Merge tag 'arm64-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux

Pull arm64 fixes from Will Deacon:
 "It's a bit all over the place, as I was hoping to fix a decade-old bug
  in our seccomp handling on syscall entry and ended up collecting other
  fixes in the meantime. You'll see the failed attempt (+revert) here
  but I didn't want to hold off on the others any longer. Hopefully
  we'll get that one squashed next week...

   - Fix early_ioremap() of unaligned ACPI tables

   - Remove bogus information from data abort diagnostics

   - Fix kprobes recursion during single-step

   - Fix incorrect constant in ESR address size fault macro

   - Fix OOB page-table walk in memory hot-unplug notifier

   - Fix OOB access to the linear map when retrieving an unaligned huge pte

   - Fix MPAM register reset values

   - Fix MPAM NULL dereference on teardown"

* tag 'arm64-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux:
  arm64: make huge_ptep_get handled unaligned addresses
  arm64/mm: Check the requested PFN range during memory removal
  arm64: Correct value returned by ESR_ELx_FSC_ADDRSZ_nL()
  arm64: kprobes: Allow reentering kprobes while single-stepping
  arm64: kprobes: Only handle faults originating from XOL slot
  drivers/virt: pkvm: Fix end calculation in mmio_guard_ioremap_hook()
  Revert "arm64: syscall: Ensure saved x0 is kept in-sync with tracer updates"
  arm64: mm: When logging data aborts only decode Xs when ISV=1
  arm64: fixmap: Allow 256K early_ioremap() at any offset
  arm_mpam: guard MBWU state before adding it to garbage
  arm_mpam: Fix MPAMCFG_MBW_PBM register setting
  arm_mpam: Fix software reset values of MPAMCFG_PRI
  arm64: syscall: Ensure saved x0 is kept in-sync with tracer updates

9 files changed, 85 insertions, 23 deletions

diff --git a/arch/arm64/include/asm/esr.h b/arch/arm64/include/asm/esr.h
index 81c17320a588..f816f5d77f1a 100644
--- a/arch/arm64/include/asm/esr.h
+++ b/arch/arm64/include/asm/esr.h
@@ -131,7 +131,7 @@
  * Annoyingly, the negative levels for Address size faults aren't laid out
  * contiguously (or in the desired order)
  */
-#define ESR_ELx_FSC_ADDRSZ_nL(n)	((n) == -1 ? 0x25 : 0x2C)
+#define ESR_ELx_FSC_ADDRSZ_nL(n)	((n) == -1 ? 0x29 : 0x2C)
 #define ESR_ELx_FSC_ADDRSZ_L(n)		((n) < 0 ? ESR_ELx_FSC_ADDRSZ_nL(n) : \
 						   (ESR_ELx_FSC_ADDRSZ + (n)))
 
diff --git a/arch/arm64/include/asm/fixmap.h b/arch/arm64/include/asm/fixmap.h
index 65555284446e..7075a3bd2c61 100644
--- a/arch/arm64/include/asm/fixmap.h
+++ b/arch/arm64/include/asm/fixmap.h
@@ -78,8 +78,12 @@ enum fixed_addresses {
 	/*
 	 * Temporary boot-time mappings, used by early_ioremap(),
 	 * before ioremap() is functional.
+	 *
+	 * Reserve one extra page so a 256K mapping may start at any
+	 * offset within a page. early_ioremap() maps the page-aligned
+	 * physical range, so the initial offset can consume an extra page.
 	 */
-#define NR_FIX_BTMAPS		(SZ_256K / PAGE_SIZE)
+#define NR_FIX_BTMAPS		((SZ_256K / PAGE_SIZE) + 1)
 #define FIX_BTMAPS_SLOTS	7
 #define TOTAL_FIX_BTMAPS	(NR_FIX_BTMAPS * FIX_BTMAPS_SLOTS)
 
diff --git a/arch/arm64/include/asm/kprobes.h b/arch/arm64/include/asm/kprobes.h
index f2782560647b..35ce2c94040e 100644
--- a/arch/arm64/include/asm/kprobes.h
+++ b/arch/arm64/include/asm/kprobes.h
@@ -26,6 +26,12 @@
 struct prev_kprobe {
 	struct kprobe *kp;
 	unsigned int status;
+
+	/*
+	 * The original DAIF state of the outer kprobe, saved here before
+	 * a nested kprobe overwrites kcb->saved_irqflag during reentry.
+	 */
+	unsigned long saved_irqflag;
 };
 
 /* per-cpu kprobe control block */
diff --git a/arch/arm64/kernel/probes/kprobes.c b/arch/arm64/kernel/probes/kprobes.c
index 43a0361a8bf0..4e0efad5caf2 100644
--- a/arch/arm64/kernel/probes/kprobes.c
+++ b/arch/arm64/kernel/probes/kprobes.c
@@ -174,12 +174,27 @@ static void __kprobes save_previous_kprobe(struct kprobe_ctlblk *kcb)
 {
 	kcb->prev_kprobe.kp = kprobe_running();
 	kcb->prev_kprobe.status = kcb->kprobe_status;
+
+	/*
+	 * Save the outer kprobe's original DAIF flags before the nested
+	 * kprobe calls kprobes_save_local_irqflag() and overwrites
+	 * kcb->saved_irqflag. Without this, the outer kprobe will restore
+	 * the wrong DAIF state and leave interrupts permanently masked.
+	 */
+	kcb->prev_kprobe.saved_irqflag = kcb->saved_irqflag;
 }
 
 static void __kprobes restore_previous_kprobe(struct kprobe_ctlblk *kcb)
 {
 	__this_cpu_write(current_kprobe, kcb->prev_kprobe.kp);
 	kcb->kprobe_status = kcb->prev_kprobe.status;
+
+	/*
+	 * Restore the outer kprobe's saved_irqflag so that when its
+	 * single-step completes, kprobes_restore_local_irqflag() uses
+	 * the correct original DAIF value.
+	 */
+	kcb->saved_irqflag = kcb->prev_kprobe.saved_irqflag;
 }
 
 static void __kprobes set_current_kprobe(struct kprobe *p)
@@ -240,10 +255,16 @@ static int __kprobes reenter_kprobe(struct kprobe *p,
 	switch (kcb->kprobe_status) {
 	case KPROBE_HIT_SSDONE:
 	case KPROBE_HIT_ACTIVE:
+	case KPROBE_HIT_SS:
+		/*
+		 * A probe can be hit while another kprobe is preparing or
+		 * executing its XOL single-step instruction. This is still a
+		 * recoverable one-level reentry, so handle it in the same way as
+		 * reentry from KPROBE_HIT_ACTIVE or KPROBE_HIT_SSDONE.
+		 */
 		kprobes_inc_nmissed_count(p);
 		setup_singlestep(p, regs, kcb, 1);
 		break;
-	case KPROBE_HIT_SS:
 	case KPROBE_REENTER:
 		pr_warn("Failed to recover from reentered kprobes.\n");
 		dump_kprobe(p);
@@ -282,10 +303,32 @@ int __kprobes kprobe_fault_handler(struct pt_regs *regs, unsigned int fsr)
 	struct kprobe *cur = kprobe_running();
 	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
 
+	/*
+	 * Simulated kprobes execute in the debug trap context and have no
+	 * XOL slot. Any page fault taken while a simulated kprobe is in
+	 * progress cannot have been caused by kprobe single-stepping and
+	 * must be left alone for the normal page fault handler, including
+	 * fixup_exception.
+	 */
+	if (cur && !cur->ainsn.xol_insn)
+		return 0;
+
 	switch (kcb->kprobe_status) {
 	case KPROBE_HIT_SS:
 	case KPROBE_REENTER:
 		/*
+		 * A page fault taken while in KPROBE_HIT_SS or
+		 * KPROBE_REENTER state is only attributable to kprobe
+		 * single-stepping if the faulting PC points to the
+		 * current kprobe's XOL instruction. If the fault occurred
+		 * elsewhere (e.g. in perf or tracing code invoked from the
+		 * debug exception path), leave it for the normal page fault
+		 * handler to process.
+		 */
+		if (instruction_pointer(regs) != (unsigned long)cur->ainsn.xol_insn)
+			break;
+
+		/*
 		 * We are here because the instruction being single
 		 * stepped caused a page fault. We reset the current
 		 * kprobe and the ip points back to the probe address
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 85e23388f9bb..0b52557652be 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -76,6 +76,8 @@ static void data_abort_decode(unsigned long esr)
 		pr_alert("  SF = %lu, AR = %lu\n",
 			 (esr & ESR_ELx_SF) >> ESR_ELx_SF_SHIFT,
 			 (esr & ESR_ELx_AR) >> ESR_ELx_AR_SHIFT);
+		pr_alert("  Xs = %llu\n",
+			 (iss2 & ESR_ELx_Xs_MASK) >> ESR_ELx_Xs_SHIFT);
 	} else {
 		pr_alert("  ISV = 0, ISS = 0x%08lx, ISS2 = 0x%08lx\n",
 			 esr & ESR_ELx_ISS_MASK, iss2);
@@ -87,11 +89,10 @@ static void data_abort_decode(unsigned long esr)
 		 (iss2 & ESR_ELx_TnD) >> ESR_ELx_TnD_SHIFT,
 		 (iss2 & ESR_ELx_TagAccess) >> ESR_ELx_TagAccess_SHIFT);
 
-	pr_alert("  GCS = %ld, Overlay = %lu, DirtyBit = %lu, Xs = %llu\n",
+	pr_alert("  GCS = %ld, Overlay = %lu, DirtyBit = %lu\n",
 		 (iss2 & ESR_ELx_GCS) >> ESR_ELx_GCS_SHIFT,
 		 (iss2 & ESR_ELx_Overlay) >> ESR_ELx_Overlay_SHIFT,
-		 (iss2 & ESR_ELx_DirtyBit) >> ESR_ELx_DirtyBit_SHIFT,
-		 (iss2 & ESR_ELx_Xs_MASK) >> ESR_ELx_Xs_SHIFT);
+		 (iss2 & ESR_ELx_DirtyBit) >> ESR_ELx_DirtyBit_SHIFT);
 }
 
 static void mem_abort_decode(unsigned long esr)
diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c
index 30772a909aea..8e799c1fe0aa 100644
--- a/arch/arm64/mm/hugetlbpage.c
+++ b/arch/arm64/mm/hugetlbpage.c
@@ -87,7 +87,7 @@ static int find_num_contig(struct mm_struct *mm, unsigned long addr,
 	p4dp = p4d_offset(pgdp, addr);
 	pudp = pud_offset(p4dp, addr);
 	pmdp = pmd_offset(pudp, addr);
-	if ((pte_t *)pmdp == ptep) {
+	if ((pte_t *)PTR_ALIGN_DOWN(pmdp, sizeof(*pmdp) * CONT_PMDS) == ptep) {
 		*pgsize = PMD_SIZE;
 		return CONT_PMDS;
 	}
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index a25d8beacc83..18a8b0d3714e 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -2194,7 +2194,7 @@ static int prevent_memory_remove_notifier(struct notifier_block *nb,
 		}
 	}
 
-	if (!can_unmap_without_split(pfn, arg->nr_pages))
+	if (!can_unmap_without_split(arg->start_pfn, arg->nr_pages))
 		return NOTIFY_BAD;
 
 	return NOTIFY_OK;
diff --git a/drivers/resctrl/mpam_devices.c b/drivers/resctrl/mpam_devices.c
index b69f99488111..2f09f4b78bd3 100644
--- a/drivers/resctrl/mpam_devices.c
+++ b/drivers/resctrl/mpam_devices.c
@@ -1552,12 +1552,9 @@ static u16 mpam_wa_t241_calc_min_from_max(struct mpam_props *props,
 static void mpam_reprogram_ris_partid(struct mpam_msc_ris *ris, u16 partid,
 				      struct mpam_config *cfg)
 {
-	u32 pri_val = 0;
 	u16 cmax = MPAMCFG_CMAX_CMAX;
 	struct mpam_msc *msc = ris->vmsc->msc;
 	struct mpam_props *rprops = &ris->props;
-	u16 dspri = GENMASK(rprops->dspri_wd, 0);
-	u16 intpri = GENMASK(rprops->intpri_wd, 0);
 
 	mutex_lock(&msc->part_sel_lock);
 	__mpam_part_sel(ris->ris_idx, partid, msc);
@@ -1583,9 +1580,9 @@ static void mpam_reprogram_ris_partid(struct mpam_msc_ris *ris, u16 partid,
 
 	if (mpam_has_feature(mpam_feat_mbw_part, rprops)) {
 		if (mpam_has_feature(mpam_feat_mbw_part, cfg))
-			mpam_reset_msc_bitmap(msc, MPAMCFG_MBW_PBM, rprops->mbw_pbm_bits);
-		else
 			mpam_write_partsel_reg(msc, MBW_PBM, cfg->mbw_pbm);
+		else
+			mpam_reset_msc_bitmap(msc, MPAMCFG_MBW_PBM, rprops->mbw_pbm_bits);
 	}
 
 	if (mpam_has_feature(mpam_feat_mbw_min, rprops)) {
@@ -1622,16 +1619,25 @@ static void mpam_reprogram_ris_partid(struct mpam_msc_ris *ris, u16 partid,
 
 	if (mpam_has_feature(mpam_feat_intpri_part, rprops) ||
 	    mpam_has_feature(mpam_feat_dspri_part, rprops)) {
-		/* aces high? */
-		if (!mpam_has_feature(mpam_feat_intpri_part_0_low, rprops))
-			intpri = 0;
-		if (!mpam_has_feature(mpam_feat_dspri_part_0_low, rprops))
-			dspri = 0;
+		u32 pri_val = 0;
+
+		if (mpam_has_feature(mpam_feat_intpri_part, rprops)) {
+			u16 intpri = GENMASK(rprops->intpri_wd - 1, 0);
+
+			/* aces high? */
+			if (!mpam_has_feature(mpam_feat_intpri_part_0_low, rprops))
+				intpri = 0;
 
-		if (mpam_has_feature(mpam_feat_intpri_part, rprops))
 			pri_val |= FIELD_PREP(MPAMCFG_PRI_INTPRI, intpri);
-		if (mpam_has_feature(mpam_feat_dspri_part, rprops))
+		}
+		if (mpam_has_feature(mpam_feat_dspri_part, rprops)) {
+			u16 dspri = GENMASK(rprops->dspri_wd - 1, 0);
+
+			if (!mpam_has_feature(mpam_feat_dspri_part_0_low, rprops))
+				dspri = 0;
+
 			pri_val |= FIELD_PREP(MPAMCFG_PRI_DSPRI, dspri);
+		}
 
 		mpam_write_partsel_reg(msc, PRI, pri_val);
 	}
@@ -2606,8 +2612,10 @@ static void __destroy_component_cfg(struct mpam_component *comp)
 		msc = vmsc->msc;
 
 		if (mpam_mon_sel_lock(msc)) {
-			list_for_each_entry(ris, &vmsc->ris, vmsc_list)
-				add_to_garbage(ris->mbwu_state);
+			list_for_each_entry(ris, &vmsc->ris, vmsc_list) {
+				if (ris->mbwu_state)
+					add_to_garbage(ris->mbwu_state);
+			}
 			mpam_mon_sel_unlock(msc);
 		}
 	}
diff --git a/drivers/virt/coco/pkvm-guest/arm-pkvm-guest.c b/drivers/virt/coco/pkvm-guest/arm-pkvm-guest.c
index 4230b817a80b..d66291def0f4 100644
--- a/drivers/virt/coco/pkvm-guest/arm-pkvm-guest.c
+++ b/drivers/virt/coco/pkvm-guest/arm-pkvm-guest.c
@@ -82,8 +82,8 @@ static int mmio_guard_ioremap_hook(phys_addr_t phys, size_t size,
 	if (protval != PROT_DEVICE_nGnRE && protval != PROT_DEVICE_nGnRnE)
 		return 0;
 
+	end = PAGE_ALIGN(phys + size);
 	phys = PAGE_ALIGN_DOWN(phys);
-	end = phys + PAGE_ALIGN(size);
 
 	while (phys < end) {
 		const int func_id = ARM_SMCCC_VENDOR_HYP_KVM_MMIO_GUARD_FUNC_ID;