Merge tag 'powerpc-5.11-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc updates from Michael Ellerman:

 - Switch to the generic C VDSO, as well as some cleanups of our VDSO
   setup/handling code.

 - Support for KUAP (Kernel User Access Prevention) on systems using the
   hashed page table MMU, using memory protection keys.

 - Better handling of PowerVM SMT8 systems where all threads of a core
   do not share an L2, allowing the scheduler to make better scheduling
   decisions.

 - Further improvements to our machine check handling.

 - Show registers when unwinding interrupt frames during stack traces.

 - Improvements to our pseries (PowerVM) partition migration code.

 - Several series from Christophe refactoring and cleaning up various
   parts of the 32-bit code.

 - Other smaller features, fixes & cleanups.

Thanks to: Alan Modra, Alexey Kardashevskiy, Andrew Donnellan, Aneesh
Kumar K.V, Ard Biesheuvel, Athira Rajeev, Balamuruhan S, Bill Wendling,
Cédric Le Goater, Christophe Leroy, Christophe Lombard, Colin Ian King,
Daniel Axtens, David Hildenbrand, Frederic Barrat, Ganesh Goudar,
Gautham R. Shenoy, Geert Uytterhoeven, Giuseppe Sacco, Greg Kurz,
Harish, Jan Kratochvil, Jordan Niethe, Kaixu Xia, Laurent Dufour,
Leonardo Bras, Madhavan Srinivasan, Mahesh Salgaonkar, Mathieu
Desnoyers, Nathan Lynch, Nicholas Piggin, Oleg Nesterov, Oliver
O'Halloran, Oscar Salvador, Po-Hsu Lin, Qian Cai, Qinglang Miao, Randy
Dunlap, Ravi Bangoria, Sachin Sant, Sandipan Das, Sebastian Andrzej
Siewior , Segher Boessenkool, Srikar Dronamraju, Tyrel Datwyler, Uwe
Kleine-König, Vincent Stehlé, Youling Tang, and Zhang Xiaoxu.

* tag 'powerpc-5.11-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (304 commits)
  powerpc/32s: Fix cleanup_cpu_mmu_context() compile bug
  powerpc: Add config fragment for disabling -Werror
  powerpc/configs: Add ppc64le_allnoconfig target
  powerpc/powernv: Rate limit opal-elog read failure message
  powerpc/pseries/memhotplug: Quieten some DLPAR operations
  powerpc/ps3: use dma_mapping_error()
  powerpc: force inlining of csum_partial() to avoid multiple csum_partial() with GCC10
  powerpc/perf: Fix Threshold Event Counter Multiplier width for P10
  powerpc/mm: Fix hugetlb_free_pmd_range() and hugetlb_free_pud_range()
  KVM: PPC: Book3S HV: Fix mask size for emulated msgsndp
  KVM: PPC: fix comparison to bool warning
  KVM: PPC: Book3S: Assign boolean values to a bool variable
  powerpc: Inline setup_kup()
  powerpc/64s: Mark the kuap/kuep functions non __init
  KVM: PPC: Book3S HV: XIVE: Add a comment regarding VP numbering
  powerpc/xive: Improve error reporting of OPAL calls
  powerpc/xive: Simplify xive_do_source_eoi()
  powerpc/xive: Remove P9 DD1 flag XIVE_IRQ_FLAG_EOI_FW
  powerpc/xive: Remove P9 DD1 flag XIVE_IRQ_FLAG_MASK_FW
  powerpc/xive: Remove P9 DD1 flag XIVE_IRQ_FLAG_SHIFT_BUG
  ...

1 files changed, 35 insertions, 134 deletions

diff --git a/arch/powerpc/mm/book3s32/hash_low.S b/arch/powerpc/mm/book3s32/hash_low.S
index b2c912e517b9..0e6dc830c38b 100644
--- a/arch/powerpc/mm/book3s32/hash_low.S
+++ b/arch/powerpc/mm/book3s32/hash_low.S
@@ -26,12 +26,11 @@
 #include <asm/feature-fixups.h>
 #include <asm/code-patching-asm.h>
 
-#ifdef CONFIG_SMP
-	.section .bss
-	.align	2
-mmu_hash_lock:
-	.space	4
-#endif /* CONFIG_SMP */
+#ifdef CONFIG_PTE_64BIT
+#define PTE_FLAGS_OFFSET	4	/* offset of PTE flags, in bytes */
+#else
+#define PTE_FLAGS_OFFSET	0
+#endif
 
 /*
  * Load a PTE into the hash table, if possible.
@@ -65,13 +64,14 @@ _GLOBAL(hash_page)
 	/* Get PTE (linux-style) and check access */
 	lis	r0, TASK_SIZE@h		/* check if kernel address */
 	cmplw	0,r4,r0
+	mfspr	r8,SPRN_SPRG_THREAD	/* current task's THREAD (phys) */
 	ori	r3,r3,_PAGE_USER|_PAGE_PRESENT /* test low addresses as user */
-	mfspr	r5, SPRN_SPRG_PGDIR	/* phys page-table root */
+	lwz	r5,PGDIR(r8)		/* virt page-table root */
 	blt+	112f			/* assume user more likely */
-	lis	r5, (swapper_pg_dir - PAGE_OFFSET)@ha	/* if kernel address, use */
-	addi	r5 ,r5 ,(swapper_pg_dir - PAGE_OFFSET)@l	/* kernel page table */
+	lis	r5,swapper_pg_dir@ha	/* if kernel address, use */
+	addi	r5,r5,swapper_pg_dir@l	/* kernel page table */
 	rlwimi	r3,r9,32-12,29,29	/* MSR_PR -> _PAGE_USER */
-112:
+112:	tophys(r5, r5)
 #ifndef CONFIG_PTE_64BIT
 	rlwimi	r5,r4,12,20,29		/* insert top 10 bits of address */
 	lwz	r8,0(r5)		/* get pmd entry */
@@ -94,25 +94,33 @@ _GLOBAL(hash_page)
 	rlwimi	r8,r4,22,20,29		/* insert next 10 bits of address */
 #else
 	rlwimi	r8,r4,23,20,28		/* compute pte address */
+	/*
+	 * If PTE_64BIT is set, the low word is the flags word; use that
+	 * word for locking since it contains all the interesting bits.
+	 */
+	addi	r8,r8,PTE_FLAGS_OFFSET
 #endif
-	rlwinm	r0,r3,32-3,24,24	/* _PAGE_RW access -> _PAGE_DIRTY */
-	ori	r0,r0,_PAGE_ACCESSED|_PAGE_HASHPTE
 
 	/*
 	 * Update the linux PTE atomically.  We do the lwarx up-front
 	 * because almost always, there won't be a permission violation
 	 * and there won't already be an HPTE, and thus we will have
 	 * to update the PTE to set _PAGE_HASHPTE.  -- paulus.
-	 *
-	 * If PTE_64BIT is set, the low word is the flags word; use that
-	 * word for locking since it contains all the interesting bits.
 	 */
-#if (PTE_FLAGS_OFFSET != 0)
-	addi	r8,r8,PTE_FLAGS_OFFSET
-#endif
 .Lretry:
 	lwarx	r6,0,r8			/* get linux-style pte, flag word */
+#ifdef CONFIG_PPC_KUAP
+	mfsrin	r5,r4
+	rlwinm	r0,r9,28,_PAGE_RW	/* MSR[PR] => _PAGE_RW */
+	rlwinm	r5,r5,12,_PAGE_RW	/* Ks => _PAGE_RW */
+	andc	r5,r5,r0		/* Ks & ~MSR[PR] */
+	andc	r5,r6,r5		/* Clear _PAGE_RW when Ks = 1 && MSR[PR] = 0 */
+	andc.	r5,r3,r5		/* check access & ~permission */
+#else
 	andc.	r5,r3,r6		/* check access & ~permission */
+#endif
+	rlwinm	r0,r3,32-3,24,24	/* _PAGE_RW access -> _PAGE_DIRTY */
+	ori	r0,r0,_PAGE_ACCESSED|_PAGE_HASHPTE
 #ifdef CONFIG_SMP
 	bne-	.Lhash_page_out		/* return if access not permitted */
 #else
@@ -179,12 +187,6 @@ _GLOBAL(add_hash_page)
 	mflr	r0
 	stw	r0,4(r1)
 
-	/* Convert context and va to VSID */
-	mulli	r3,r3,897*16		/* multiply context by context skew */
-	rlwinm	r0,r4,4,28,31		/* get ESID (top 4 bits of va) */
-	mulli	r0,r0,0x111		/* multiply by ESID skew */
-	add	r3,r3,r0		/* note create_hpte trims to 24 bits */
-
 #ifdef CONFIG_SMP
 	lwz	r8,TASK_CPU(r2)		/* to go in mmu_hash_lock */
 	oris	r8,r8,12
@@ -248,6 +250,12 @@ _GLOBAL(add_hash_page)
 	stwcx.	r5,0,r8
 	bne-	1b
 
+	/* Convert context and va to VSID */
+	mulli	r3,r3,897*16		/* multiply context by context skew */
+	rlwinm	r0,r4,4,28,31		/* get ESID (top 4 bits of va) */
+	mulli	r0,r0,0x111		/* multiply by ESID skew */
+	add	r3,r3,r0		/* note create_hpte trims to 24 bits */
+
 	bl	create_hpte
 
 9:
@@ -350,11 +358,6 @@ END_FTR_SECTION_IFCLR(CPU_FTR_NEED_COHERENT)
 	beq+	10f			/* no PTE: go look for an empty slot */
 	tlbie	r4
 
-	lis	r4, (htab_hash_searches - PAGE_OFFSET)@ha
-	lwz	r6, (htab_hash_searches - PAGE_OFFSET)@l(r4)
-	addi	r6,r6,1			/* count how many searches we do */
-	stw	r6, (htab_hash_searches - PAGE_OFFSET)@l(r4)
-
 	/* Search the primary PTEG for a PTE whose 1st (d)word matches r5 */
 	mtctr	r0
 	addi	r4,r3,-HPTE_SIZE
@@ -384,12 +387,6 @@ END_FTR_SECTION_IFCLR(CPU_FTR_NEED_COHERENT)
 	bdnzf	2,1b			/* loop while ctr != 0 && !cr0.eq */
 	beq+	.Lfound_empty
 
-	/* update counter of times that the primary PTEG is full */
-	lis	r4, (primary_pteg_full - PAGE_OFFSET)@ha
-	lwz	r6, (primary_pteg_full - PAGE_OFFSET)@l(r4)
-	addi	r6,r6,1
-	stw	r6, (primary_pteg_full - PAGE_OFFSET)@l(r4)
-
 	patch_site	0f, patch__hash_page_C
 	/* Search the secondary PTEG for an empty slot */
 	ori	r5,r5,PTE_H		/* set H (secondary hash) bit */
@@ -411,30 +408,14 @@ END_FTR_SECTION_IFCLR(CPU_FTR_NEED_COHERENT)
 	 * and we know there is a definite (although small) speed
 	 * advantage to putting the PTE in the primary PTEG, we always
 	 * put the PTE in the primary PTEG.
-	 *
-	 * In addition, we skip any slot that is mapping kernel text in
-	 * order to avoid a deadlock when not using BAT mappings if
-	 * trying to hash in the kernel hash code itself after it has
-	 * already taken the hash table lock. This works in conjunction
-	 * with pre-faulting of the kernel text.
-	 *
-	 * If the hash table bucket is full of kernel text entries, we'll
-	 * lockup here but that shouldn't happen
 	 */
 
-1:	lis	r4, (next_slot - PAGE_OFFSET)@ha	/* get next evict slot */
+	lis	r4, (next_slot - PAGE_OFFSET)@ha	/* get next evict slot */
 	lwz	r6, (next_slot - PAGE_OFFSET)@l(r4)
 	addi	r6,r6,HPTE_SIZE			/* search for candidate */
 	andi.	r6,r6,7*HPTE_SIZE
 	stw	r6,next_slot@l(r4)
 	add	r4,r3,r6
-	LDPTE	r0,HPTE_SIZE/2(r4)		/* get PTE second word */
-	clrrwi	r0,r0,12
-	lis	r6,etext@h
-	ori	r6,r6,etext@l			/* get etext */
-	tophys(r6,r6)
-	cmpl	cr0,r0,r6			/* compare and try again */
-	blt	1b
 
 #ifndef CONFIG_SMP
 	/* Store PTE in PTEG */
@@ -482,10 +463,6 @@ _ASM_NOKPROBE_SYMBOL(create_hpte)
 	.align	2
 next_slot:
 	.space	4
-primary_pteg_full:
-	.space	4
-htab_hash_searches:
-	.space	4
 	.previous
 
 /*
@@ -517,8 +494,9 @@ _GLOBAL(flush_hash_pages)
 	rlwimi	r5,r4,22,20,29
 #else
 	rlwimi	r5,r4,23,20,28
+	addi	r5,r5,PTE_FLAGS_OFFSET
 #endif
-1:	lwz	r0,PTE_FLAGS_OFFSET(r5)
+1:	lwz	r0,0(r5)
 	cmpwi	cr1,r6,1
 	andi.	r0,r0,_PAGE_HASHPTE
 	bne	2f
@@ -562,9 +540,6 @@ _GLOBAL(flush_hash_pages)
 	 * already clear, we're done (for this pte).  If not,
 	 * clear it (atomically) and proceed.  -- paulus.
 	 */
-#if (PTE_FLAGS_OFFSET != 0)
-	addi	r5,r5,PTE_FLAGS_OFFSET
-#endif
 33:	lwarx	r8,0,r5			/* fetch the pte flags word */
 	andi.	r0,r8,_PAGE_HASHPTE
 	beq	8f			/* done if HASHPTE is already clear */
@@ -633,77 +608,3 @@ _GLOBAL(flush_hash_pages)
 	.previous
 EXPORT_SYMBOL(flush_hash_pages)
 _ASM_NOKPROBE_SYMBOL(flush_hash_pages)
-
-/*
- * Flush an entry from the TLB
- */
-_GLOBAL(_tlbie)
-#ifdef CONFIG_SMP
-	lwz	r8,TASK_CPU(r2)
-	oris	r8,r8,11
-	mfmsr	r10
-	rlwinm	r0,r10,0,17,15		/* clear bit 16 (MSR_EE) */
-	rlwinm	r0,r0,0,28,26		/* clear DR */
-	mtmsr	r0
-	isync
-	lis	r9,mmu_hash_lock@h
-	ori	r9,r9,mmu_hash_lock@l
-	tophys(r9,r9)
-10:	lwarx	r7,0,r9
-	cmpwi	0,r7,0
-	bne-	10b
-	stwcx.	r8,0,r9
-	bne-	10b
-	eieio
-	tlbie	r3
-	sync
-	TLBSYNC
-	li	r0,0
-	stw	r0,0(r9)		/* clear mmu_hash_lock */
-	mtmsr	r10
-	isync
-#else /* CONFIG_SMP */
-	tlbie	r3
-	sync
-#endif /* CONFIG_SMP */
-	blr
-_ASM_NOKPROBE_SYMBOL(_tlbie)
-
-/*
- * Flush the entire TLB. 603/603e only
- */
-_GLOBAL(_tlbia)
-#if defined(CONFIG_SMP)
-	lwz	r8,TASK_CPU(r2)
-	oris	r8,r8,10
-	mfmsr	r10
-	rlwinm	r0,r10,0,17,15		/* clear bit 16 (MSR_EE) */
-	rlwinm	r0,r0,0,28,26		/* clear DR */
-	mtmsr	r0
-	isync
-	lis	r9,mmu_hash_lock@h
-	ori	r9,r9,mmu_hash_lock@l
-	tophys(r9,r9)
-10:	lwarx	r7,0,r9
-	cmpwi	0,r7,0
-	bne-	10b
-	stwcx.	r8,0,r9
-	bne-	10b
-#endif /* CONFIG_SMP */
-	li	r5, 32
-	lis	r4, KERNELBASE@h
-	mtctr	r5
-	sync
-0:	tlbie	r4
-	addi	r4, r4, 0x1000
-	bdnz	0b
-	sync
-#ifdef CONFIG_SMP
-	TLBSYNC
-	li	r0,0
-	stw	r0,0(r9)		/* clear mmu_hash_lock */
-	mtmsr	r10
-	isync
-#endif /* CONFIG_SMP */
-	blr
-_ASM_NOKPROBE_SYMBOL(_tlbia)