
- wait_event(osb->recovery_event, !ocfs2_recovery_thread_running(osb));
- /* At this point, we know that no more recovery threads can be
- * launched, so wait for any recovery completion work to
- * complete. */
+ /*
+ * At this point we know that no more recovery work can be queued so
+ * wait for any recovery completion work to complete.
+ */
if (osb->ocfs2_wq)
flush_workqueue(osb->ocfs2_wq);
+}
+
+void ocfs2_recovery_disable_quota(struct ocfs2_super *osb)
+{
+ ocfs2_recovery_disable(osb, OCFS2_REC_QUOTA_WANT_DISABLE);
+}
+
+void ocfs2_recovery_exit(struct ocfs2_super *osb)
+{
+ struct ocfs2_recovery_map *rm;
+
+ /* disable any new recovery threads and wait for any currently
+ * running ones to exit. Do this before setting the vol_state. */
+ ocfs2_recovery_disable(osb, OCFS2_REC_WANT_DISABLE);
/*
* Now that recovery is shut down, and the osb is about to be
@@ -1472,6 +1494,18 @@ static int __ocfs2_recovery_thread(void *arg)
}
}
restart:
+ if (quota_enabled) {
+ mutex_lock(&osb->recovery_lock);
+ /* Confirm that recovery thread will no longer recover quotas */
+ if (osb->recovery_state == OCFS2_REC_QUOTA_WANT_DISABLE) {
+ osb->recovery_state = OCFS2_REC_QUOTA_DISABLED;
+ wake_up(&osb->recovery_event);
+ }
+ if (osb->recovery_state >= OCFS2_REC_QUOTA_DISABLED)
+ quota_enabled = 0;
+ mutex_unlock(&osb->recovery_lock);
+ }
+
status = ocfs2_super_lock(osb, 1);
if (status < 0) {
mlog_errno(status);
@@ -1569,27 +1603,29 @@ bail:
ocfs2_free_replay_slots(osb);
osb->recovery_thread_task = NULL;
- mb(); /* sync with ocfs2_recovery_thread_running */
+ if (osb->recovery_state == OCFS2_REC_WANT_DISABLE)
+ osb->recovery_state = OCFS2_REC_DISABLED;
wake_up(&osb->recovery_event);
mutex_unlock(&osb->recovery_lock);
- if (quota_enabled)
- kfree(rm_quota);
+ kfree(rm_quota);
return status;
}
void ocfs2_recovery_thread(struct ocfs2_super *osb, int node_num)
{
+ int was_set = -1;
+
mutex_lock(&osb->recovery_lock);
+ if (osb->recovery_state < OCFS2_REC_WANT_DISABLE)
+ was_set = ocfs2_recovery_map_set(osb, node_num);
trace_ocfs2_recovery_thread(node_num, osb->node_num,
- osb->disable_recovery, osb->recovery_thread_task,
- osb->disable_recovery ?
- -1 : ocfs2_recovery_map_set(osb, node_num));
+ osb->recovery_state, osb->recovery_thread_task, was_set);
- if (osb->disable_recovery)
+ if (osb->recovery_state >= OCFS2_REC_WANT_DISABLE)
goto out;
if (osb->recovery_thread_task)
diff --git a/fs/ocfs2/journal.h b/fs/ocfs2/journal.h
index e3c3a35dc5e0..6397170f302f 100644
--- a/fs/ocfs2/journal.h
+++ b/fs/ocfs2/journal.h
@@ -148,6 +148,7 @@ void ocfs2_wait_for_recovery(struct ocfs2_super *osb);
int ocfs2_recovery_init(struct ocfs2_super *osb);
void ocfs2_recovery_exit(struct ocfs2_super *osb);
+void ocfs2_recovery_disable_quota(struct ocfs2_super *osb);
int ocfs2_compute_replay_slots(struct ocfs2_super *osb);
void ocfs2_free_replay_slots(struct ocfs2_super *osb);
diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h
index 51c52768132d..6aaa94c554c1 100644
--- a/fs/ocfs2/ocfs2.h
+++ b/fs/ocfs2/ocfs2.h
@@ -308,6 +308,21 @@ enum ocfs2_journal_trigger_type {
void ocfs2_initialize_journal_triggers(struct super_block *sb,
struct ocfs2_triggers triggers[]);
+enum ocfs2_recovery_state {
+ OCFS2_REC_ENABLED = 0,
+ OCFS2_REC_QUOTA_WANT_DISABLE,
+ /*
+ * Must be OCFS2_REC_QUOTA_WANT_DISABLE + 1 for
+ * ocfs2_recovery_disable_quota() to work.
+ */
+ OCFS2_REC_QUOTA_DISABLED,
+ OCFS2_REC_WANT_DISABLE,
+ /*
+ * Must be OCFS2_REC_WANT_DISABLE + 1 for ocfs2_recovery_exit() to work
+ */
+ OCFS2_REC_DISABLED,
+};
+
struct ocfs2_journal;
struct ocfs2_slot_info;
struct ocfs2_recovery_map;
@@ -370,7 +385,7 @@ struct ocfs2_super
struct ocfs2_recovery_map *recovery_map;
struct ocfs2_replay_map *replay_map;
struct task_struct *recovery_thread_task;
- int disable_recovery;
+ enum ocfs2_recovery_state recovery_state;
wait_queue_head_t checkpoint_event;
struct ocfs2_journal *journal;
unsigned long osb_commit_interval;
diff --git a/fs/ocfs2/quota_local.c b/fs/ocfs2/quota_local.c
index 2956d888c131..e272429da3db 100644
--- a/fs/ocfs2/quota_local.c
+++ b/fs/ocfs2/quota_local.c
@@ -453,8 +453,7 @@ out:
/* Sync changes in local quota file into global quota file and
* reinitialize local quota file.
- * The function expects local quota file to be already locked and
- * s_umount locked in shared mode. */
+ * The function expects local quota file to be already locked. */
static int ocfs2_recover_local_quota_file(struct inode *lqinode,
int type,
struct ocfs2_quota_recovery *rec)
@@ -588,7 +587,6 @@ int ocfs2_finish_quota_recovery(struct ocfs2_super *osb,
{
unsigned int ino[OCFS2_MAXQUOTAS] = { LOCAL_USER_QUOTA_SYSTEM_INODE,
LOCAL_GROUP_QUOTA_SYSTEM_INODE };
- struct super_block *sb = osb->sb;
struct ocfs2_local_disk_dqinfo *ldinfo;
struct buffer_head *bh;
handle_t *handle;
@@ -600,7 +598,6 @@ int ocfs2_finish_quota_recovery(struct ocfs2_super *osb,
printk(KERN_NOTICE "ocfs2: Finishing quota recovery on device (%s) for "
"slot %u\n", osb->dev_str, slot_num);
- down_read(&sb->s_umount);
for (type = 0; type < OCFS2_MAXQUOTAS; type++) {
if (list_empty(&(rec->r_list[type])))
continue;
@@ -677,7 +674,6 @@ out_put:
break;
}
out:
- up_read(&sb->s_umount);
kfree(rec);
return status;
}
@@ -843,8 +839,7 @@ static int ocfs2_local_free_info(struct super_block *sb, int type)
ocfs2_release_local_quota_bitmaps(&oinfo->dqi_chunk);
/*
- * s_umount held in exclusive mode protects us against racing with
- * recovery thread...
+ * ocfs2_dismount_volume() has already aborted quota recovery...
*/
if (oinfo->dqi_rec) {
ocfs2_free_quota_recovery(oinfo->dqi_rec);
diff --git a/fs/ocfs2/suballoc.c b/fs/ocfs2/suballoc.c
index f7b483f0de2a..6ac4dcd54588 100644
--- a/fs/ocfs2/suballoc.c
+++ b/fs/ocfs2/suballoc.c
@@ -698,10 +698,12 @@ static int ocfs2_block_group_alloc(struct ocfs2_super *osb,
bg_bh = ocfs2_block_group_alloc_contig(osb, handle, alloc_inode,
ac, cl);
- if (PTR_ERR(bg_bh) == -ENOSPC)
+ if (PTR_ERR(bg_bh) == -ENOSPC) {
+ ac->ac_which = OCFS2_AC_USE_MAIN_DISCONTIG;
bg_bh = ocfs2_block_group_alloc_discontig(handle,
alloc_inode,
ac, cl);
+ }
if (IS_ERR(bg_bh)) {
status = PTR_ERR(bg_bh);
bg_bh = NULL;
@@ -1794,6 +1796,7 @@ static int ocfs2_search_chain(struct ocfs2_alloc_context *ac,
{
int status;
u16 chain;
+ u32 contig_bits;
u64 next_group;
struct inode *alloc_inode = ac->ac_inode;
struct buffer_head *group_bh = NULL;
@@ -1819,10 +1822,21 @@ static int ocfs2_search_chain(struct ocfs2_alloc_context *ac,
status = -ENOSPC;
/* for now, the chain search is a bit simplistic. We just use
* the 1st group with any empty bits. */
- while ((status = ac->ac_group_search(alloc_inode, group_bh,
- bits_wanted, min_bits,
- ac->ac_max_block,
- res)) == -ENOSPC) {
+ while (1) {
+ if (ac->ac_which == OCFS2_AC_USE_MAIN_DISCONTIG) {
+ contig_bits = le16_to_cpu(bg->bg_contig_free_bits);
+ if (!contig_bits)
+ contig_bits = ocfs2_find_max_contig_free_bits(bg->bg_bitmap,
+ le16_to_cpu(bg->bg_bits), 0);
+ if (bits_wanted > contig_bits && contig_bits >= min_bits)
+ bits_wanted = contig_bits;
+ }
+
+ status = ac->ac_group_search(alloc_inode, group_bh,
+ bits_wanted, min_bits,
+ ac->ac_max_block, res);
+ if (status != -ENOSPC)
+ break;
if (!bg->bg_next_group)
break;
@@ -1982,6 +1996,7 @@ static int ocfs2_claim_suballoc_bits(struct ocfs2_alloc_context *ac,
victim = ocfs2_find_victim_chain(cl);
ac->ac_chain = victim;
+search:
status = ocfs2_search_chain(ac, handle, bits_wanted, min_bits,
res, &bits_left);
if (!status) {
@@ -2022,6 +2037,16 @@ static int ocfs2_claim_suballoc_bits(struct ocfs2_alloc_context *ac,
}
}
+ /* Chains can't supply the bits_wanted contiguous space.
+ * We should switch to using every single bit when allocating
+ * from the global bitmap. */
+ if (i == le16_to_cpu(cl->cl_next_free_rec) &&
+ status == -ENOSPC && ac->ac_which == OCFS2_AC_USE_MAIN) {
+ ac->ac_which = OCFS2_AC_USE_MAIN_DISCONTIG;
+ ac->ac_chain = victim;
+ goto search;
+ }
+
set_hint:
if (status != -ENOSPC) {
/* If the next search of this group is not likely to
@@ -2365,7 +2390,8 @@ int __ocfs2_claim_clusters(handle_t *handle,
BUG_ON(ac->ac_bits_given >= ac->ac_bits_wanted);
BUG_ON(ac->ac_which != OCFS2_AC_USE_LOCAL
- && ac->ac_which != OCFS2_AC_USE_MAIN);
+ && ac->ac_which != OCFS2_AC_USE_MAIN
+ && ac->ac_which != OCFS2_AC_USE_MAIN_DISCONTIG);
if (ac->ac_which == OCFS2_AC_USE_LOCAL) {
WARN_ON(min_clusters > 1);
diff --git a/fs/ocfs2/suballoc.h b/fs/ocfs2/suballoc.h
index b481b834857d..bcf2ed4a8631 100644
--- a/fs/ocfs2/suballoc.h
+++ b/fs/ocfs2/suballoc.h
@@ -29,6 +29,7 @@ struct ocfs2_alloc_context {
#define OCFS2_AC_USE_MAIN 2
#define OCFS2_AC_USE_INODE 3
#define OCFS2_AC_USE_META 4
+#define OCFS2_AC_USE_MAIN_DISCONTIG 5
u32 ac_which;
/* these are used by the chain search */
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index 8bb5022f3082..3d2533950bae 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -1812,6 +1812,9 @@ static void ocfs2_dismount_volume(struct super_block *sb, int mnt_err)
/* Orphan scan should be stopped as early as possible */
ocfs2_orphan_scan_stop(osb);
+ /* Stop quota recovery so that we can disable quotas */
+ ocfs2_recovery_disable_quota(osb);
+
ocfs2_disable_quotas(osb);
/* All dquots should be freed by now */
diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index d80f94346199..22f4bf956ba1 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -1585,8 +1585,11 @@ static int userfaultfd_copy(struct userfaultfd_ctx *ctx,
user_uffdio_copy = (struct uffdio_copy __user *) arg;
ret = -EAGAIN;
- if (atomic_read(&ctx->mmap_changing))
+ if (unlikely(atomic_read(&ctx->mmap_changing))) {
+ if (unlikely(put_user(ret, &user_uffdio_copy->copy)))
+ return -EFAULT;
goto out;
+ }
ret = -EFAULT;
if (copy_from_user(&uffdio_copy, user_uffdio_copy,
@@ -1641,8 +1644,11 @@ static int userfaultfd_zeropage(struct userfaultfd_ctx *ctx,
user_uffdio_zeropage = (struct uffdio_zeropage __user *) arg;
ret = -EAGAIN;
- if (atomic_read(&ctx->mmap_changing))
+ if (unlikely(atomic_read(&ctx->mmap_changing))) {
+ if (unlikely(put_user(ret, &user_uffdio_zeropage->zeropage)))
+ return -EFAULT;
goto out;
+ }
ret = -EFAULT;
if (copy_from_user(&uffdio_zeropage, user_uffdio_zeropage,
@@ -1744,8 +1750,11 @@ static int userfaultfd_continue(struct userfaultfd_ctx *ctx, unsigned long arg)
user_uffdio_continue = (struct uffdio_continue __user *)arg;
ret = -EAGAIN;
- if (atomic_read(&ctx->mmap_changing))
+ if (unlikely(atomic_read(&ctx->mmap_changing))) {
+ if (unlikely(put_user(ret, &user_uffdio_continue->mapped)))
+ return -EFAULT;
goto out;
+ }
ret = -EFAULT;
if (copy_from_user(&uffdio_continue, user_uffdio_continue,
@@ -1801,8 +1810,11 @@ static inline int userfaultfd_poison(struct userfaultfd_ctx *ctx, unsigned long
user_uffdio_poison = (struct uffdio_poison __user *)arg;
ret = -EAGAIN;
- if (atomic_read(&ctx->mmap_changing))
+ if (unlikely(atomic_read(&ctx->mmap_changing))) {
+ if (unlikely(put_user(ret, &user_uffdio_poison->updated)))
+ return -EFAULT;
goto out;
+ }
ret = -EFAULT;
if (copy_from_user(&uffdio_poison, user_uffdio_poison,
@@ -1870,8 +1882,12 @@ static int userfaultfd_move(struct userfaultfd_ctx *ctx,
user_uffdio_move = (struct uffdio_move __user *) arg;
- if (atomic_read(&ctx->mmap_changing))
- return -EAGAIN;
+ ret = -EAGAIN;
+ if (unlikely(atomic_read(&ctx->mmap_changing))) {
+ if (unlikely(put_user(ret, &user_uffdio_move->move)))
+ return -EFAULT;
+ goto out;
+ }
if (copy_from_user(&uffdio_move, user_uffdio_move,
/* don't copy "move" last field */
diff --git a/include/linux/timekeeper_internal.h b/include/linux/timekeeper_internal.h
index e39d4d563b19..785048a3b3e6 100644
--- a/include/linux/timekeeper_internal.h
+++ b/include/linux/timekeeper_internal.h
@@ -51,7 +51,7 @@ struct tk_read_base {
* @offs_real: Offset clock monotonic -> clock realtime
* @offs_boot: Offset clock monotonic -> clock boottime
* @offs_tai: Offset clock monotonic -> clock tai
- * @tai_offset: The current UTC to TAI offset in seconds
+ * @coarse_nsec: The nanoseconds part for coarse time getters
* @tkr_raw: The readout base structure for CLOCK_MONOTONIC_RAW
* @raw_sec: CLOCK_MONOTONIC_RAW time in seconds
* @clock_was_set_seq: The sequence number of clock was set events
@@ -76,6 +76,7 @@ struct tk_read_base {
* ntp shifted nano seconds.
* @ntp_err_mult: Multiplication factor for scaled math conversion
* @skip_second_overflow: Flag used to avoid updating NTP twice with same second
+ * @tai_offset: The current UTC to TAI offset in seconds
*
* Note: For timespec(64) based interfaces wall_to_monotonic is what
* we need to add to xtime (or xtime corrected for sub jiffy times)
@@ -100,7 +101,7 @@ struct tk_read_base {
* which results in the following cacheline layout:
*
* 0: seqcount, tkr_mono
- * 1: xtime_sec ... tai_offset
+ * 1: xtime_sec ... coarse_nsec
* 2: tkr_raw, raw_sec
* 3,4: Internal variables
*
@@ -121,7 +122,7 @@ struct timekeeper {
ktime_t offs_real;
ktime_t offs_boot;
ktime_t offs_tai;
- s32 tai_offset;
+ u32 coarse_nsec;
/* Cacheline 2: */
struct tk_read_base tkr_raw;
@@ -144,6 +145,7 @@ struct timekeeper {
u32 ntp_error_shift;
u32 ntp_err_mult;
u32 skip_second_overflow;
+ s32 tai_offset;
};
#ifdef CONFIG_GENERIC_TIME_VSYSCALL
diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h
index 31e9ffd936e3..5ca8d4dd149d 100644
--- a/include/linux/vmalloc.h
+++ b/include/linux/vmalloc.h
@@ -61,6 +61,7 @@ struct vm_struct {
unsigned int nr_pages;
phys_addr_t phys_addr;
const void *caller;
+ unsigned long requested_size;
};
struct vmap_area {
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 1e67d076f195..a009c91f7b05 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -164,10 +164,34 @@ static inline struct timespec64 tk_xtime(const struct timekeeper *tk)
return ts;
}
+static inline struct timespec64 tk_xtime_coarse(const struct timekeeper *tk)
+{
+ struct timespec64 ts;
+
+ ts.tv_sec = tk->xtime_sec;
+ ts.tv_nsec = tk->coarse_nsec;
+ return ts;
+}
+
+/*
+ * Update the nanoseconds part for the coarse time keepers. They can't rely
+ * on xtime_nsec because xtime_nsec could be adjusted by a small negative
+ * amount when the multiplication factor of the clock is adjusted, which
+ * could cause the coarse clocks to go slightly backwards. See
+ * timekeeping_apply_adjustment(). Thus we keep a separate copy for the coarse
+ * clockids which only is updated when the clock has been set or we have
+ * accumulated time.
+ */
+static inline void tk_update_coarse_nsecs(struct timekeeper *tk)
+{
+ tk->coarse_nsec = tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift;
+}
+
static void tk_set_xtime(struct timekeeper *tk, const struct timespec64 *ts)
{
tk->xtime_sec = ts->tv_sec;
tk->tkr_mono.xtime_nsec = (u64)ts->tv_nsec << tk->tkr_mono.shift;
+ tk_update_coarse_nsecs(tk);
}
static void tk_xtime_add(struct timekeeper *tk, const struct timespec64 *ts)
@@ -175,6 +199,7 @@ static void tk_xtime_add(struct timekeeper *tk, const struct timespec64 *ts)
tk->xtime_sec += ts->tv_sec;
tk->tkr_mono.xtime_nsec += (u64)ts->tv_nsec << tk->tkr_mono.shift;
tk_normalize_xtime(tk);
+ tk_update_coarse_nsecs(tk);
}
static void tk_set_wall_to_mono(struct timekeeper *tk, struct timespec64 wtm)
@@ -708,6 +733,7 @@ static void timekeeping_forward_now(struct timekeeper *tk)
tk_normalize_xtime(tk);
delta -= incr;
}
+ tk_update_coarse_nsecs(tk);
}
/**
@@ -804,8 +830,8 @@ EXPORT_SYMBOL_GPL(ktime_get_with_offset);
ktime_t ktime_get_coarse_with_offset(enum tk_offsets offs)
{
struct timekeeper *tk = &tk_core.timekeeper;
- unsigned int seq;
ktime_t base, *offset = offsets[offs];
+ unsigned int seq;
u64 nsecs;
WARN_ON(timekeeping_suspended);
@@ -813,7 +839,7 @@ ktime_t ktime_get_coarse_with_offset(enum tk_offsets offs)
do {
seq = read_seqcount_begin(&tk_core.seq);
base = ktime_add(tk->tkr_mono.base, *offset);
- nsecs = tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift;
+ nsecs = tk->coarse_nsec;
} while (read_seqcount_retry(&tk_core.seq, seq));
@@ -2161,7 +2187,7 @@ static bool timekeeping_advance(enum timekeeping_adv_mode mode)
struct timekeeper *real_tk = &tk_core.timekeeper;
unsigned int clock_set = 0;
int shift = 0, maxshift;
- u64 offset;
+ u64 offset, orig_offset;
guard(raw_spinlock_irqsave)(&tk_core.lock);
@@ -2172,7 +2198,7 @@ static bool timekeeping_advance(enum timekeeping_adv_mode mode)
offset = clocksource_delta(tk_clock_read(&tk->tkr_mono),
tk->tkr_mono.cycle_last, tk->tkr_mono.mask,
tk->tkr_mono.clock->max_raw_delta);
-
+ orig_offset = offset;
/* Check if there's really nothing to do */
if (offset < real_tk->cycle_interval && mode == TK_ADV_TICK)
return false;
@@ -2205,6 +2231,14 @@ static bool timekeeping_advance(enum timekeeping_adv_mode mode)
*/
clock_set |= accumulate_nsecs_to_secs(tk);
+ /*
+ * To avoid inconsistencies caused adjtimex TK_ADV_FREQ calls
+ * making small negative adjustments to the base xtime_nsec
+ * value, only update the coarse clocks if we accumulated time
+ */
+ if (orig_offset != offset)
+ tk_update_coarse_nsecs(tk);
+
timekeeping_update_from_shadow(&tk_core, clock_set);
return !!clock_set;
@@ -2248,7 +2282,7 @@ void ktime_get_coarse_real_ts64(struct timespec64 *ts)
do {
seq = read_seqcount_begin(&tk_core.seq);
- *ts = tk_xtime(tk);
+ *ts = tk_xtime_coarse(tk);
} while (read_seqcount_retry(&tk_core.seq, seq));
}
EXPORT_SYMBOL(ktime_get_coarse_real_ts64);
@@ -2271,7 +2305,7 @@ void ktime_get_coarse_real_ts64_mg(struct timespec64 *ts)
do {
seq = read_seqcount_begin(&tk_core.seq);
- *ts = tk_xtime(tk);
+ *ts = tk_xtime_coarse(tk);
offset = tk_core.timekeeper.offs_real;
} while (read_seqcount_retry(&tk_core.seq, seq));
@@ -2350,12 +2384,12 @@ void ktime_get_coarse_ts64(struct timespec64 *ts)
do {
seq = read_seqcount_begin(&tk_core.seq);
- now = tk_xtime(tk);
+ now = tk_xtime_coarse(tk);
mono = tk->wall_to_monotonic;
} while (read_seqcount_retry(&tk_core.seq, seq));
set_normalized_timespec64(ts, now.tv_sec + mono.tv_sec,
- now.tv_nsec + mono.tv_nsec);
+ now.tv_nsec + mono.tv_nsec);
}
EXPORT_SYMBOL(ktime_get_coarse_ts64);
diff --git a/kernel/time/vsyscall.c b/kernel/time/vsyscall.c
index 01c2ab1e8971..32ef27c71b57 100644
--- a/kernel/time/vsyscall.c
+++ b/kernel/time/vsyscall.c
@@ -98,12 +98,12 @@ void update_vsyscall(struct timekeeper *tk)
/* CLOCK_REALTIME_COARSE */
vdso_ts = &vc[CS_HRES_COARSE].basetime[CLOCK_REALTIME_COARSE];
vdso_ts->sec = tk->xtime_sec;
- vdso_ts->nsec = tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift;
+ vdso_ts->nsec = tk->coarse_nsec;
/* CLOCK_MONOTONIC_COARSE */
vdso_ts = &vc[CS_HRES_COARSE].basetime[CLOCK_MONOTONIC_COARSE];
vdso_ts->sec = tk->xtime_sec + tk->wall_to_monotonic.tv_sec;
- nsec = tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift;
+ nsec = tk->coarse_nsec;
nsec = nsec + tk->wall_to_monotonic.tv_nsec;
vdso_ts->sec += __iter_div_u64_rem(nsec, NSEC_PER_SEC, &vdso_ts->nsec);
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 2a47682d1ab7..47d76d03ce30 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -3075,6 +3075,8 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
void split_huge_pmd_locked(struct vm_area_struct *vma, unsigned long address,
pmd_t *pmd, bool freeze, struct folio *folio)
{
+ bool pmd_migration = is_pmd_migration_entry(*pmd);
+
VM_WARN_ON_ONCE(folio && !folio_test_pmd_mappable(folio));
VM_WARN_ON_ONCE(!IS_ALIGNED(address, HPAGE_PMD_SIZE));
VM_WARN_ON_ONCE(folio && !folio_test_locked(folio));
@@ -3085,9 +3087,12 @@ void split_huge_pmd_locked(struct vm_area_struct *vma, unsigned long address,
* require a folio to check the PMD against. Otherwise, there
* is a risk of replacing the wrong folio.
*/
- if (pmd_trans_huge(*pmd) || pmd_devmap(*pmd) ||
- is_pmd_migration_entry(*pmd)) {
- if (folio && folio != pmd_folio(*pmd))
+ if (pmd_trans_huge(*pmd) || pmd_devmap(*pmd) || pmd_migration) {
+ /*
+ * Do not apply pmd_folio() to a migration entry; and folio lock
+ * guarantees that it must be of the wrong folio anyway.
+ */
+ if (folio && (pmd_migration || folio != pmd_folio(*pmd)))
return;
__split_huge_pmd_locked(vma, pmd, address, freeze);
}
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index e3e6ac991b9c..6ea1be71aa42 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -4034,10 +4034,13 @@ static long demote_free_hugetlb_folios(struct hstate *src, struct hstate *dst,
list_for_each_entry_safe(folio, next, src_list, lru) {
int i;
+ bool cma;
if (folio_test_hugetlb_vmemmap_optimized(folio))
continue;
+ cma = folio_test_hugetlb_cma(folio);
+
list_del(&folio->lru);
split_page_owner(&folio->page, huge_page_order(src), huge_page_order(dst));
@@ -4053,6 +4056,9 @@ static long demote_free_hugetlb_folios(struct hstate *src, struct hstate *dst,
new_folio->mapping = NULL;
init_new_hugetlb_folio(dst, new_folio);
+ /* Copy the CMA flag so that it is freed correctly */
+ if (cma)
+ folio_set_hugetlb_cma(new_folio);
list_add(&new_folio->lru, &dst_list);
}
}
diff --git a/mm/internal.h b/mm/internal.h
index e9695baa5922..25a29872c634 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -248,11 +248,9 @@ static inline int folio_pte_batch(struct folio *folio, unsigned long addr,
pte_t *start_ptep, pte_t pte, int max_nr, fpb_t flags,
bool *any_writable, bool *any_young, bool *any_dirty)
{
- unsigned long folio_end_pfn = folio_pfn(folio) + folio_nr_pages(folio);
- const pte_t *end_ptep = start_ptep + max_nr;
pte_t expected_pte, *ptep;
bool writable, young, dirty;
- int nr;
+ int nr, cur_nr;
if (any_writable)
*any_writable = false;
@@ -265,11 +263,15 @@ static inline int folio_pte_batch(struct folio *folio, unsigned long addr,
VM_WARN_ON_FOLIO(!folio_test_large(folio) || max_nr < 1, folio);
VM_WARN_ON_FOLIO(page_folio(pfn_to_page(pte_pfn(pte))) != folio, folio);
+ /* Limit max_nr to the actual remaining PFNs in the folio we could batch. */
+ max_nr = min_t(unsigned long, max_nr,
+ folio_pfn(folio) + folio_nr_pages(folio) - pte_pfn(pte));
+
nr = pte_batch_hint(start_ptep, pte);
expected_pte = __pte_batch_clear_ignored(pte_advance_pfn(pte, nr), flags);
ptep = start_ptep + nr;
- while (ptep < end_ptep) {
+ while (nr < max_nr) {
pte = ptep_get(ptep);
if (any_writable)
writable = !!pte_write(pte);
@@ -282,14 +284,6 @@ static inline int folio_pte_batch(struct folio *folio, unsigned long addr,
if (!pte_same(pte, expected_pte))
break;
- /*
- * Stop immediately once we reached the end of the folio. In
- * corner cases the next PFN might fall into a different
- * folio.
- */
- if (pte_pfn(pte) >= folio_end_pfn)
- break;
-
if (any_writable)
*any_writable |= writable;
if (any_young)
@@ -297,12 +291,13 @@ static inline int folio_pte_batch(struct folio *folio, unsigned long addr,
if (any_dirty)
*any_dirty |= dirty;
- nr = pte_batch_hint(ptep, pte);
- expected_pte = pte_advance_pfn(expected_pte, nr);
- ptep += nr;
+ cur_nr = pte_batch_hint(ptep, pte);
+ expected_pte = pte_advance_pfn(expected_pte, cur_nr);
+ ptep += cur_nr;
+ nr += cur_nr;
}
- return min(ptep - start_ptep, max_nr);
+ return min(nr, max_nr);
}
/**
diff --git a/mm/memblock.c b/mm/memblock.c
index d3509414b8c3..0e9ebb8aa7fe 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -457,7 +457,14 @@ static int __init_memblock memblock_double_array(struct memblock_type *type,
min(new_area_start, memblock.current_limit),
new_alloc_size, PAGE_SIZE);
- new_array = addr ? __va(addr) : NULL;
+ if (addr) {
+ /* The memory may not have been accepted, yet. */
+ accept_memory(addr, new_alloc_size);
+
+ new_array = __va(addr);
+ } else {
+ new_array = NULL;
+ }
}
if (!addr) {
pr_err("memblock: Failed to double %s array from %ld to %ld entries !\n",
diff --git a/mm/mm_init.c b/mm/mm_init.c
index 9659689b8ace..327764ca0ee4 100644
--- a/mm/mm_init.c
+++ b/mm/mm_init.c
@@ -1786,7 +1786,7 @@ static bool arch_has_descending_max_zone_pfns(void)
return IS_ENABLED(CONFIG_ARC) && !IS_ENABLED(CONFIG_ARC_HAS_PAE40);
}
-static void set_high_memory(void)
+static void __init set_high_memory(void)
{
phys_addr_t highmem = memblock_end_of_DRAM();
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 2eff8b51a945..f214843612dc 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -1272,13 +1272,22 @@ int folio_alloc_swap(struct folio *folio, gfp_t gfp)
VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio);
VM_BUG_ON_FOLIO(!folio_test_uptodate(folio), folio);
- /*
- * Should not even be attempting large allocations when huge
- * page swap is disabled. Warn and fail the allocation.
- */
- if (order && (!IS_ENABLED(CONFIG_THP_SWAP) || size > SWAPFILE_CLUSTER)) {
- VM_WARN_ON_ONCE(1);
- return -EINVAL;
+ if (order) {
+ /*
+ * Reject large allocation when THP_SWAP is disabled,
+ * the caller should split the folio and try again.
+ */
+ if (!IS_ENABLED(CONFIG_THP_SWAP))
+ return -EAGAIN;
+
+ /*
+ * Allocation size should never exceed cluster size
+ * (HPAGE_PMD_SIZE).
+ */
+ if (size > SWAPFILE_CLUSTER) {
+ VM_WARN_ON_ONCE(1);
+ return -EINVAL;
+ }
}
local_lock(&percpu_swap_cluster.lock);
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 3ed720a787ec..2d7511654831 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -1940,7 +1940,7 @@ static inline void setup_vmalloc_vm(struct vm_struct *vm,
{
vm->flags = flags;
vm->addr = (void *)va->va_start;
- vm->size = va_size(va);
+ vm->size = vm->requested_size = va_size(va);
vm->caller = caller;
va->vm = vm;
}
@@ -3133,6 +3133,7 @@ struct vm_struct *__get_vm_area_node(unsigned long size,
area->flags = flags;
area->caller = caller;
+ area->requested_size = requested_size;
va = alloc_vmap_area(size, align, start, end, node, gfp_mask, 0, area);
if (IS_ERR(va)) {
@@ -4063,6 +4064,8 @@ EXPORT_SYMBOL(vzalloc_node_noprof);
*/
void *vrealloc_noprof(const void *p, size_t size, gfp_t flags)
{
+ struct vm_struct *vm = NULL;
+ size_t alloced_size = 0;
size_t old_size = 0;
void *n;
@@ -4072,15 +4075,17 @@ void *vrealloc_noprof(const void *p, size_t size, gfp_t flags)
}
if (p) {
- struct vm_struct *vm;
-
vm = find_vm_area(p);
if (unlikely(!vm)) {
WARN(1, "Trying to vrealloc() nonexistent vm area (%p)\n", p);
return NULL;
}
- old_size = get_vm_area_size(vm);
+ alloced_size = get_vm_area_size(vm);
+ old_size = vm->requested_size;
+ if (WARN(alloced_size < old_size,
+ "vrealloc() has mismatched area vs requested sizes (%p)\n", p))
+ return NULL;
}
/*
@@ -4088,14 +4093,26 @@ void *vrealloc_noprof(const void *p, size_t size, gfp_t flags)
* would be a good heuristic for when to shrink the vm_area?
*/
if (size <= old_size) {
- /* Zero out spare memory. */
- if (want_init_on_alloc(flags))
+ /* Zero out "freed" memory. */
+ if (want_init_on_free())
memset((void *)p + size, 0, old_size - size);
+ vm->requested_size = size;
kasan_poison_vmalloc(p + size, old_size - size);
- kasan_unpoison_vmalloc(p, size, KASAN_VMALLOC_PROT_NORMAL);
return (void *)p;
}
+ /*
+ * We already have the bytes available in the allocation; use them.
+ */
+ if (size <= alloced_size) {
+ kasan_unpoison_vmalloc(p + old_size, size - old_size,
+ KASAN_VMALLOC_PROT_NORMAL);
+ /* Zero out "alloced" memory. */
+ if (want_init_on_alloc(flags))
+ memset((void *)p + old_size, 0, size - old_size);
+ vm->requested_size = size;
+ }
+
/* TODO: Grow the vm_area, i.e. allocate and map additional pages. */
n = __vmalloc_noprof(size, flags);
if (!n)
diff --git a/tools/testing/selftests/kvm/arm64/set_id_regs.c b/tools/testing/selftests/kvm/arm64/set_id_regs.c
index 322b9d3b0125..57708de2075d 100644
--- a/tools/testing/selftests/kvm/arm64/set_id_regs.c
+++ b/tools/testing/selftests/kvm/arm64/set_id_regs.c
@@ -129,10 +129,10 @@ static const struct reg_ftr_bits ftr_id_aa64pfr0_el1[] = {
REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64PFR0_EL1, DIT, 0),
REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64PFR0_EL1, SEL2, 0),
REG_FTR_BITS(FTR_EXACT, ID_AA64PFR0_EL1, GIC, 0),
- REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64PFR0_EL1, EL3, 0),
- REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64PFR0_EL1, EL2, 0),
- REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64PFR0_EL1, EL1, 0),
- REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64PFR0_EL1, EL0, 0),
+ REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64PFR0_EL1, EL3, 1),
+ REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64PFR0_EL1, EL2, 1),
+ REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64PFR0_EL1, EL1, 1),
+ REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64PFR0_EL1, EL0, 1),
REG_FTR_END,
};
diff --git a/tools/testing/selftests/mm/compaction_test.c b/tools/testing/selftests/mm/compaction_test.c
index 2c3a0eb6b22d..9bc4591c7b16 100644
--- a/tools/testing/selftests/mm/compaction_test.c
+++ b/tools/testing/selftests/mm/compaction_test.c
@@ -90,6 +90,8 @@ int check_compaction(unsigned long mem_free, unsigned long hugepage_size,
int compaction_index = 0;
char nr_hugepages[20] = {0};
char init_nr_hugepages[24] = {0};
+ char target_nr_hugepages[24] = {0};
+ int slen;
snprintf(init_nr_hugepages, sizeof(init_nr_hugepages),
"%lu", initial_nr_hugepages);
@@ -106,11 +108,18 @@ int check_compaction(unsigned long mem_free, unsigned long hugepage_size,
goto out;
}
- /* Request a large number of huge pages. The Kernel will allocate
- as much as it can */
- if (write(fd, "100000", (6*sizeof(char))) != (6*sizeof(char))) {
- ksft_print_msg("Failed to write 100000 to /proc/sys/vm/nr_hugepages: %s\n",
- strerror(errno));
+ /*
+ * Request huge pages for about half of the free memory. The Kernel
+ * will allocate as much as it can, and we expect it will get at least 1/3
+ */
+ nr_hugepages_ul = mem_free / hugepage_size / 2;
+ snprintf(target_nr_hugepages, sizeof(target_nr_hugepages),
+ "%lu", nr_hugepages_ul);
+
+ slen = strlen(target_nr_hugepages);
+ if (write(fd, target_nr_hugepages, slen) != slen) {
+ ksft_print_msg("Failed to write %lu to /proc/sys/vm/nr_hugepages: %s\n",
+ nr_hugepages_ul, strerror(errno));
goto close_fd;
}
diff --git a/tools/testing/selftests/mm/guard-regions.c b/tools/testing/selftests/mm/guard-regions.c
index b3d0e2771096..eba43ead13ae 100644
--- a/tools/testing/selftests/mm/guard-regions.c
+++ b/tools/testing/selftests/mm/guard-regions.c
@@ -271,12 +271,16 @@ FIXTURE_SETUP(guard_regions)
self->page_size = (unsigned long)sysconf(_SC_PAGESIZE);
setup_sighandler();
- if (variant->backing == ANON_BACKED)
+ switch (variant->backing) {
+ case ANON_BACKED:
return;
-
- self->fd = open_file(
- variant->backing == SHMEM_BACKED ? "/tmp/" : "",
- self->path);
+ case LOCAL_FILE_BACKED:
+ self->fd = open_file("", self->path);
+ break;
+ case SHMEM_BACKED:
+ self->fd = memfd_create(self->path, 0);
+ break;
+ }
/* We truncate file to at least 100 pages, tests can modify as needed. */
ASSERT_EQ(ftruncate(self->fd, 100 * self->page_size), 0);
@@ -1696,7 +1700,7 @@ TEST_F(guard_regions, readonly_file)
char *ptr;
int i;
- if (variant->backing == ANON_BACKED)
+ if (variant->backing != LOCAL_FILE_BACKED)
SKIP(return, "Read-only test specific to file-backed");
/* Map shared so we can populate with pattern, populate it, unmap. */
diff --git a/tools/testing/selftests/mm/pkey-powerpc.h b/tools/testing/selftests/mm/pkey-powerpc.h
index 1bad310d282a..17bf2d1b0192 100644
--- a/tools/testing/selftests/mm/pkey-powerpc.h
+++ b/tools/testing/selftests/mm/pkey-powerpc.h
@@ -3,6 +3,8 @@
#ifndef _PKEYS_POWERPC_H
#define _PKEYS_POWERPC_H
+#include <sys/stat.h>
+
#ifndef SYS_pkey_alloc
# define SYS_pkey_alloc 384
# define SYS_pkey_free 385
@@ -102,8 +104,18 @@ static inline void expect_fault_on_read_execonly_key(void *p1, int pkey)
return;
}
+#define REPEAT_8(s) s s s s s s s s
+#define REPEAT_64(s) REPEAT_8(s) REPEAT_8(s) REPEAT_8(s) REPEAT_8(s) \
+ REPEAT_8(s) REPEAT_8(s) REPEAT_8(s) REPEAT_8(s)
+#define REPEAT_512(s) REPEAT_64(s) REPEAT_64(s) REPEAT_64(s) REPEAT_64(s) \
+ REPEAT_64(s) REPEAT_64(s) REPEAT_64(s) REPEAT_64(s)
+#define REPEAT_4096(s) REPEAT_512(s) REPEAT_512(s) REPEAT_512(s) REPEAT_512(s) \
+ REPEAT_512(s) REPEAT_512(s) REPEAT_512(s) REPEAT_512(s)
+#define REPEAT_16384(s) REPEAT_4096(s) REPEAT_4096(s) \
+ REPEAT_4096(s) REPEAT_4096(s)
+
/* 4-byte instructions * 16384 = 64K page */
-#define __page_o_noops() asm(".rept 16384 ; nop; .endr")
+#define __page_o_noops() asm(REPEAT_16384("nop\n"))
static inline void *malloc_pkey_with_mprotect_subpage(long size, int prot, u16 pkey)
{
diff --git a/tools/testing/selftests/mm/pkey_util.c b/tools/testing/selftests/mm/pkey_util.c
index ca4ad0d44ab2..255b332f7a08 100644
--- a/tools/testing/selftests/mm/pkey_util.c
+++ b/tools/testing/selftests/mm/pkey_util.c
@@ -1,4 +1,5 @@
// SPDX-License-Identifier: GPL-2.0-only
+#define __SANE_USERSPACE_TYPES__
#include <sys/syscall.h>
#include <unistd.h>