[PATCH AUTOSEL 5.14 31/99] cpuidle: pseries: Do not cap the CEDE0 latency in fixup_cede0_latency()

[PATCH AUTOSEL 5.14 31/99] cpuidle: pseries: Do not cap the CEDE0 latency in fixup_cede0_latency()

[Sasha Levin]

From: "Gautham R. Shenoy" <ego@linux.vnet.ibm.com>

[ Upstream commit 71737a6c2a8f801622d2b71567d1ec1e4c5b40b8 ]

Currently in fixup_cede0_latency() code, we perform the fixup the
CEDE(0) exit latency value only if minimum advertized extended CEDE
latency values are less than 10us. This was done so as to not break
the expected behaviour on POWER8 platforms where the advertised
latency was higher than the default 10us, which would delay the SMT
folding on the core.

However, after the earlier patch "cpuidle/pseries: Fixup CEDE0 latency
only for POWER10 onwards", we can be sure that the fixup of CEDE0
latency is going to happen only from POWER10 onwards. Hence
unconditionally use the minimum exit latency provided by the platform.

Signed-off-by: Gautham R. Shenoy <ego@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/1626676399-15975-3-git-send-email-ego@linux.vnet.ibm.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/cpuidle/cpuidle-pseries.c | 59 ++++++++++++++++---------------
 1 file changed, 30 insertions(+), 29 deletions(-)

diff --git a/drivers/cpuidle/cpuidle-pseries.c b/drivers/cpuidle/cpuidle-pseries.c
index a2b5c6f60cf0..18747e5287c8 100644
--- a/drivers/cpuidle/cpuidle-pseries.c
+++ b/drivers/cpuidle/cpuidle-pseries.c
@@ -346,11 +346,9 @@ static int pseries_cpuidle_driver_init(void)
 static void __init fixup_cede0_latency(void)
 {
 	struct xcede_latency_payload *payload;
-	u64 min_latency_us;
+	u64 min_xcede_latency_us = UINT_MAX;
 	int i;
 
-	min_latency_us = dedicated_states[1].exit_latency; // CEDE latency
-
 	if (parse_cede_parameters())
 		return;
 
@@ -358,42 +356,45 @@ static void __init fixup_cede0_latency(void)
 		nr_xcede_records);
 
 	payload = &xcede_latency_parameter.payload;
+
+	/*
+	 * The CEDE idle state maps to CEDE(0). While the hypervisor
+	 * does not advertise CEDE(0) exit latency values, it does
+	 * advertise the latency values of the extended CEDE states.
+	 * We use the lowest advertised exit latency value as a proxy
+	 * for the exit latency of CEDE(0).
+	 */
 	for (i = 0; i < nr_xcede_records; i++) {
 		struct xcede_latency_record *record = &payload->records[i];
+		u8 hint = record->hint;
 		u64 latency_tb = be64_to_cpu(record->latency_ticks);
 		u64 latency_us = DIV_ROUND_UP_ULL(tb_to_ns(latency_tb), NSEC_PER_USEC);
 
-		if (latency_us == 0)
-			pr_warn("cpuidle: xcede record %d has an unrealistic latency of 0us.\n", i);
-
-		if (latency_us < min_latency_us)
-			min_latency_us = latency_us;
-	}
-
-	/*
-	 * By default, we assume that CEDE(0) has exit latency 10us,
-	 * since there is no way for us to query from the platform.
-	 *
-	 * However, if the wakeup latency of an Extended CEDE state is
-	 * smaller than 10us, then we can be sure that CEDE(0)
-	 * requires no more than that.
-	 *
-	 * Perform the fix-up.
-	 */
-	if (min_latency_us < dedicated_states[1].exit_latency) {
 		/*
-		 * We set a minimum of 1us wakeup latency for cede0 to
-		 * distinguish it from snooze
+		 * We expect the exit latency of an extended CEDE
+		 * state to be non-zero, it to since it takes at least
+		 * a few nanoseconds to wakeup the idle CPU and
+		 * dispatch the virtual processor into the Linux
+		 * Guest.
+		 *
+		 * So we consider only non-zero value for performing
+		 * the fixup of CEDE(0) latency.
 		 */
-		u64 cede0_latency = 1;
+		if (latency_us == 0) {
+			pr_warn("cpuidle: Skipping xcede record %d [hint=%d]. Exit latency = 0us\n",
+				i, hint);
+			continue;
+		}
 
-		if (min_latency_us > cede0_latency)
-			cede0_latency = min_latency_us - 1;
+		if (latency_us < min_xcede_latency_us)
+			min_xcede_latency_us = latency_us;
+	}
 
-		dedicated_states[1].exit_latency = cede0_latency;
-		dedicated_states[1].target_residency = 10 * (cede0_latency);
+	if (min_xcede_latency_us != UINT_MAX) {
+		dedicated_states[1].exit_latency = min_xcede_latency_us;
+		dedicated_states[1].target_residency = 10 * (min_xcede_latency_us);
 		pr_info("cpuidle: Fixed up CEDE exit latency to %llu us\n",
-			cede0_latency);
+			min_xcede_latency_us);
 	}
 
 }
-- 
2.30.2

[PATCH AUTOSEL 5.14 32/99] powerpc: make the install target not depend on any build artifact

[Sasha Levin]

From: Masahiro Yamada <masahiroy@kernel.org>

[ Upstream commit 9bef456b20581e630ef9a13555ca04fed65a859d ]

The install target should not depend on any build artifact.

The reason is explained in commit 19514fc665ff ("arm, kbuild: make
"make install" not depend on vmlinux").

Change the PowerPC installation code in a similar way.

Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
Reviewed-by: Nick Desaulniers <ndesaulniers@google.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20210729141937.445051-2-masahiroy@kernel.org
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 arch/powerpc/boot/Makefile   |  2 +-
 arch/powerpc/boot/install.sh | 14 ++++++++++++++
 2 files changed, 15 insertions(+), 1 deletion(-)

diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile
index e312ea802aa6..b90e53e413c8 100644
--- a/arch/powerpc/boot/Makefile
+++ b/arch/powerpc/boot/Makefile
@@ -445,7 +445,7 @@ $(obj)/zImage.initrd:	$(addprefix $(obj)/, $(initrd-y))
 	$(Q)rm -f $@; ln $< $@
 
 # Only install the vmlinux
-install: $(CONFIGURE) $(addprefix $(obj)/, $(image-y))
+install:
 	sh -x $(srctree)/$(src)/install.sh "$(KERNELRELEASE)" vmlinux System.map "$(INSTALL_PATH)"
 
 # Install the vmlinux and other built boot targets.
diff --git a/arch/powerpc/boot/install.sh b/arch/powerpc/boot/install.sh
index b6a256bc96ee..8d669cf1ccda 100644
--- a/arch/powerpc/boot/install.sh
+++ b/arch/powerpc/boot/install.sh
@@ -21,6 +21,20 @@
 # Bail with error code if anything goes wrong
 set -e
 
+verify () {
+	if [ ! -f "$1" ]; then
+		echo ""                                                   1>&2
+		echo " *** Missing file: $1"                              1>&2
+		echo ' *** You need to run "make" before "make install".' 1>&2
+		echo ""                                                   1>&2
+		exit 1
+	fi
+}
+
+# Make sure the files actually exist
+verify "$2"
+verify "$3"
+
 # User may have a custom install script
 
 if [ -x ~/bin/${INSTALLKERNEL} ]; then exec ~/bin/${INSTALLKERNEL} "$@"; fi
-- 
2.30.2

[PATCH AUTOSEL 5.14 37/99] powerpc: Always inline radix_enabled() to fix build failure

[Sasha Levin]

From: Jordan Niethe <jniethe5@gmail.com>

[ Upstream commit 27fd1111051dc218e5b6cb2da5dbb3f342879ff1 ]

This is the same as commit acdad8fb4a15 ("powerpc: Force inlining of
mmu_has_feature to fix build failure") but for radix_enabled().  The
config in the linked bugzilla causes the following build failure:

  LD      .tmp_vmlinux.kallsyms1
  powerpc64-linux-ld: arch/powerpc/mm/pgtable.o: in function `.__ptep_set_access_flags':
  pgtable.c:(.text+0x17c): undefined reference to `.radix__ptep_set_access_flags'
  powerpc64-linux-ld: arch/powerpc/mm/pageattr.o: in function `.change_page_attr':
  pageattr.c:(.text+0xc0): undefined reference to `.radix__flush_tlb_kernel_range'
  etc.

This is due to radix_enabled() not being inlined. See extract from
building with -Winline:

  In file included from arch/powerpc/include/asm/lppaca.h:46,
                   from arch/powerpc/include/asm/paca.h:17,
                   from arch/powerpc/include/asm/current.h:13,
                   from include/linux/thread_info.h:23,
                   from include/asm-generic/preempt.h:5,
                   from ./arch/powerpc/include/generated/asm/preempt.h:1,
                   from include/linux/preempt.h:78,
                   from include/linux/spinlock.h:51,
                   from include/linux/mmzone.h:8,
                   from include/linux/gfp.h:6,
                   from arch/powerpc/mm/pgtable.c:21:
  arch/powerpc/include/asm/book3s/64/pgtable.h: In function '__ptep_set_access_flags':
  arch/powerpc/include/asm/mmu.h:327:20: error: inlining failed in call to 'radix_enabled': call is unlikely and code size would grow [-Werror=inline]

The code relies on constant folding of MMU_FTRS_POSSIBLE at buildtime
and elimination of non possible parts of code at compile time. For this
to work radix_enabled() must be inlined so make it __always_inline.

Reported-by: Erhard F. <erhard_f@mailbox.org>
Suggested-by: Michael Ellerman <mpe@ellerman.id.au>
Tested-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Jordan Niethe <jniethe5@gmail.com>
[mpe: Trimmed error messages in change log]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://bugzilla.kernel.org/show_bug.cgi?id=213803
Link: https://lore.kernel.org/r/20210804013724.514468-1-jniethe5@gmail.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 arch/powerpc/include/asm/mmu.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/powerpc/include/asm/mmu.h b/arch/powerpc/include/asm/mmu.h
index 27016b98ecb2..8abe8e42e045 100644
--- a/arch/powerpc/include/asm/mmu.h
+++ b/arch/powerpc/include/asm/mmu.h
@@ -324,7 +324,7 @@ static inline void assert_pte_locked(struct mm_struct *mm, unsigned long addr)
 }
 #endif /* !CONFIG_DEBUG_VM */
 
-static inline bool radix_enabled(void)
+static __always_inline bool radix_enabled(void)
 {
 	return mmu_has_feature(MMU_FTR_TYPE_RADIX);
 }
-- 
2.30.2

[PATCH AUTOSEL 5.14 38/99] KVM: PPC: Book3S HV: XICS: Fix mapping of passthrough interrupts

[Sasha Levin]

From: Cédric Le Goater <clg@kaod.org>

[ Upstream commit 1753081f2d445f9157550692fcc4221cd3ff0958 ]

PCI MSIs now live in an MSI domain but the underlying calls, which
will EOI the interrupt in real mode, need an HW IRQ number mapped in
the XICS IRQ domain. Grab it there.

Signed-off-by: Cédric Le Goater <clg@kaod.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20210701132750.1475580-31-clg@kaod.org
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 arch/powerpc/kvm/book3s_hv.c | 12 ++++++++++--
 1 file changed, 10 insertions(+), 2 deletions(-)

diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 085fb8ecbf68..1ca0a4f760bc 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -5328,6 +5328,7 @@ static int kvmppc_set_passthru_irq(struct kvm *kvm, int host_irq, int guest_gsi)
 	struct kvmppc_passthru_irqmap *pimap;
 	struct irq_chip *chip;
 	int i, rc = 0;
+	struct irq_data *host_data;
 
 	if (!kvm_irq_bypass)
 		return 1;
@@ -5392,7 +5393,14 @@ static int kvmppc_set_passthru_irq(struct kvm *kvm, int host_irq, int guest_gsi)
 	 * the KVM real mode handler.
 	 */
 	smp_wmb();
-	irq_map->r_hwirq = desc->irq_data.hwirq;
+
+	/*
+	 * The 'host_irq' number is mapped in the PCI-MSI domain but
+	 * the underlying calls, which will EOI the interrupt in real
+	 * mode, need an HW IRQ number mapped in the XICS IRQ domain.
+	 */
+	host_data = irq_domain_get_irq_data(irq_get_default_host(), host_irq);
+	irq_map->r_hwirq = (unsigned int)irqd_to_hwirq(host_data);
 
 	if (i == pimap->n_mapped)
 		pimap->n_mapped++;
@@ -5400,7 +5408,7 @@ static int kvmppc_set_passthru_irq(struct kvm *kvm, int host_irq, int guest_gsi)
 	if (xics_on_xive())
 		rc = kvmppc_xive_set_mapped(kvm, guest_gsi, desc);
 	else
-		kvmppc_xics_set_mapped(kvm, guest_gsi, desc->irq_data.hwirq);
+		kvmppc_xics_set_mapped(kvm, guest_gsi, irq_map->r_hwirq);
 	if (rc)
 		irq_map->r_hwirq = 0;
 
-- 
2.30.2

Re: [PATCH AUTOSEL 5.14 38/99] KVM: PPC: Book3S HV: XICS: Fix mapping of passthrough interrupts

[Cédric Le Goater]

On 9/10/21 2:14 AM, Sasha Levin wrote:
> From: Cédric Le Goater <clg@kaod.org>
> 
> [ Upstream commit 1753081f2d445f9157550692fcc4221cd3ff0958 ]
> 
> PCI MSIs now live in an MSI domain but the underlying calls, which
> will EOI the interrupt in real mode, need an HW IRQ number mapped in
> the XICS IRQ domain. Grab it there.
> 
> Signed-off-by: Cédric Le Goater <clg@kaod.org>
> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
> Link: https://lore.kernel.org/r/20210701132750.1475580-31-clg@kaod.org
> Signed-off-by: Sasha Levin <sashal@kernel.org>


Why are we backporting this patch in stable trees ?

It should be fine but to compile, we need a partial backport of commit
51be9e51a800 ("KVM: PPC: Book3S HV: XIVE: Fix mapping of passthrough 
interrupts") which exports irq_get_default_host().

Thanks,

C.


> ---
>  arch/powerpc/kvm/book3s_hv.c | 12 ++++++++++--
>  1 file changed, 10 insertions(+), 2 deletions(-)
> 
> diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
> index 085fb8ecbf68..1ca0a4f760bc 100644
> --- a/arch/powerpc/kvm/book3s_hv.c
> +++ b/arch/powerpc/kvm/book3s_hv.c
> @@ -5328,6 +5328,7 @@ static int kvmppc_set_passthru_irq(struct kvm *kvm, int host_irq, int guest_gsi)
>  	struct kvmppc_passthru_irqmap *pimap;
>  	struct irq_chip *chip;
>  	int i, rc = 0;
> +	struct irq_data *host_data;
>  
>  	if (!kvm_irq_bypass)
>  		return 1;
> @@ -5392,7 +5393,14 @@ static int kvmppc_set_passthru_irq(struct kvm *kvm, int host_irq, int guest_gsi)
>  	 * the KVM real mode handler.
>  	 */
>  	smp_wmb();
> -	irq_map->r_hwirq = desc->irq_data.hwirq;
> +
> +	/*
> +	 * The 'host_irq' number is mapped in the PCI-MSI domain but
> +	 * the underlying calls, which will EOI the interrupt in real
> +	 * mode, need an HW IRQ number mapped in the XICS IRQ domain.
> +	 */
> +	host_data = irq_domain_get_irq_data(irq_get_default_host(), host_irq);
> +	irq_map->r_hwirq = (unsigned int)irqd_to_hwirq(host_data);
>  
>  	if (i == pimap->n_mapped)
>  		pimap->n_mapped++;
> @@ -5400,7 +5408,7 @@ static int kvmppc_set_passthru_irq(struct kvm *kvm, int host_irq, int guest_gsi)
>  	if (xics_on_xive())
>  		rc = kvmppc_xive_set_mapped(kvm, guest_gsi, desc);
>  	else
> -		kvmppc_xics_set_mapped(kvm, guest_gsi, desc->irq_data.hwirq);
> +		kvmppc_xics_set_mapped(kvm, guest_gsi, irq_map->r_hwirq);
>  	if (rc)
>  		irq_map->r_hwirq = 0;
>  
> 

Re: [PATCH AUTOSEL 5.14 38/99] KVM: PPC: Book3S HV: XICS: Fix mapping of passthrough interrupts

[Sasha Levin]

On Fri, Sep 10, 2021 at 07:48:18AM +0200, Cédric Le Goater wrote:
>On 9/10/21 2:14 AM, Sasha Levin wrote:
>> From: Cédric Le Goater <clg@kaod.org>
>>
>> [ Upstream commit 1753081f2d445f9157550692fcc4221cd3ff0958 ]
>>
>> PCI MSIs now live in an MSI domain but the underlying calls, which
>> will EOI the interrupt in real mode, need an HW IRQ number mapped in
>> the XICS IRQ domain. Grab it there.
>>
>> Signed-off-by: Cédric Le Goater <clg@kaod.org>
>> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
>> Link: https://lore.kernel.org/r/20210701132750.1475580-31-clg@kaod.org
>> Signed-off-by: Sasha Levin <sashal@kernel.org>
>
>
>Why are we backporting this patch in stable trees ?
>
>It should be fine but to compile, we need a partial backport of commit
>51be9e51a800 ("KVM: PPC: Book3S HV: XIVE: Fix mapping of passthrough
>interrupts") which exports irq_get_default_host().

Or, I can drop it if it makes no sense?

-- 
Thanks,
Sasha

Re: [PATCH AUTOSEL 5.14 38/99] KVM: PPC: Book3S HV: XICS: Fix mapping of passthrough interrupts

[Cédric Le Goater]

On 9/11/21 4:35 PM, Sasha Levin wrote:
> On Fri, Sep 10, 2021 at 07:48:18AM +0200, Cédric Le Goater wrote:
>> On 9/10/21 2:14 AM, Sasha Levin wrote:
>>> From: Cédric Le Goater <clg@kaod.org>
>>>
>>> [ Upstream commit 1753081f2d445f9157550692fcc4221cd3ff0958 ]
>>>
>>> PCI MSIs now live in an MSI domain but the underlying calls, which
>>> will EOI the interrupt in real mode, need an HW IRQ number mapped in
>>> the XICS IRQ domain. Grab it there.
>>>
>>> Signed-off-by: Cédric Le Goater <clg@kaod.org>
>>> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
>>> Link: https://lore.kernel.org/r/20210701132750.1475580-31-clg@kaod.org
>>> Signed-off-by: Sasha Levin <sashal@kernel.org>
>>
>>
>> Why are we backporting this patch in stable trees ?
>>
>> It should be fine but to compile, we need a partial backport of commit
>> 51be9e51a800 ("KVM: PPC: Book3S HV: XIVE: Fix mapping of passthrough
>> interrupts") which exports irq_get_default_host().
> 
> Or, I can drop it if it makes no sense?

Yes I would. 

It makes sense only with the full patchset, the one reworking PCI MSI 
support in the PPC pSeries and PowerNV platforms.

Thanks,

C.

[PATCH AUTOSEL 5.14 68/99] powerpc/32: indirect function call use bctrl rather than blrl in ret_from_kernel_thread

[Sasha Levin]

From: Christophe Leroy <christophe.leroy@csgroup.eu>

[ Upstream commit 113ec9ccc8049c3772f0eab46b62c5d6654c09f7 ]

Copied from commit 89bbe4c798bc ("powerpc/64: indirect function call
use bctrl rather than blrl in ret_from_kernel_thread")

blrl is not recommended to use as an indirect function call, as it may
corrupt the link stack predictor.

This is not a performance critical path but this should be fixed for
consistency.

Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/91b1d242525307ceceec7ef6e832bfbacdd4501b.1629436472.git.christophe.leroy@csgroup.eu
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 arch/powerpc/kernel/entry_32.S | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
index 0273a1349006..61fdd53cdd9a 100644
--- a/arch/powerpc/kernel/entry_32.S
+++ b/arch/powerpc/kernel/entry_32.S
@@ -161,10 +161,10 @@ ret_from_fork:
 ret_from_kernel_thread:
 	REST_NVGPRS(r1)
 	bl	schedule_tail
-	mtlr	r14
+	mtctr	r14
 	mr	r3,r15
 	PPC440EP_ERR42
-	blrl
+	bctrl
 	li	r3,0
 	b	ret_from_syscall
 
-- 
2.30.2

[PATCH AUTOSEL 5.14 69/99] powerpc/booke: Avoid link stack corruption in several places

[Sasha Levin]

From: Christophe Leroy <christophe.leroy@csgroup.eu>

[ Upstream commit f5007dbf4da729baa850b33a64dc3cc53757bdf8 ]

Use bcl 20,31,+4 instead of bl in order to preserve link stack.

See commit c974809a26a1 ("powerpc/vdso: Avoid link stack corruption
in __get_datapage()") for details.

Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/e9fbc285eceb720e6c0e032ef47fe8b05f669b48.1629791751.git.christophe.leroy@csgroup.eu
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 arch/powerpc/include/asm/ppc_asm.h            | 2 +-
 arch/powerpc/kernel/exceptions-64e.S          | 6 +++---
 arch/powerpc/kernel/fsl_booke_entry_mapping.S | 8 ++++----
 arch/powerpc/kernel/head_44x.S                | 6 +++---
 arch/powerpc/kernel/head_fsl_booke.S          | 6 +++---
 arch/powerpc/mm/nohash/tlb_low.S              | 4 ++--
 6 files changed, 16 insertions(+), 16 deletions(-)

diff --git a/arch/powerpc/include/asm/ppc_asm.h b/arch/powerpc/include/asm/ppc_asm.h
index 116c1519728a..d5d7b8f1b021 100644
--- a/arch/powerpc/include/asm/ppc_asm.h
+++ b/arch/powerpc/include/asm/ppc_asm.h
@@ -259,7 +259,7 @@ GLUE(.,name):
 
 /* Be careful, this will clobber the lr register. */
 #define LOAD_REG_ADDR_PIC(reg, name)		\
-	bl	0f;				\
+	bcl	20,31,$+4;			\
 0:	mflr	reg;				\
 	addis	reg,reg,(name - 0b)@ha;		\
 	addi	reg,reg,(name - 0b)@l;
diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S
index 1401787b0b93..7e0943d9f9b0 100644
--- a/arch/powerpc/kernel/exceptions-64e.S
+++ b/arch/powerpc/kernel/exceptions-64e.S
@@ -1127,7 +1127,7 @@ found_iprot:
  * r3 = MAS0_TLBSEL (for the iprot array)
  * r4 = SPRN_TLBnCFG
  */
-	bl	invstr				/* Find our address */
+	bcl	20,31,$+4			/* Find our address */
 invstr:	mflr	r6				/* Make it accessible */
 	mfmsr	r7
 	rlwinm	r5,r7,27,31,31			/* extract MSR[IS] */
@@ -1196,7 +1196,7 @@ skpinv:	addi	r6,r6,1				/* Increment */
 	mfmsr	r6
 	xori	r6,r6,MSR_IS
 	mtspr	SPRN_SRR1,r6
-	bl	1f		/* Find our address */
+	bcl	20,31,$+4	/* Find our address */
 1:	mflr	r6
 	addi	r6,r6,(2f - 1b)
 	mtspr	SPRN_SRR0,r6
@@ -1256,7 +1256,7 @@ skpinv:	addi	r6,r6,1				/* Increment */
  * r4 = MAS0 w/TLBSEL & ESEL for the temp mapping
  */
 	/* Now we branch the new virtual address mapped by this entry */
-	bl	1f		/* Find our address */
+	bcl	20,31,$+4	/* Find our address */
 1:	mflr	r6
 	addi	r6,r6,(2f - 1b)
 	tovirt(r6,r6)
diff --git a/arch/powerpc/kernel/fsl_booke_entry_mapping.S b/arch/powerpc/kernel/fsl_booke_entry_mapping.S
index 8bccce6544b5..dedc17fac8f8 100644
--- a/arch/powerpc/kernel/fsl_booke_entry_mapping.S
+++ b/arch/powerpc/kernel/fsl_booke_entry_mapping.S
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 
 /* 1. Find the index of the entry we're executing in */
-	bl	invstr				/* Find our address */
+	bcl	20,31,$+4				/* Find our address */
 invstr:	mflr	r6				/* Make it accessible */
 	mfmsr	r7
 	rlwinm	r4,r7,27,31,31			/* extract MSR[IS] */
@@ -85,7 +85,7 @@ skpinv:	addi	r6,r6,1				/* Increment */
 	addi	r6,r6,10
 	slw	r6,r8,r6	/* convert to mask */
 
-	bl	1f		/* Find our address */
+	bcl	20,31,$+4	/* Find our address */
 1:	mflr	r7
 
 	mfspr	r8,SPRN_MAS3
@@ -117,7 +117,7 @@ skpinv:	addi	r6,r6,1				/* Increment */
 
 	xori	r6,r4,1
 	slwi	r6,r6,5		/* setup new context with other address space */
-	bl	1f		/* Find our address */
+	bcl	20,31,$+4	/* Find our address */
 1:	mflr	r9
 	rlwimi	r7,r9,0,20,31
 	addi	r7,r7,(2f - 1b)
@@ -207,7 +207,7 @@ next_tlb_setup:
 
 	lis	r7,MSR_KERNEL@h
 	ori	r7,r7,MSR_KERNEL@l
-	bl	1f			/* Find our address */
+	bcl	20,31,$+4		/* Find our address */
 1:	mflr	r9
 	rlwimi	r6,r9,0,20,31
 	addi	r6,r6,(2f - 1b)
diff --git a/arch/powerpc/kernel/head_44x.S b/arch/powerpc/kernel/head_44x.S
index ddc978a2d381..02d2928d1e01 100644
--- a/arch/powerpc/kernel/head_44x.S
+++ b/arch/powerpc/kernel/head_44x.S
@@ -70,7 +70,7 @@ _ENTRY(_start);
  * address.
  * r21 will be loaded with the physical runtime address of _stext
  */
-	bl	0f				/* Get our runtime address */
+	bcl	20,31,$+4			/* Get our runtime address */
 0:	mflr	r21				/* Make it accessible */
 	addis	r21,r21,(_stext - 0b)@ha
 	addi	r21,r21,(_stext - 0b)@l 	/* Get our current runtime base */
@@ -853,7 +853,7 @@ _GLOBAL(init_cpu_state)
 wmmucr:	mtspr	SPRN_MMUCR,r3			/* Put MMUCR */
 	sync
 
-	bl	invstr				/* Find our address */
+	bcl	20,31,$+4			/* Find our address */
 invstr:	mflr	r5				/* Make it accessible */
 	tlbsx	r23,0,r5			/* Find entry we are in */
 	li	r4,0				/* Start at TLB entry 0 */
@@ -1045,7 +1045,7 @@ head_start_47x:
 	sync
 
 	/* Find the entry we are running from */
-	bl	1f
+	bcl	20,31,$+4
 1:	mflr	r23
 	tlbsx	r23,0,r23
 	tlbre	r24,r23,0
diff --git a/arch/powerpc/kernel/head_fsl_booke.S b/arch/powerpc/kernel/head_fsl_booke.S
index 0f9642f36b49..dbf3b89e543c 100644
--- a/arch/powerpc/kernel/head_fsl_booke.S
+++ b/arch/powerpc/kernel/head_fsl_booke.S
@@ -79,7 +79,7 @@ _ENTRY(_start);
 	mr	r23,r3
 	mr	r25,r4
 
-	bl	0f
+	bcl	20,31,$+4
 0:	mflr	r8
 	addis	r3,r8,(is_second_reloc - 0b)@ha
 	lwz	r19,(is_second_reloc - 0b)@l(r3)
@@ -1132,7 +1132,7 @@ _GLOBAL(switch_to_as1)
 	bne	1b
 
 	/* Get the tlb entry used by the current running code */
-	bl	0f
+	bcl	20,31,$+4
 0:	mflr	r4
 	tlbsx	0,r4
 
@@ -1166,7 +1166,7 @@ _GLOBAL(switch_to_as1)
 _GLOBAL(restore_to_as0)
 	mflr	r0
 
-	bl	0f
+	bcl	20,31,$+4
 0:	mflr	r9
 	addi	r9,r9,1f - 0b
 
diff --git a/arch/powerpc/mm/nohash/tlb_low.S b/arch/powerpc/mm/nohash/tlb_low.S
index 4613bf8e9aae..5add4a51e51f 100644
--- a/arch/powerpc/mm/nohash/tlb_low.S
+++ b/arch/powerpc/mm/nohash/tlb_low.S
@@ -199,7 +199,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_476_DD2)
  * Touch enough instruction cache lines to ensure cache hits
  */
 1:	mflr	r9
-	bl	2f
+	bcl	20,31,$+4
 2:	mflr	r6
 	li	r7,32
 	PPC_ICBT(0,R6,R7)		/* touch next cache line */
@@ -414,7 +414,7 @@ _GLOBAL(loadcam_multi)
 	 * Set up temporary TLB entry that is the same as what we're
 	 * running from, but in AS=1.
 	 */
-	bl	1f
+	bcl	20,31,$+4
 1:	mflr	r6
 	tlbsx	0,r8
 	mfspr	r6,SPRN_MAS1
-- 
2.30.2

[PATCH AUTOSEL 5.14 70/99] powerpc: Avoid link stack corruption in misc asm functions

[Sasha Levin]

From: Christophe Leroy <christophe.leroy@csgroup.eu>

[ Upstream commit 33e1402435cb9f3021439a15935ea2dc69ec1844 ]

bl;mflr is used at several places to get code position.

Use bcl 20,31,+4 instead of bl in order to preserve link stack.

See commit c974809a26a1 ("powerpc/vdso: Avoid link stack corruption
in __get_datapage()") for details.

Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/c6eabb4fb6c156f75d56dcbcc6f243e5ac0fba42.1629791763.git.christophe.leroy@csgroup.eu
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 arch/powerpc/kernel/misc.S       |  2 +-
 arch/powerpc/kernel/misc_32.S    |  2 +-
 arch/powerpc/kernel/misc_64.S    |  2 +-
 arch/powerpc/kernel/reloc_32.S   |  2 +-
 arch/powerpc/kexec/relocate_32.S | 12 ++++++------
 5 files changed, 10 insertions(+), 10 deletions(-)

diff --git a/arch/powerpc/kernel/misc.S b/arch/powerpc/kernel/misc.S
index 5be96feccb55..fb7de3543c03 100644
--- a/arch/powerpc/kernel/misc.S
+++ b/arch/powerpc/kernel/misc.S
@@ -29,7 +29,7 @@ _GLOBAL(reloc_offset)
 	li	r3, 0
 _GLOBAL(add_reloc_offset)
 	mflr	r0
-	bl	1f
+	bcl	20,31,$+4
 1:	mflr	r5
 	PPC_LL	r4,(2f-1b)(r5)
 	subf	r5,r4,r5
diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S
index 39ab15419592..921d4198bfaa 100644
--- a/arch/powerpc/kernel/misc_32.S
+++ b/arch/powerpc/kernel/misc_32.S
@@ -67,7 +67,7 @@ _GLOBAL(reloc_got2)
 	srwi.	r8,r8,2
 	beqlr
 	mtctr	r8
-	bl	1f
+	bcl	20,31,$+4
 1:	mflr	r0
 	lis	r4,1b@ha
 	addi	r4,r4,1b@l
diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S
index 4b761a18a74d..d38a019b38e1 100644
--- a/arch/powerpc/kernel/misc_64.S
+++ b/arch/powerpc/kernel/misc_64.S
@@ -255,7 +255,7 @@ _GLOBAL(scom970_write)
  * Physical (hardware) cpu id should be in r3.
  */
 _GLOBAL(kexec_wait)
-	bl	1f
+	bcl	20,31,$+4
 1:	mflr	r5
 	addi	r5,r5,kexec_flag-1b
 
diff --git a/arch/powerpc/kernel/reloc_32.S b/arch/powerpc/kernel/reloc_32.S
index 10e96f3e22fe..0508c14b4c28 100644
--- a/arch/powerpc/kernel/reloc_32.S
+++ b/arch/powerpc/kernel/reloc_32.S
@@ -30,7 +30,7 @@ R_PPC_RELATIVE = 22
 _GLOBAL(relocate)
 
 	mflr	r0		/* Save our LR */
-	bl	0f		/* Find our current runtime address */
+	bcl	20,31,$+4	/* Find our current runtime address */
 0:	mflr	r12		/* Make it accessible */
 	mtlr	r0
 
diff --git a/arch/powerpc/kexec/relocate_32.S b/arch/powerpc/kexec/relocate_32.S
index 61946c19e07c..cf6e52bdf8d8 100644
--- a/arch/powerpc/kexec/relocate_32.S
+++ b/arch/powerpc/kexec/relocate_32.S
@@ -93,7 +93,7 @@ wmmucr:
 	 * Invalidate all the TLB entries except the current entry
 	 * where we are running from
 	 */
-	bl	0f				/* Find our address */
+	bcl	20,31,$+4			/* Find our address */
 0:	mflr	r5				/* Make it accessible */
 	tlbsx	r23,0,r5			/* Find entry we are in */
 	li	r4,0				/* Start at TLB entry 0 */
@@ -158,7 +158,7 @@ write_out:
 	/* Switch to other address space in MSR */
 	insrwi	r9, r7, 1, 26		/* Set MSR[IS] = r7 */
 
-	bl	1f
+	bcl	20,31,$+4
 1:	mflr	r8
 	addi	r8, r8, (2f-1b)		/* Find the target offset */
 
@@ -202,7 +202,7 @@ next_tlb:
 	li	r9,0
 	insrwi	r9, r7, 1, 26			/* Set MSR[IS] = r7 */
 
-	bl	1f
+	bcl	20,31,$+4
 1:	mflr	r8
 	and	r8, r8, r11			/* Get our offset within page */
 	addi	r8, r8, (2f-1b)
@@ -240,7 +240,7 @@ setup_map_47x:
 	sync
 
 	/* Find the entry we are running from */
-	bl	2f
+	bcl	20,31,$+4
 2:	mflr	r23
 	tlbsx	r23, 0, r23
 	tlbre	r24, r23, 0			/* TLB Word 0 */
@@ -296,7 +296,7 @@ clear_utlb_entry:
 	/* Update the msr to the new TS */
 	insrwi	r5, r7, 1, 26
 
-	bl	1f
+	bcl	20,31,$+4
 1:	mflr	r6
 	addi	r6, r6, (2f-1b)
 
@@ -355,7 +355,7 @@ write_utlb:
 	/* Defaults to 256M */
 	lis	r10, 0x1000
 
-	bl	1f
+	bcl	20,31,$+4
 1:	mflr	r4
 	addi	r4, r4, (2f-1b)			/* virtual address  of 2f */
 
-- 
2.30.2

[PATCH AUTOSEL 5.14 71/99] KVM: PPC: Book3S HV: Initialise vcpu MSR with MSR_ME

[Sasha Levin]

From: Nicholas Piggin <npiggin@gmail.com>

[ Upstream commit fd42b7b09c602c904452c0c3e5955ca21d8e387a ]

It is possible to create a VCPU without setting the MSR before running
it, which results in a warning in kvmhv_vcpu_entry_p9() that MSR_ME is
not set. This is pretty harmless because the MSR_ME bit is added to
HSRR1 before HRFID to guest, and a normal qemu guest doesn't hit it.

Initialise the vcpu MSR with MSR_ME set.

Reported-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20210811160134.904987-2-npiggin@gmail.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 arch/powerpc/kvm/book3s_hv.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 1ca0a4f760bc..18453aba86c4 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -2684,6 +2684,7 @@ static int kvmppc_core_vcpu_create_hv(struct kvm_vcpu *vcpu)
 	spin_lock_init(&vcpu->arch.vpa_update_lock);
 	spin_lock_init(&vcpu->arch.tbacct_lock);
 	vcpu->arch.busy_preempt = TB_NIL;
+	vcpu->arch.shregs.msr = MSR_ME;
 	vcpu->arch.intr_msr = MSR_SF | MSR_ME;
 
 	/*
-- 
2.30.2

[PATCH AUTOSEL 5.14 72/99] KVM: PPC: Book3S HV P9: Fixes for TM softpatch interrupt NIP

[Sasha Levin]

From: Nicholas Piggin <npiggin@gmail.com>

[ Upstream commit 4782e0cd0d184d727ad3b0cfe20d1d44d9f98239 ]

The softpatch interrupt sets HSRR0 to the faulting instruction +4, so
it should subtract 4 for the faulting instruction address in the case
it is a TM softpatch interrupt (the instruction was not executed) and
it was not emulated.

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20210811160134.904987-4-npiggin@gmail.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 arch/powerpc/kvm/book3s_hv_tm.c | 17 +++++++++++++++--
 1 file changed, 15 insertions(+), 2 deletions(-)

diff --git a/arch/powerpc/kvm/book3s_hv_tm.c b/arch/powerpc/kvm/book3s_hv_tm.c
index cc90b8b82329..e7c36f8bf205 100644
--- a/arch/powerpc/kvm/book3s_hv_tm.c
+++ b/arch/powerpc/kvm/book3s_hv_tm.c
@@ -46,6 +46,15 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu)
 	u64 newmsr, bescr;
 	int ra, rs;
 
+	/*
+	 * The TM softpatch interrupt sets NIP to the instruction following
+	 * the faulting instruction, which is not executed. Rewind nip to the
+	 * faulting instruction so it looks like a normal synchronous
+	 * interrupt, then update nip in the places where the instruction is
+	 * emulated.
+	 */
+	vcpu->arch.regs.nip -= 4;
+
 	/*
 	 * rfid, rfebb, and mtmsrd encode bit 31 = 0 since it's a reserved bit
 	 * in these instructions, so masking bit 31 out doesn't change these
@@ -67,7 +76,7 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu)
 			       (newmsr & MSR_TM)));
 		newmsr = sanitize_msr(newmsr);
 		vcpu->arch.shregs.msr = newmsr;
-		vcpu->arch.cfar = vcpu->arch.regs.nip - 4;
+		vcpu->arch.cfar = vcpu->arch.regs.nip;
 		vcpu->arch.regs.nip = vcpu->arch.shregs.srr0;
 		return RESUME_GUEST;
 
@@ -100,7 +109,7 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu)
 		vcpu->arch.bescr = bescr;
 		msr = (msr & ~MSR_TS_MASK) | MSR_TS_T;
 		vcpu->arch.shregs.msr = msr;
-		vcpu->arch.cfar = vcpu->arch.regs.nip - 4;
+		vcpu->arch.cfar = vcpu->arch.regs.nip;
 		vcpu->arch.regs.nip = vcpu->arch.ebbrr;
 		return RESUME_GUEST;
 
@@ -116,6 +125,7 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu)
 		newmsr = (newmsr & ~MSR_LE) | (msr & MSR_LE);
 		newmsr = sanitize_msr(newmsr);
 		vcpu->arch.shregs.msr = newmsr;
+		vcpu->arch.regs.nip += 4;
 		return RESUME_GUEST;
 
 	/* ignore bit 31, see comment above */
@@ -152,6 +162,7 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu)
 				msr = (msr & ~MSR_TS_MASK) | MSR_TS_S;
 		}
 		vcpu->arch.shregs.msr = msr;
+		vcpu->arch.regs.nip += 4;
 		return RESUME_GUEST;
 
 	/* ignore bit 31, see comment above */
@@ -189,6 +200,7 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu)
 		vcpu->arch.regs.ccr = (vcpu->arch.regs.ccr & 0x0fffffff) |
 			(((msr & MSR_TS_MASK) >> MSR_TS_S_LG) << 29);
 		vcpu->arch.shregs.msr &= ~MSR_TS_MASK;
+		vcpu->arch.regs.nip += 4;
 		return RESUME_GUEST;
 
 	/* ignore bit 31, see comment above */
@@ -220,6 +232,7 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu)
 		vcpu->arch.regs.ccr = (vcpu->arch.regs.ccr & 0x0fffffff) |
 			(((msr & MSR_TS_MASK) >> MSR_TS_S_LG) << 29);
 		vcpu->arch.shregs.msr = msr | MSR_TS_S;
+		vcpu->arch.regs.nip += 4;
 		return RESUME_GUEST;
 	}
 
-- 
2.30.2

[PATCH AUTOSEL 5.14 73/99] KVM: PPC: Book3S HV Nested: Fix TM softpatch HFAC interrupt emulation

[Sasha Levin]

From: Nicholas Piggin <npiggin@gmail.com>

[ Upstream commit d82b392d9b3556b63e3f9916cf057ea847e173a9 ]

Have the TM softpatch emulation code set up the HFAC interrupt and
return -1 in case an instruction was executed with HFSCR bits clear,
and have the interrupt exit handler fall through to the HFAC handler.
When the L0 is running a nested guest, this ensures the HFAC interrupt
is correctly passed up to the L1.

The "direct guest" exit handler will turn these into PROGILL program
interrupts so functionality in practice will be unchanged. But it's
possible an L1 would want to handle these in a different way.

Also rearrange the FAC interrupt emulation code to match the HFAC format
while here (mainly, adding the FSCR_INTR_CAUSE mask).

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20210811160134.904987-5-npiggin@gmail.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 arch/powerpc/include/asm/reg.h  |  3 ++-
 arch/powerpc/kvm/book3s_hv.c    | 35 ++++++++++++++++----------
 arch/powerpc/kvm/book3s_hv_tm.c | 44 ++++++++++++++++++---------------
 3 files changed, 48 insertions(+), 34 deletions(-)

diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index be85cf156a1f..e9d27265253b 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -415,6 +415,7 @@
 #define   FSCR_TAR	__MASK(FSCR_TAR_LG)
 #define   FSCR_EBB	__MASK(FSCR_EBB_LG)
 #define   FSCR_DSCR	__MASK(FSCR_DSCR_LG)
+#define   FSCR_INTR_CAUSE (ASM_CONST(0xFF) << 56)	/* interrupt cause */
 #define SPRN_HFSCR	0xbe	/* HV=1 Facility Status & Control Register */
 #define   HFSCR_PREFIX	__MASK(FSCR_PREFIX_LG)
 #define   HFSCR_MSGP	__MASK(FSCR_MSGP_LG)
@@ -426,7 +427,7 @@
 #define   HFSCR_DSCR	__MASK(FSCR_DSCR_LG)
 #define   HFSCR_VECVSX	__MASK(FSCR_VECVSX_LG)
 #define   HFSCR_FP	__MASK(FSCR_FP_LG)
-#define   HFSCR_INTR_CAUSE (ASM_CONST(0xFF) << 56)	/* interrupt cause */
+#define   HFSCR_INTR_CAUSE FSCR_INTR_CAUSE
 #define SPRN_TAR	0x32f	/* Target Address Register */
 #define SPRN_LPCR	0x13E	/* LPAR Control Register */
 #define   LPCR_VPM0		ASM_CONST(0x8000000000000000)
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 18453aba86c4..c364eeec410f 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -1679,6 +1679,21 @@ static int kvmppc_handle_exit_hv(struct kvm_vcpu *vcpu,
 			r = RESUME_GUEST;
 		}
 		break;
+
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+	case BOOK3S_INTERRUPT_HV_SOFTPATCH:
+		/*
+		 * This occurs for various TM-related instructions that
+		 * we need to emulate on POWER9 DD2.2.  We have already
+		 * handled the cases where the guest was in real-suspend
+		 * mode and was transitioning to transactional state.
+		 */
+		r = kvmhv_p9_tm_emulation(vcpu);
+		if (r != -1)
+			break;
+		fallthrough; /* go to facility unavailable handler */
+#endif
+
 	/*
 	 * This occurs if the guest (kernel or userspace), does something that
 	 * is prohibited by HFSCR.
@@ -1697,18 +1712,6 @@ static int kvmppc_handle_exit_hv(struct kvm_vcpu *vcpu,
 		}
 		break;
 
-#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
-	case BOOK3S_INTERRUPT_HV_SOFTPATCH:
-		/*
-		 * This occurs for various TM-related instructions that
-		 * we need to emulate on POWER9 DD2.2.  We have already
-		 * handled the cases where the guest was in real-suspend
-		 * mode and was transitioning to transactional state.
-		 */
-		r = kvmhv_p9_tm_emulation(vcpu);
-		break;
-#endif
-
 	case BOOK3S_INTERRUPT_HV_RM_HARD:
 		r = RESUME_PASSTHROUGH;
 		break;
@@ -1811,9 +1814,15 @@ static int kvmppc_handle_nested_exit(struct kvm_vcpu *vcpu)
 		 * mode and was transitioning to transactional state.
 		 */
 		r = kvmhv_p9_tm_emulation(vcpu);
-		break;
+		if (r != -1)
+			break;
+		fallthrough; /* go to facility unavailable handler */
 #endif
 
+	case BOOK3S_INTERRUPT_H_FAC_UNAVAIL:
+		r = RESUME_HOST;
+		break;
+
 	case BOOK3S_INTERRUPT_HV_RM_HARD:
 		vcpu->arch.trap = 0;
 		r = RESUME_GUEST;
diff --git a/arch/powerpc/kvm/book3s_hv_tm.c b/arch/powerpc/kvm/book3s_hv_tm.c
index e7c36f8bf205..866cadd70094 100644
--- a/arch/powerpc/kvm/book3s_hv_tm.c
+++ b/arch/powerpc/kvm/book3s_hv_tm.c
@@ -88,14 +88,15 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu)
 		}
 		/* check EBB facility is available */
 		if (!(vcpu->arch.hfscr & HFSCR_EBB)) {
-			/* generate an illegal instruction interrupt */
-			kvmppc_core_queue_program(vcpu, SRR1_PROGILL);
-			return RESUME_GUEST;
+			vcpu->arch.hfscr &= ~HFSCR_INTR_CAUSE;
+			vcpu->arch.hfscr |= (u64)FSCR_EBB_LG << 56;
+			vcpu->arch.trap = BOOK3S_INTERRUPT_H_FAC_UNAVAIL;
+			return -1; /* rerun host interrupt handler */
 		}
 		if ((msr & MSR_PR) && !(vcpu->arch.fscr & FSCR_EBB)) {
 			/* generate a facility unavailable interrupt */
-			vcpu->arch.fscr = (vcpu->arch.fscr & ~(0xffull << 56)) |
-				((u64)FSCR_EBB_LG << 56);
+			vcpu->arch.fscr &= ~FSCR_INTR_CAUSE;
+			vcpu->arch.fscr |= (u64)FSCR_EBB_LG << 56;
 			kvmppc_book3s_queue_irqprio(vcpu, BOOK3S_INTERRUPT_FAC_UNAVAIL);
 			return RESUME_GUEST;
 		}
@@ -138,14 +139,15 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu)
 		}
 		/* check for TM disabled in the HFSCR or MSR */
 		if (!(vcpu->arch.hfscr & HFSCR_TM)) {
-			/* generate an illegal instruction interrupt */
-			kvmppc_core_queue_program(vcpu, SRR1_PROGILL);
-			return RESUME_GUEST;
+			vcpu->arch.hfscr &= ~HFSCR_INTR_CAUSE;
+			vcpu->arch.hfscr |= (u64)FSCR_TM_LG << 56;
+			vcpu->arch.trap = BOOK3S_INTERRUPT_H_FAC_UNAVAIL;
+			return -1; /* rerun host interrupt handler */
 		}
 		if (!(msr & MSR_TM)) {
 			/* generate a facility unavailable interrupt */
-			vcpu->arch.fscr = (vcpu->arch.fscr & ~(0xffull << 56)) |
-				((u64)FSCR_TM_LG << 56);
+			vcpu->arch.fscr &= ~FSCR_INTR_CAUSE;
+			vcpu->arch.fscr |= (u64)FSCR_TM_LG << 56;
 			kvmppc_book3s_queue_irqprio(vcpu,
 						BOOK3S_INTERRUPT_FAC_UNAVAIL);
 			return RESUME_GUEST;
@@ -169,14 +171,15 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu)
 	case (PPC_INST_TRECLAIM & PO_XOP_OPCODE_MASK):
 		/* check for TM disabled in the HFSCR or MSR */
 		if (!(vcpu->arch.hfscr & HFSCR_TM)) {
-			/* generate an illegal instruction interrupt */
-			kvmppc_core_queue_program(vcpu, SRR1_PROGILL);
-			return RESUME_GUEST;
+			vcpu->arch.hfscr &= ~HFSCR_INTR_CAUSE;
+			vcpu->arch.hfscr |= (u64)FSCR_TM_LG << 56;
+			vcpu->arch.trap = BOOK3S_INTERRUPT_H_FAC_UNAVAIL;
+			return -1; /* rerun host interrupt handler */
 		}
 		if (!(msr & MSR_TM)) {
 			/* generate a facility unavailable interrupt */
-			vcpu->arch.fscr = (vcpu->arch.fscr & ~(0xffull << 56)) |
-				((u64)FSCR_TM_LG << 56);
+			vcpu->arch.fscr &= ~FSCR_INTR_CAUSE;
+			vcpu->arch.fscr |= (u64)FSCR_TM_LG << 56;
 			kvmppc_book3s_queue_irqprio(vcpu,
 						BOOK3S_INTERRUPT_FAC_UNAVAIL);
 			return RESUME_GUEST;
@@ -208,14 +211,15 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu)
 		/* XXX do we need to check for PR=0 here? */
 		/* check for TM disabled in the HFSCR or MSR */
 		if (!(vcpu->arch.hfscr & HFSCR_TM)) {
-			/* generate an illegal instruction interrupt */
-			kvmppc_core_queue_program(vcpu, SRR1_PROGILL);
-			return RESUME_GUEST;
+			vcpu->arch.hfscr &= ~HFSCR_INTR_CAUSE;
+			vcpu->arch.hfscr |= (u64)FSCR_TM_LG << 56;
+			vcpu->arch.trap = BOOK3S_INTERRUPT_H_FAC_UNAVAIL;
+			return -1; /* rerun host interrupt handler */
 		}
 		if (!(msr & MSR_TM)) {
 			/* generate a facility unavailable interrupt */
-			vcpu->arch.fscr = (vcpu->arch.fscr & ~(0xffull << 56)) |
-				((u64)FSCR_TM_LG << 56);
+			vcpu->arch.fscr &= ~FSCR_INTR_CAUSE;
+			vcpu->arch.fscr |= (u64)FSCR_TM_LG << 56;
 			kvmppc_book3s_queue_irqprio(vcpu,
 						BOOK3S_INTERRUPT_FAC_UNAVAIL);
 			return RESUME_GUEST;
-- 
2.30.2

[PATCH AUTOSEL 5.14 78/99] powerpc/pseries/iommu: Allow DDW windows starting at 0x00

[Sasha Levin]

From: Leonardo Bras <leobras.c@gmail.com>

[ Upstream commit 2ca73c54ce24489518a56d816331b774044c2445 ]

enable_ddw() currently returns the address of the DMA window, which is
considered invalid if has the value 0x00.

Also, it only considers valid an address returned from find_existing_ddw
if it's not 0x00.

Changing this behavior makes sense, given the users of enable_ddw() only
need to know if direct mapping is possible. It can also allow a DMA window
starting at 0x00 to be used.

This will be helpful for using a DDW with indirect mapping, as the window
address will be different than 0x00, but it will not map the whole
partition.

Signed-off-by: Leonardo Bras <leobras.c@gmail.com>
Reviewed-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Reviewed-by: Frederic Barrat <fbarrat@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20210817063929.38701-6-leobras.c@gmail.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 arch/powerpc/platforms/pseries/iommu.c | 36 +++++++++++++-------------
 1 file changed, 18 insertions(+), 18 deletions(-)

diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c
index 0c55b991f665..a189178ca8e0 100644
--- a/arch/powerpc/platforms/pseries/iommu.c
+++ b/arch/powerpc/platforms/pseries/iommu.c
@@ -843,25 +843,26 @@ static void remove_ddw(struct device_node *np, bool remove_prop)
 			np, ret);
 }
 
-static u64 find_existing_ddw(struct device_node *pdn, int *window_shift)
+static bool find_existing_ddw(struct device_node *pdn, u64 *dma_addr, int *window_shift)
 {
 	struct direct_window *window;
 	const struct dynamic_dma_window_prop *direct64;
-	u64 dma_addr = 0;
+	bool found = false;
 
 	spin_lock(&direct_window_list_lock);
 	/* check if we already created a window and dupe that config if so */
 	list_for_each_entry(window, &direct_window_list, list) {
 		if (window->device == pdn) {
 			direct64 = window->prop;
-			dma_addr = be64_to_cpu(direct64->dma_base);
+			*dma_addr = be64_to_cpu(direct64->dma_base);
 			*window_shift = be32_to_cpu(direct64->window_shift);
+			found = true;
 			break;
 		}
 	}
 	spin_unlock(&direct_window_list_lock);
 
-	return dma_addr;
+	return found;
 }
 
 static int find_existing_ddw_windows(void)
@@ -1139,20 +1140,20 @@ static int iommu_get_page_shift(u32 query_page_size)
  * pdn: the parent pe node with the ibm,dma_window property
  * Future: also check if we can remap the base window for our base page size
  *
- * returns the dma offset for use by the direct mapped DMA code.
+ * returns true if can map all pages (direct mapping), false otherwise..
  */
-static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn)
+static bool enable_ddw(struct pci_dev *dev, struct device_node *pdn)
 {
 	int len = 0, ret;
 	int max_ram_len = order_base_2(ddw_memory_hotplug_max());
 	struct ddw_query_response query;
 	struct ddw_create_response create;
 	int page_shift;
-	u64 dma_addr;
 	struct device_node *dn;
 	u32 ddw_avail[DDW_APPLICABLE_SIZE];
 	struct direct_window *window;
 	struct property *win64;
+	bool ddw_enabled = false;
 	struct dynamic_dma_window_prop *ddwprop;
 	struct failed_ddw_pdn *fpdn;
 	bool default_win_removed = false;
@@ -1164,9 +1165,10 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn)
 
 	mutex_lock(&direct_window_init_mutex);
 
-	dma_addr = find_existing_ddw(pdn, &len);
-	if (dma_addr != 0)
+	if (find_existing_ddw(pdn, &dev->dev.archdata.dma_offset, &len)) {
+		ddw_enabled = true;
 		goto out_unlock;
+	}
 
 	/*
 	 * If we already went through this for a previous function of
@@ -1322,7 +1324,8 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn)
 	list_add(&window->list, &direct_window_list);
 	spin_unlock(&direct_window_list_lock);
 
-	dma_addr = be64_to_cpu(ddwprop->dma_base);
+	dev->dev.archdata.dma_offset = be64_to_cpu(ddwprop->dma_base);
+	ddw_enabled = true;
 	goto out_unlock;
 
 out_free_window:
@@ -1354,10 +1357,10 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn)
 	 * as RAM, then we failed to create a window to cover persistent
 	 * memory and need to set the DMA limit.
 	 */
-	if (pmem_present && dma_addr && (len == max_ram_len))
-		dev->dev.bus_dma_limit = dma_addr + (1ULL << len);
+	if (pmem_present && ddw_enabled && (len == max_ram_len))
+		dev->dev.bus_dma_limit = dev->dev.archdata.dma_offset + (1ULL << len);
 
-	return dma_addr;
+	return ddw_enabled;
 }
 
 static void pci_dma_dev_setup_pSeriesLP(struct pci_dev *dev)
@@ -1436,11 +1439,8 @@ static bool iommu_bypass_supported_pSeriesLP(struct pci_dev *pdev, u64 dma_mask)
 			break;
 	}
 
-	if (pdn && PCI_DN(pdn)) {
-		pdev->dev.archdata.dma_offset = enable_ddw(pdev, pdn);
-		if (pdev->dev.archdata.dma_offset)
-			return true;
-	}
+	if (pdn && PCI_DN(pdn))
+		return enable_ddw(pdev, pdn);
 
 	return false;
 }
-- 
2.30.2