* [PATCH] powerpc/features: Remove CPU_FTR_NODSISRALIGN
From: Christophe Leroy @ 2020-10-12 8:03 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman
Cc: linuxppc-dev, linux-kernel
CPU_FTR_NODSISRALIGN has not been used since
commit 31bfdb036f12 ("powerpc: Use instruction emulation
infrastructure to handle alignment faults")
Remove it.
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
---
arch/powerpc/include/asm/cputable.h | 22 ++++++++++------------
arch/powerpc/kernel/dt_cpu_ftrs.c | 8 --------
arch/powerpc/kernel/prom.c | 2 +-
3 files changed, 11 insertions(+), 21 deletions(-)
diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h
index 9780c55f9811..accdc1286f37 100644
--- a/arch/powerpc/include/asm/cputable.h
+++ b/arch/powerpc/include/asm/cputable.h
@@ -137,7 +137,6 @@ static inline void cpu_feature_keys_init(void) { }
#define CPU_FTR_DBELL ASM_CONST(0x00000004)
#define CPU_FTR_CAN_NAP ASM_CONST(0x00000008)
#define CPU_FTR_DEBUG_LVL_EXC ASM_CONST(0x00000010)
-#define CPU_FTR_NODSISRALIGN ASM_CONST(0x00000020)
#define CPU_FTR_FPU_UNAVAILABLE ASM_CONST(0x00000040)
#define CPU_FTR_LWSYNC ASM_CONST(0x00000080)
#define CPU_FTR_NOEXECUTE ASM_CONST(0x00000100)
@@ -219,7 +218,7 @@ static inline void cpu_feature_keys_init(void) { }
#ifndef __ASSEMBLY__
-#define CPU_FTR_PPCAS_ARCH_V2 (CPU_FTR_NOEXECUTE | CPU_FTR_NODSISRALIGN)
+#define CPU_FTR_PPCAS_ARCH_V2 (CPU_FTR_NOEXECUTE)
#define MMU_FTR_PPCAS_ARCH_V2 (MMU_FTR_TLBIEL | MMU_FTR_16M_PAGE)
@@ -378,33 +377,33 @@ static inline void cpu_feature_keys_init(void) { }
CPU_FTR_COMMON | CPU_FTR_FPU_UNAVAILABLE | CPU_FTR_NOEXECUTE)
#define CPU_FTRS_CLASSIC32 (CPU_FTR_COMMON)
#define CPU_FTRS_8XX (CPU_FTR_NOEXECUTE)
-#define CPU_FTRS_40X (CPU_FTR_NODSISRALIGN | CPU_FTR_NOEXECUTE)
-#define CPU_FTRS_44X (CPU_FTR_NODSISRALIGN | CPU_FTR_NOEXECUTE)
-#define CPU_FTRS_440x6 (CPU_FTR_NODSISRALIGN | CPU_FTR_NOEXECUTE | \
+#define CPU_FTRS_40X (CPU_FTR_NOEXECUTE)
+#define CPU_FTRS_44X (CPU_FTR_NOEXECUTE)
+#define CPU_FTRS_440x6 (CPU_FTR_NOEXECUTE | \
CPU_FTR_INDEXED_DCR)
#define CPU_FTRS_47X (CPU_FTRS_440x6)
#define CPU_FTRS_E200 (CPU_FTR_SPE_COMP | \
- CPU_FTR_NODSISRALIGN | CPU_FTR_COHERENT_ICACHE | \
+ CPU_FTR_COHERENT_ICACHE | \
CPU_FTR_NOEXECUTE | \
CPU_FTR_DEBUG_LVL_EXC)
#define CPU_FTRS_E500 (CPU_FTR_MAYBE_CAN_DOZE | \
- CPU_FTR_SPE_COMP | CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_NODSISRALIGN | \
+ CPU_FTR_SPE_COMP | CPU_FTR_MAYBE_CAN_NAP | \
CPU_FTR_NOEXECUTE)
#define CPU_FTRS_E500_2 (CPU_FTR_MAYBE_CAN_DOZE | \
CPU_FTR_SPE_COMP | CPU_FTR_MAYBE_CAN_NAP | \
- CPU_FTR_NODSISRALIGN | CPU_FTR_NOEXECUTE)
-#define CPU_FTRS_E500MC (CPU_FTR_NODSISRALIGN | \
+ CPU_FTR_NOEXECUTE)
+#define CPU_FTRS_E500MC ( \
CPU_FTR_LWSYNC | CPU_FTR_NOEXECUTE | \
CPU_FTR_DBELL | CPU_FTR_DEBUG_LVL_EXC | CPU_FTR_EMB_HV)
/*
* e5500/e6500 erratum A-006958 is a timebase bug that can use the
* same workaround as CPU_FTR_CELL_TB_BUG.
*/
-#define CPU_FTRS_E5500 (CPU_FTR_NODSISRALIGN | \
+#define CPU_FTRS_E5500 ( \
CPU_FTR_LWSYNC | CPU_FTR_NOEXECUTE | \
CPU_FTR_DBELL | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD | \
CPU_FTR_DEBUG_LVL_EXC | CPU_FTR_EMB_HV | CPU_FTR_CELL_TB_BUG)
-#define CPU_FTRS_E6500 (CPU_FTR_NODSISRALIGN | \
+#define CPU_FTRS_E6500 ( \
CPU_FTR_LWSYNC | CPU_FTR_NOEXECUTE | \
CPU_FTR_DBELL | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD | \
CPU_FTR_DEBUG_LVL_EXC | CPU_FTR_EMB_HV | CPU_FTR_ALTIVEC_COMP | \
@@ -554,7 +553,6 @@ enum {
#define CPU_FTRS_DT_CPU_BASE \
(CPU_FTR_LWSYNC | \
CPU_FTR_FPU_UNAVAILABLE | \
- CPU_FTR_NODSISRALIGN | \
CPU_FTR_NOEXECUTE | \
CPU_FTR_COHERENT_ICACHE | \
CPU_FTR_STCX_CHECKS_ADDRESS | \
diff --git a/arch/powerpc/kernel/dt_cpu_ftrs.c b/arch/powerpc/kernel/dt_cpu_ftrs.c
index 1098863e17ee..c598961d9f15 100644
--- a/arch/powerpc/kernel/dt_cpu_ftrs.c
+++ b/arch/powerpc/kernel/dt_cpu_ftrs.c
@@ -273,13 +273,6 @@ static int __init feat_enable_idle_nap(struct dt_cpu_feature *f)
return 1;
}
-static int __init feat_enable_align_dsisr(struct dt_cpu_feature *f)
-{
- cur_cpu_spec->cpu_features &= ~CPU_FTR_NODSISRALIGN;
-
- return 1;
-}
-
static int __init feat_enable_idle_stop(struct dt_cpu_feature *f)
{
u64 lpcr;
@@ -641,7 +634,6 @@ static struct dt_cpu_feature_match __initdata
{"tm-suspend-hypervisor-assist", feat_enable, CPU_FTR_P9_TM_HV_ASSIST},
{"tm-suspend-xer-so-bug", feat_enable, CPU_FTR_P9_TM_XER_SO_BUG},
{"idle-nap", feat_enable_idle_nap, 0},
- {"alignment-interrupt-dsisr", feat_enable_align_dsisr, 0},
{"idle-stop", feat_enable_idle_stop, 0},
{"machine-check-power8", feat_enable_mce_power8, 0},
{"performance-monitor-power8", feat_enable_pmu_power8, 0},
diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c
index c1545f22c077..a5a5acb627fe 100644
--- a/arch/powerpc/kernel/prom.c
+++ b/arch/powerpc/kernel/prom.c
@@ -165,7 +165,7 @@ static struct ibm_pa_feature {
#ifdef CONFIG_PPC_RADIX_MMU
{ .pabyte = 40, .pabit = 0, .mmu_features = MMU_FTR_TYPE_RADIX | MMU_FTR_GTSE },
#endif
- { .pabyte = 1, .pabit = 1, .invert = 1, .cpu_features = CPU_FTR_NODSISRALIGN },
+ { .pabyte = 1, .pabit = 1, .invert = 1, },
{ .pabyte = 5, .pabit = 0, .cpu_features = CPU_FTR_REAL_LE,
.cpu_user_ftrs = PPC_FEATURE_TRUE_LE },
/*
--
2.25.0
^ permalink raw reply related
* [PATCH] powerpc/mm: Remove useless #ifndef CPU_FTR_COHERENT_ICACHE in mem.c
From: Christophe Leroy @ 2020-10-12 8:02 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman
Cc: linuxppc-dev, linux-kernel
Since commit 10b35d9978ac ("[PATCH] powerpc: merged asm/cputable.h"),
CPU_FTR_COHERENT_ICACHE has always been defined.
Remove the #ifndef CPU_FTR_COHERENT_ICACHE block.
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
---
arch/powerpc/mm/mem.c | 5 -----
1 file changed, 5 deletions(-)
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index b7586d8c835b..2708d40c38e4 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -53,11 +53,6 @@
#include <mm/mmu_decl.h>
-#ifndef CPU_FTR_COHERENT_ICACHE
-#define CPU_FTR_COHERENT_ICACHE 0 /* XXX for now */
-#define CPU_FTR_NOEXECUTE 0
-#endif
-
unsigned long long memory_limit;
bool init_mem_is_free;
--
2.25.0
^ permalink raw reply related
* [PATCH] powerpc/feature: Add CPU_FTR_NOEXECUTE to G2_LE
From: Christophe Leroy @ 2020-10-12 8:02 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman
Cc: linuxppc-dev, linux-kernel
G2_LE has a 603 core, add CPU_FTR_NOEXECUTE.
Fixes: 385e89d5b20f ("powerpc/mm: add exec protection on powerpc 603")
Cc: stable@vger.kernel.org
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
---
arch/powerpc/include/asm/cputable.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h
index c596bab134e2..9780c55f9811 100644
--- a/arch/powerpc/include/asm/cputable.h
+++ b/arch/powerpc/include/asm/cputable.h
@@ -369,7 +369,7 @@ static inline void cpu_feature_keys_init(void) { }
CPU_FTR_PPC_LE | CPU_FTR_NEED_PAIRED_STWCX)
#define CPU_FTRS_82XX (CPU_FTR_COMMON | CPU_FTR_MAYBE_CAN_DOZE | CPU_FTR_NOEXECUTE)
#define CPU_FTRS_G2_LE (CPU_FTR_COMMON | CPU_FTR_MAYBE_CAN_DOZE | \
- CPU_FTR_MAYBE_CAN_NAP)
+ CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_NOEXECUTE)
#define CPU_FTRS_E300 (CPU_FTR_MAYBE_CAN_DOZE | \
CPU_FTR_MAYBE_CAN_NAP | \
CPU_FTR_COMMON | CPU_FTR_NOEXECUTE)
--
2.25.0
^ permalink raw reply related
* [PATCH] powerpc/feature: Fix CPU_FTRS_ALWAYS by removing CPU_FTRS_GENERIC_32
From: Christophe Leroy @ 2020-10-12 8:01 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman
Cc: linuxppc-dev, linux-kernel
On 8xx, we get the following features:
[ 0.000000] cpu_features = 0x0000000000000100
[ 0.000000] possible = 0x0000000000000120
[ 0.000000] always = 0x0000000000000000
This is not correct. As CONFIG_PPC_8xx is mutually exclusive with all
other configurations, the three lines should be equal.
The problem is due to CPU_FTRS_GENERIC_32 which is taken when
CONFIG_BOOK3S_32 is NOT selected. This CPU_FTRS_GENERIC_32 is
pointless because there is no generic configuration supporting
all 32 bits but book3s/32.
Remove this pointless generic features definition to unbreak the
calculation of 'possible' features and 'always' features.
Fixes: 76bc080ef5a3 ("[POWERPC] Make default cputable entries reflect selected CPU family")
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
---
arch/powerpc/include/asm/cputable.h | 5 -----
1 file changed, 5 deletions(-)
diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h
index 93bc70d4c9a1..c596bab134e2 100644
--- a/arch/powerpc/include/asm/cputable.h
+++ b/arch/powerpc/include/asm/cputable.h
@@ -409,7 +409,6 @@ static inline void cpu_feature_keys_init(void) { }
CPU_FTR_DBELL | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD | \
CPU_FTR_DEBUG_LVL_EXC | CPU_FTR_EMB_HV | CPU_FTR_ALTIVEC_COMP | \
CPU_FTR_CELL_TB_BUG | CPU_FTR_SMT)
-#define CPU_FTRS_GENERIC_32 (CPU_FTR_COMMON | CPU_FTR_NODSISRALIGN)
/* 64-bit CPUs */
#define CPU_FTRS_PPC970 (CPU_FTR_LWSYNC | \
@@ -520,8 +519,6 @@ enum {
CPU_FTRS_7447 | CPU_FTRS_7447A | CPU_FTRS_82XX |
CPU_FTRS_G2_LE | CPU_FTRS_E300 | CPU_FTRS_E300C2 |
CPU_FTRS_CLASSIC32 |
-#else
- CPU_FTRS_GENERIC_32 |
#endif
#ifdef CONFIG_PPC_8xx
CPU_FTRS_8XX |
@@ -596,8 +593,6 @@ enum {
CPU_FTRS_7447 & CPU_FTRS_7447A & CPU_FTRS_82XX &
CPU_FTRS_G2_LE & CPU_FTRS_E300 & CPU_FTRS_E300C2 &
CPU_FTRS_CLASSIC32 &
-#else
- CPU_FTRS_GENERIC_32 &
#endif
#ifdef CONFIG_PPC_8xx
CPU_FTRS_8XX &
--
2.25.0
^ permalink raw reply related
* Re: [PATCH RFC PKS/PMEM 48/58] drivers/md: Utilize new kmap_thread()
From: Coly Li @ 2020-10-12 7:40 UTC (permalink / raw)
To: Ira Weiny
Cc: linux-aio, linux-efi, kvm, linux-doc, Peter Zijlstra, linux-mmc,
Dave Hansen, dri-devel, linux-mm, target-devel, linux-mtd,
linux-kselftest, samba-technical, Thomas Gleixner, drbd-dev,
devel, linux-cifs, linux-nilfs, linux-scsi, linux-nvdimm,
linux-rdma, x86, ceph-devel, amd-gfx, io-uring, cluster-devel,
Ingo Molnar, intel-wired-lan, xen-devel, linux-ext4,
Kent Overstreet, Fenghua Yu, linux-afs, linux-um, intel-gfx,
ecryptfs, linux-erofs, reiserfs-devel, linux-block, linux-bcache,
Borislav Petkov, Andy Lutomirski, Dan Williams, Andrew Morton,
linux-cachefs, linux-nfs, linux-ntfs-dev, netdev, kexec,
linux-kernel, linux-f2fs-devel, linux-fsdevel, bpf, linuxppc-dev,
linux-btrfs
In-Reply-To: <20201012052817.GZ2046448@iweiny-DESK2.sc.intel.com>
On 2020/10/12 13:28, Ira Weiny wrote:
> On Sat, Oct 10, 2020 at 10:20:34AM +0800, Coly Li wrote:
>> On 2020/10/10 03:50, ira.weiny@intel.com wrote:
>>> From: Ira Weiny <ira.weiny@intel.com>
>>>
>>> These kmap() calls are localized to a single thread. To avoid the over
>>> head of global PKRS updates use the new kmap_thread() call.
>>>
>>
>> Hi Ira,
>>
>> There were a number of options considered.
>>
>> 1) Attempt to change all the thread local kmap() calls to kmap_atomic()
>> 2) Introduce a flags parameter to kmap() to indicate if the mapping
>> should be global or not
>> 3) Change ~20-30 call sites to 'kmap_global()' to indicate that they
>> require a global mapping of the pages
>> 4) Change ~209 call sites to 'kmap_thread()' to indicate that the
>> mapping is to be used within that thread of execution only
>>
>>
>> I copied the above information from patch 00/58 to this message. The
>> idea behind kmap_thread() is fine to me, but as you said the new api is
>> very easy to be missed in new code (even for me). I would like to be
>> supportive to option 2) introduce a flag to kmap(), then we won't forget
>> the new thread-localized kmap method, and people won't ask why a
>> _thread() function is called but no kthread created.
>
> Thanks for the feedback.
>
> I'm going to hold off making any changes until others weigh in. FWIW, I kind
> of like option 2 as well. But there is already kmap_atomic() so it seemed like
> kmap_XXXX() was more in line with the current API.
I understand it now, the idea is fine to me.
Acked-by: Coly Li <colyli@suse.de>
Thanks.
Coly Li
^ permalink raw reply
* [RFC v1 2/2] KVM: PPC: Book3S HV: abstract secure VM related calls.
From: Ram Pai @ 2020-10-12 7:27 UTC (permalink / raw)
To: kvm-ppc, linuxppc-dev; +Cc: farosas, linuxram, bharata
In-Reply-To: <1602487663-7321-2-git-send-email-linuxram@us.ibm.com>
Abstract the secure VM related calls into generic calls.
These generic calls will call the corresponding method of the
backend that prvoides the implementation to support secure VM.
Currently there is only the ultravisor based implementation.
Modify that implementation to act as a backed to the generic calls.
This plumbing will provide the flexibility to add more backends
in the future.
Signed-off-by: Ram Pai <linuxram@us.ibm.com>
---
arch/powerpc/include/asm/kvm_book3s_uvmem.h | 100 -----------
arch/powerpc/include/asm/kvmppc_svm_backend.h | 250 ++++++++++++++++++++++++++
arch/powerpc/kvm/book3s_64_mmu_radix.c | 6 +-
arch/powerpc/kvm/book3s_hv.c | 28 +--
arch/powerpc/kvm/book3s_hv_uvmem.c | 78 ++++++--
5 files changed, 327 insertions(+), 135 deletions(-)
delete mode 100644 arch/powerpc/include/asm/kvm_book3s_uvmem.h
create mode 100644 arch/powerpc/include/asm/kvmppc_svm_backend.h
diff --git a/arch/powerpc/include/asm/kvm_book3s_uvmem.h b/arch/powerpc/include/asm/kvm_book3s_uvmem.h
deleted file mode 100644
index 0a63194..0000000
--- a/arch/powerpc/include/asm/kvm_book3s_uvmem.h
+++ /dev/null
@@ -1,100 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef __ASM_KVM_BOOK3S_UVMEM_H__
-#define __ASM_KVM_BOOK3S_UVMEM_H__
-
-#ifdef CONFIG_PPC_UV
-int kvmppc_uvmem_init(void);
-void kvmppc_uvmem_free(void);
-bool kvmppc_uvmem_available(void);
-int kvmppc_uvmem_slot_init(struct kvm *kvm, const struct kvm_memory_slot *slot);
-void kvmppc_uvmem_slot_free(struct kvm *kvm,
- const struct kvm_memory_slot *slot);
-unsigned long kvmppc_h_svm_page_in(struct kvm *kvm,
- unsigned long gra,
- unsigned long flags,
- unsigned long page_shift);
-unsigned long kvmppc_h_svm_page_out(struct kvm *kvm,
- unsigned long gra,
- unsigned long flags,
- unsigned long page_shift);
-unsigned long kvmppc_h_svm_init_start(struct kvm *kvm);
-unsigned long kvmppc_h_svm_init_done(struct kvm *kvm);
-int kvmppc_send_page_to_uv(struct kvm *kvm, unsigned long gfn);
-unsigned long kvmppc_h_svm_init_abort(struct kvm *kvm);
-void kvmppc_uvmem_drop_pages(const struct kvm_memory_slot *free,
- struct kvm *kvm, bool skip_page_out);
-int kvmppc_uvmem_memslot_create(struct kvm *kvm,
- const struct kvm_memory_slot *new);
-void kvmppc_uvmem_memslot_delete(struct kvm *kvm,
- const struct kvm_memory_slot *old);
-#else
-static inline int kvmppc_uvmem_init(void)
-{
- return 0;
-}
-
-static inline void kvmppc_uvmem_free(void) { }
-
-static inline bool kvmppc_uvmem_available(void)
-{
- return false;
-}
-
-static inline int
-kvmppc_uvmem_slot_init(struct kvm *kvm, const struct kvm_memory_slot *slot)
-{
- return 0;
-}
-
-static inline void
-kvmppc_uvmem_slot_free(struct kvm *kvm, const struct kvm_memory_slot *slot) { }
-
-static inline unsigned long
-kvmppc_h_svm_page_in(struct kvm *kvm, unsigned long gra,
- unsigned long flags, unsigned long page_shift)
-{
- return H_UNSUPPORTED;
-}
-
-static inline unsigned long
-kvmppc_h_svm_page_out(struct kvm *kvm, unsigned long gra,
- unsigned long flags, unsigned long page_shift)
-{
- return H_UNSUPPORTED;
-}
-
-static inline unsigned long kvmppc_h_svm_init_start(struct kvm *kvm)
-{
- return H_UNSUPPORTED;
-}
-
-static inline unsigned long kvmppc_h_svm_init_done(struct kvm *kvm)
-{
- return H_UNSUPPORTED;
-}
-
-static inline unsigned long kvmppc_h_svm_init_abort(struct kvm *kvm)
-{
- return H_UNSUPPORTED;
-}
-
-static inline int kvmppc_send_page_to_uv(struct kvm *kvm, unsigned long gfn)
-{
- return -EFAULT;
-}
-
-static inline void
-kvmppc_uvmem_drop_pages(const struct kvm_memory_slot *free,
- struct kvm *kvm, bool skip_page_out) { }
-
-static inline int kvmppc_uvmem_memslot_create(struct kvm *kvm,
- const struct kvm_memory_slot *new)
-{
- return H_UNSUPPORTED;
-}
-
-static inline void kvmppc_uvmem_memslot_delete(struct kvm *kvm,
- const struct kvm_memory_slot *old) { }
-
-#endif /* CONFIG_PPC_UV */
-#endif /* __ASM_KVM_BOOK3S_UVMEM_H__ */
diff --git a/arch/powerpc/include/asm/kvmppc_svm_backend.h b/arch/powerpc/include/asm/kvmppc_svm_backend.h
new file mode 100644
index 0000000..be60d80
--- /dev/null
+++ b/arch/powerpc/include/asm/kvmppc_svm_backend.h
@@ -0,0 +1,250 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ *
+ * Copyright IBM Corp. 2020
+ *
+ * Authors: Ram Pai <linuxram@us.ibm.com>
+ */
+
+#ifndef __POWERPC_KVMPPC_SVM_BACKEND_H__
+#define __POWERPC_KVMPPC_SVM_BACKEND_H__
+
+#include <linux/mutex.h>
+#include <linux/timer.h>
+#include <linux/types.h>
+#include <linux/kvm_types.h>
+#include <linux/kvm_host.h>
+#include <linux/bug.h>
+#ifdef CONFIG_PPC_BOOK3S
+#include <asm/kvm_book3s.h>
+#else
+#include <asm/kvm_booke.h>
+#endif
+#ifdef CONFIG_KVM_BOOK3S_64_HANDLER
+#include <asm/paca.h>
+#include <asm/xive.h>
+#include <asm/cpu_has_feature.h>
+#endif
+
+struct kvmppc_hmm_backend {
+ /* initialize */
+ int (*kvmppc_secmem_init)(void);
+
+ /* cleanup */
+ void (*kvmppc_secmem_free)(void);
+
+ /* is memory available */
+ bool (*kvmppc_secmem_available)(void);
+
+ /* allocate a protected/secure page for the secure VM */
+ unsigned long (*kvmppc_svm_page_in)(struct kvm *kvm,
+ unsigned long gra,
+ unsigned long flags,
+ unsigned long page_shift);
+
+ /* recover the protected/secure page from the secure VM */
+ unsigned long (*kvmppc_svm_page_out)(struct kvm *kvm,
+ unsigned long gra,
+ unsigned long flags,
+ unsigned long page_shift);
+
+ /* initiate the transition of a VM to secure VM */
+ unsigned long (*kvmppc_svm_init_start)(struct kvm *kvm);
+
+ /* finalize the transition of a secure VM */
+ unsigned long (*kvmppc_svm_init_done)(struct kvm *kvm);
+
+ /* share the page on page fault */
+ int (*kvmppc_svm_page_share)(struct kvm *kvm, unsigned long gfn);
+
+ /* abort the transition to a secure VM */
+ unsigned long (*kvmppc_svm_init_abort)(struct kvm *kvm);
+
+ /* add a memory slot */
+ int (*kvmppc_svm_memslot_create)(struct kvm *kvm,
+ const struct kvm_memory_slot *new);
+
+ /* free a memory slot */
+ void (*kvmppc_svm_memslot_delete)(struct kvm *kvm,
+ const struct kvm_memory_slot *old);
+
+ /* drop pages allocated to the secure VM */
+ void (*kvmppc_svm_drop_pages)(const struct kvm_memory_slot *free,
+ struct kvm *kvm, bool skip_page_out);
+};
+
+extern const struct kvmppc_hmm_backend *kvmppc_svm_backend;
+
+static inline int kvmppc_svm_page_share(struct kvm *kvm, unsigned long gfn)
+{
+ if (!kvmppc_svm_backend)
+ return -ENODEV;
+
+ return kvmppc_svm_backend->kvmppc_svm_page_share(kvm,
+ gfn);
+}
+
+static inline void kvmppc_svm_drop_pages(const struct kvm_memory_slot *memslot,
+ struct kvm *kvm, bool skip_page_out)
+{
+ if (!kvmppc_svm_backend)
+ return;
+
+ kvmppc_svm_backend->kvmppc_svm_drop_pages(memslot,
+ kvm, skip_page_out);
+}
+
+static inline int kvmppc_svm_page_in(struct kvm *kvm,
+ unsigned long gpa,
+ unsigned long flags,
+ unsigned long page_shift)
+{
+ if (!kvmppc_svm_backend)
+ return -ENODEV;
+
+ return kvmppc_svm_backend->kvmppc_svm_page_in(kvm,
+ gpa, flags, page_shift);
+}
+
+static inline int kvmppc_svm_page_out(struct kvm *kvm,
+ unsigned long gpa,
+ unsigned long flags,
+ unsigned long page_shift)
+{
+ if (!kvmppc_svm_backend)
+ return -ENODEV;
+
+ return kvmppc_svm_backend->kvmppc_svm_page_out(kvm,
+ gpa, flags, page_shift);
+}
+
+static inline int kvmppc_svm_init_start(struct kvm *kvm)
+{
+ if (!kvmppc_svm_backend)
+ return -ENODEV;
+
+ return kvmppc_svm_backend->kvmppc_svm_init_start(kvm);
+}
+
+static inline int kvmppc_svm_init_done(struct kvm *kvm)
+{
+ if (!kvmppc_svm_backend)
+ return -ENODEV;
+
+ return kvmppc_svm_backend->kvmppc_svm_init_done(kvm);
+}
+
+static inline int kvmppc_svm_init_abort(struct kvm *kvm)
+{
+ if (!kvmppc_svm_backend)
+ return -ENODEV;
+
+ return kvmppc_svm_backend->kvmppc_svm_init_abort(kvm);
+}
+
+static inline void kvmppc_svm_memslot_create(struct kvm *kvm,
+ const struct kvm_memory_slot *memslot)
+{
+ if (!kvmppc_svm_backend)
+ return;
+
+ kvmppc_svm_backend->kvmppc_svm_memslot_create(kvm,
+ memslot);
+}
+
+static inline void kvmppc_svm_memslot_delete(struct kvm *kvm,
+ const struct kvm_memory_slot *memslot)
+{
+ if (!kvmppc_svm_backend)
+ return;
+
+ kvmppc_svm_backend->kvmppc_svm_memslot_delete(kvm,
+ memslot);
+}
+
+static inline int kvmppc_secmem_init(void)
+{
+#ifdef CONFIG_PPC_UV
+ extern const struct kvmppc_hmm_backend kvmppc_uvmem_backend;
+
+ kvmppc_svm_backend = NULL;
+ if (kvmhv_on_pseries()) {
+ /* @TODO add the protected memory backend */
+ return 0;
+ }
+
+ kvmppc_svm_backend = &kvmppc_uvmem_backend;
+
+ if (!kvmppc_svm_backend->kvmppc_secmem_init) {
+ pr_err("KVM-HV: kvmppc_svm_backend has no %s\n", __func__);
+ goto err;
+ }
+ if (!kvmppc_svm_backend->kvmppc_secmem_free) {
+ pr_err("KVM-HV: kvmppc_svm_backend has no kvmppc_secmem_free()\n");
+ goto err;
+ }
+ if (!kvmppc_svm_backend->kvmppc_secmem_available) {
+ pr_err("KVM-HV: kvmppc_svm_backend has no kvmppc_secmem_available()\n");
+ goto err;
+ }
+ if (!kvmppc_svm_backend->kvmppc_svm_page_in) {
+ pr_err("KVM-HV: kvmppc_svm_backend has no kvmppc_svm_page_in()\n");
+ goto err;
+ }
+ if (!kvmppc_svm_backend->kvmppc_svm_page_out) {
+ pr_err("KVM-HV: kvmppc_svm_backend has no kvmppc_svm_page_out()\n");
+ goto err;
+ }
+ if (!kvmppc_svm_backend->kvmppc_svm_init_start) {
+ pr_err("KVM-HV: kvmppc_svm_backend has no kvmppc_svm_init_start()\n");
+ goto err;
+ }
+ if (!kvmppc_svm_backend->kvmppc_svm_init_done) {
+ pr_err("KVM-HV: kvmppc_svm_backend has no kvmppc_svm_init_done()\n");
+ goto err;
+ }
+ if (!kvmppc_svm_backend->kvmppc_svm_page_share) {
+ pr_err("KVM-HV: kvmppc_svm_backend has no kvmppc_svm_page_share()\n");
+ goto err;
+ }
+ if (!kvmppc_svm_backend->kvmppc_svm_init_abort) {
+ pr_err("KVM-HV: kvmppc_svm_backend has no kvmppc_svm_init_abort()\n");
+ goto err;
+ }
+ if (!kvmppc_svm_backend->kvmppc_svm_memslot_create) {
+ pr_err("KVM-HV: kvmppc_svm_backend has no kvmppc_svm_memslot_create()\n");
+ goto err;
+ }
+ if (!kvmppc_svm_backend->kvmppc_svm_memslot_delete) {
+ pr_err("KVM-HV: kvmppc_svm_backend has no kvmppc_svm_memslot_delete()\n");
+ goto err;
+ }
+ if (!kvmppc_svm_backend->kvmppc_svm_drop_pages) {
+ pr_err("KVM-HV: kvmppc_svm_backend has no kvmppc_svm_drop_pages()\n");
+ goto err;
+ }
+
+ return kvmppc_svm_backend->kvmppc_secmem_init();
+
+err: kvmppc_svm_backend = NULL;
+ return -ENODEV;
+#endif
+ return 0;
+}
+
+static inline void kvmppc_secmem_free(void)
+{
+ if (!kvmppc_svm_backend)
+ return;
+
+ return kvmppc_svm_backend->kvmppc_secmem_free();
+}
+
+static inline int kvmppc_secmem_available(void)
+{
+ if (!kvmppc_svm_backend)
+ return 0;
+
+ return kvmppc_svm_backend->kvmppc_secmem_available();
+}
+#endif /* __POWERPC_KVMPPC_SVM_BACKEND_H__ */
diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c
index 22a677b..1a559b3 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_radix.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c
@@ -20,7 +20,7 @@
#include <asm/pgalloc.h>
#include <asm/pte-walk.h>
#include <asm/ultravisor.h>
-#include <asm/kvm_book3s_uvmem.h>
+#include <asm/kvmppc_svm_backend.h>
/*
* Supported radix tree geometry.
@@ -941,7 +941,7 @@ int kvmppc_book3s_radix_page_fault(struct kvm_vcpu *vcpu,
gpa |= ea & 0xfff;
if (kvm->arch.secure_guest & KVMPPC_SECURE_INIT_DONE)
- return kvmppc_send_page_to_uv(kvm, gfn);
+ return kvmppc_svm_page_share(kvm, gfn);
/* Get the corresponding memslot */
memslot = gfn_to_memslot(kvm, gfn);
@@ -1148,7 +1148,7 @@ void kvmppc_radix_flush_memslot(struct kvm *kvm,
unsigned int shift;
if (kvm->arch.secure_guest & KVMPPC_SECURE_INIT_START)
- kvmppc_uvmem_drop_pages(memslot, kvm, true);
+ kvmppc_svm_drop_pages(memslot, kvm, true);
if (kvm->arch.secure_guest & KVMPPC_SECURE_INIT_DONE)
return;
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 4ba06a2..9c093b4 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -72,7 +72,7 @@
#include <asm/xics.h>
#include <asm/xive.h>
#include <asm/hw_breakpoint.h>
-#include <asm/kvm_book3s_uvmem.h>
+#include <asm/kvmppc_svm_backend.h>
#include <asm/ultravisor.h>
#include <asm/dtl.h>
@@ -81,6 +81,8 @@
#define CREATE_TRACE_POINTS
#include "trace_hv.h"
+const struct kvmppc_hmm_backend *kvmppc_svm_backend;
+
/* #define EXIT_DEBUG */
/* #define EXIT_DEBUG_SIMPLE */
/* #define EXIT_DEBUG_INT */
@@ -1079,7 +1081,7 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
case H_SVM_PAGE_IN:
ret = H_UNSUPPORTED;
if (kvmppc_get_srr1(vcpu) & MSR_S)
- ret = kvmppc_h_svm_page_in(vcpu->kvm,
+ ret = kvmppc_svm_page_in(vcpu->kvm,
kvmppc_get_gpr(vcpu, 4),
kvmppc_get_gpr(vcpu, 5),
kvmppc_get_gpr(vcpu, 6));
@@ -1087,7 +1089,7 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
case H_SVM_PAGE_OUT:
ret = H_UNSUPPORTED;
if (kvmppc_get_srr1(vcpu) & MSR_S)
- ret = kvmppc_h_svm_page_out(vcpu->kvm,
+ ret = kvmppc_svm_page_out(vcpu->kvm,
kvmppc_get_gpr(vcpu, 4),
kvmppc_get_gpr(vcpu, 5),
kvmppc_get_gpr(vcpu, 6));
@@ -1095,12 +1097,12 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
case H_SVM_INIT_START:
ret = H_UNSUPPORTED;
if (kvmppc_get_srr1(vcpu) & MSR_S)
- ret = kvmppc_h_svm_init_start(vcpu->kvm);
+ ret = kvmppc_svm_init_start(vcpu->kvm);
break;
case H_SVM_INIT_DONE:
ret = H_UNSUPPORTED;
if (kvmppc_get_srr1(vcpu) & MSR_S)
- ret = kvmppc_h_svm_init_done(vcpu->kvm);
+ ret = kvmppc_svm_init_done(vcpu->kvm);
break;
case H_SVM_INIT_ABORT:
/*
@@ -1110,7 +1112,7 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
* Instead the kvm->arch.secure_guest flag is checked inside
* kvmppc_h_svm_init_abort().
*/
- ret = kvmppc_h_svm_init_abort(vcpu->kvm);
+ ret = kvmppc_svm_init_abort(vcpu->kvm);
break;
default:
@@ -4564,10 +4566,10 @@ static void kvmppc_core_commit_memory_region_hv(struct kvm *kvm,
* @TODO kvmppc_uvmem_memslot_create() can fail and
* return error. Fix this.
*/
- kvmppc_uvmem_memslot_create(kvm, new);
+ kvmppc_svm_memslot_create(kvm, new);
break;
case KVM_MR_DELETE:
- kvmppc_uvmem_memslot_delete(kvm, old);
+ kvmppc_svm_memslot_delete(kvm, old);
break;
default:
/* TODO: Handle KVM_MR_MOVE */
@@ -5473,7 +5475,7 @@ static void unpin_vpa_reset(struct kvm *kvm, struct kvmppc_vpa *vpa)
*/
static int kvmhv_enable_svm(struct kvm *kvm)
{
- if (!kvmppc_uvmem_available())
+ if (!kvmppc_secmem_available())
return -EINVAL;
if (kvm)
kvm->arch.svm_enabled = 1;
@@ -5521,7 +5523,7 @@ static int kvmhv_svm_off(struct kvm *kvm)
continue;
kvm_for_each_memslot(memslot, slots) {
- kvmppc_uvmem_drop_pages(memslot, kvm, true);
+ kvmppc_svm_drop_pages(memslot, kvm, true);
uv_unregister_mem_slot(kvm->arch.lpid, memslot->id);
}
}
@@ -5710,16 +5712,16 @@ static int kvmppc_book3s_init_hv(void)
no_mixing_hpt_and_radix = true;
}
- r = kvmppc_uvmem_init();
+ r = kvmppc_secmem_init();
if (r < 0)
- pr_err("KVM-HV: kvmppc_uvmem_init failed %d\n", r);
+ pr_err("KVM-HV: kvmppc_secmem_init failed %d\n", r);
return r;
}
static void kvmppc_book3s_exit_hv(void)
{
- kvmppc_uvmem_free();
+ kvmppc_secmem_free();
kvmppc_free_host_rm_ops();
if (kvmppc_radix_possible())
kvmppc_radix_exit();
diff --git a/arch/powerpc/kvm/book3s_hv_uvmem.c b/arch/powerpc/kvm/book3s_hv_uvmem.c
index b79affc..12d10c1 100644
--- a/arch/powerpc/kvm/book3s_hv_uvmem.c
+++ b/arch/powerpc/kvm/book3s_hv_uvmem.c
@@ -93,7 +93,7 @@
#include <asm/ultravisor.h>
#include <asm/mman.h>
#include <asm/kvm_ppc.h>
-#include <asm/kvm_book3s_uvmem.h>
+#include <asm/kvmppc_svm_backend.h>
static struct dev_pagemap uvmem_pgmap;
static unsigned long *uvmem_bitmap;
@@ -234,7 +234,7 @@ struct uvmem_page_pvt {
bool remove_gfn;
};
-bool kvmppc_uvmem_available(void)
+static bool uvmem_available(void)
{
/*
* If uvmem_bitmap != NULL, then there is an ultravisor
@@ -453,7 +453,7 @@ static int __uvmem_memslot_create(struct kvm *kvm,
return ret;
}
-unsigned long kvmppc_h_svm_init_start(struct kvm *kvm)
+static unsigned long uvmem_h_svm_init_start(struct kvm *kvm)
{
struct kvm_memslots *slots;
struct kvm_memory_slot *memslot, *m;
@@ -595,7 +595,7 @@ static inline int uvmem_svm_page_out(struct vm_area_struct *vma,
* fault on them, do fault time migration to replace the device PTEs in
* QEMU page table with normal PTEs from newly allocated pages.
*/
-void kvmppc_uvmem_drop_pages(const struct kvm_memory_slot *slot,
+static void uvmem_drop_pages(const struct kvm_memory_slot *slot,
struct kvm *kvm, bool skip_page_out)
{
int i;
@@ -644,7 +644,7 @@ void kvmppc_uvmem_drop_pages(const struct kvm_memory_slot *slot,
mmap_read_unlock(kvm->mm);
}
-unsigned long kvmppc_h_svm_init_abort(struct kvm *kvm)
+static unsigned long uvmem_h_svm_init_abort(struct kvm *kvm)
{
int srcu_idx;
struct kvm_memory_slot *memslot;
@@ -662,7 +662,7 @@ unsigned long kvmppc_h_svm_init_abort(struct kvm *kvm)
srcu_idx = srcu_read_lock(&kvm->srcu);
kvm_for_each_memslot(memslot, kvm_memslots(kvm))
- kvmppc_uvmem_drop_pages(memslot, kvm, false);
+ uvmem_drop_pages(memslot, kvm, false);
srcu_read_unlock(&kvm->srcu, srcu_idx);
@@ -816,7 +816,7 @@ static int uvmem_uv_migrate_mem_slot(struct kvm *kvm,
return ret;
}
-unsigned long kvmppc_h_svm_init_done(struct kvm *kvm)
+static unsigned long uvmem_h_svm_init_done(struct kvm *kvm)
{
struct kvm_memslots *slots;
struct kvm_memory_slot *memslot;
@@ -922,7 +922,7 @@ static unsigned long uvmem_share_page(struct kvm *kvm, unsigned long gpa,
* H_PAGE_IN_SHARED flag makes the page shared which means that the same
* memory in is visible from both UV and HV.
*/
-unsigned long kvmppc_h_svm_page_in(struct kvm *kvm, unsigned long gpa,
+static unsigned long uvmem_h_svm_page_in(struct kvm *kvm, unsigned long gpa,
unsigned long flags,
unsigned long page_shift)
{
@@ -985,7 +985,7 @@ unsigned long kvmppc_h_svm_page_in(struct kvm *kvm, unsigned long gpa,
* This eventually results in dropping of device PFN and the newly
* provisioned page/PFN gets populated in QEMU page tables.
*/
-static vm_fault_t kvmppc_uvmem_migrate_to_ram(struct vm_fault *vmf)
+static vm_fault_t uvmem_migrate_to_ram(struct vm_fault *vmf)
{
struct uvmem_page_pvt *pvt = vmf->page->zone_device_data;
@@ -1004,7 +1004,7 @@ static vm_fault_t kvmppc_uvmem_migrate_to_ram(struct vm_fault *vmf)
* to a normal PFN during H_SVM_PAGE_OUT.
* Gets called with kvm->arch.uvmem_lock held.
*/
-static void kvmppc_uvmem_page_free(struct page *page)
+static void uvmem_page_free(struct page *page)
{
unsigned long pfn = page_to_pfn(page) -
(uvmem_pgmap.res.start >> PAGE_SHIFT);
@@ -1024,15 +1024,15 @@ static void kvmppc_uvmem_page_free(struct page *page)
}
static const struct dev_pagemap_ops uvmem_ops = {
- .page_free = kvmppc_uvmem_page_free,
- .migrate_to_ram = kvmppc_uvmem_migrate_to_ram,
+ .page_free = uvmem_page_free,
+ .migrate_to_ram = uvmem_migrate_to_ram,
};
/*
* H_SVM_PAGE_OUT: Move page from secure memory to normal memory.
*/
-unsigned long
-kvmppc_h_svm_page_out(struct kvm *kvm, unsigned long gpa,
+static unsigned long
+uvmem_h_svm_page_out(struct kvm *kvm, unsigned long gpa,
unsigned long flags, unsigned long page_shift)
{
unsigned long gfn = gpa >> page_shift;
@@ -1070,7 +1070,7 @@ static void kvmppc_uvmem_page_free(struct page *page)
return ret;
}
-int kvmppc_send_page_to_uv(struct kvm *kvm, unsigned long gfn)
+static int uvmem_send_page_to_uv(struct kvm *kvm, unsigned long gfn)
{
unsigned long pfn;
int ret = U_SUCCESS;
@@ -1091,7 +1091,8 @@ int kvmppc_send_page_to_uv(struct kvm *kvm, unsigned long gfn)
return (ret == U_SUCCESS) ? RESUME_GUEST : -EFAULT;
}
-int kvmppc_uvmem_memslot_create(struct kvm *kvm, const struct kvm_memory_slot *new)
+static int uvmem_memslot_create(struct kvm *kvm,
+ const struct kvm_memory_slot *new)
{
int ret = __uvmem_memslot_create(kvm, new);
@@ -1101,7 +1102,8 @@ int kvmppc_uvmem_memslot_create(struct kvm *kvm, const struct kvm_memory_slot *n
return ret;
}
-void kvmppc_uvmem_memslot_delete(struct kvm *kvm, const struct kvm_memory_slot *old)
+static void uvmem_memslot_delete(struct kvm *kvm,
+ const struct kvm_memory_slot *old)
{
__uvmem_memslot_delete(kvm, old);
}
@@ -1144,7 +1146,7 @@ static u64 uvmem_get_secmem_size(void)
return size;
}
-int kvmppc_uvmem_init(void)
+static int uvmem_init(void)
{
int ret = 0;
unsigned long size;
@@ -1199,7 +1201,7 @@ int kvmppc_uvmem_init(void)
return ret;
}
-void kvmppc_uvmem_free(void)
+static void uvmem_free(void)
{
if (!uvmem_bitmap)
return;
@@ -1209,3 +1211,41 @@ void kvmppc_uvmem_free(void)
resource_size(&uvmem_pgmap.res));
kfree(uvmem_bitmap);
}
+
+const struct kvmppc_hmm_backend kvmppc_uvmem_backend = {
+ /* initialize */
+ .kvmppc_secmem_init = uvmem_init,
+
+ /* cleanup */
+ .kvmppc_secmem_free = uvmem_free,
+
+ /* is memory available */
+ .kvmppc_secmem_available = uvmem_available,
+
+ /* allocate a protected/secure page for the secure VM */
+ .kvmppc_svm_page_in = uvmem_h_svm_page_in,
+
+ /* recover the protected/secure page from the secure VM */
+ .kvmppc_svm_page_out = uvmem_h_svm_page_out,
+
+ /* initiate the transition of a VM to secure VM */
+ .kvmppc_svm_init_start = uvmem_h_svm_init_start,
+
+ /* finalize the transition of a secure VM */
+ .kvmppc_svm_init_done = uvmem_h_svm_init_done,
+
+ /* send a page to uv on page fault */
+ .kvmppc_svm_page_share = uvmem_send_page_to_uv,
+
+ /* abort the transition to a secure VM */
+ .kvmppc_svm_init_abort = uvmem_h_svm_init_abort,
+
+ /* add a memory slot */
+ .kvmppc_svm_memslot_create = uvmem_memslot_create,
+
+ /* free a memory slot */
+ .kvmppc_svm_memslot_delete = uvmem_memslot_delete,
+
+ /* drop pages allocated to the secure VM */
+ .kvmppc_svm_drop_pages = uvmem_drop_pages,
+};
--
1.8.3.1
^ permalink raw reply related
* [RFC v1 1/2] KVM: PPC: Book3S HV: rename all variables in book3s_hv_uvmem.c
From: Ram Pai @ 2020-10-12 7:27 UTC (permalink / raw)
To: kvm-ppc, linuxppc-dev; +Cc: farosas, linuxram, bharata
In-Reply-To: <1602487663-7321-1-git-send-email-linuxram@us.ibm.com>
Preparing this file to be one of the many backends. Since this file
supports Ultravisor backend, renaming all variable from kvmppc_*
to uvmem_*. This is to avoid clash with some generic top level
functions to be defined in the next patch.
Signed-off-by: Ram Pai <linuxram@us.ibm.com>
---
arch/powerpc/kvm/book3s_hv_uvmem.c | 210 ++++++++++++++++++-------------------
1 file changed, 105 insertions(+), 105 deletions(-)
diff --git a/arch/powerpc/kvm/book3s_hv_uvmem.c b/arch/powerpc/kvm/book3s_hv_uvmem.c
index 7705d55..b79affc 100644
--- a/arch/powerpc/kvm/book3s_hv_uvmem.c
+++ b/arch/powerpc/kvm/book3s_hv_uvmem.c
@@ -95,9 +95,9 @@
#include <asm/kvm_ppc.h>
#include <asm/kvm_book3s_uvmem.h>
-static struct dev_pagemap kvmppc_uvmem_pgmap;
-static unsigned long *kvmppc_uvmem_bitmap;
-static DEFINE_SPINLOCK(kvmppc_uvmem_bitmap_lock);
+static struct dev_pagemap uvmem_pgmap;
+static unsigned long *uvmem_bitmap;
+static DEFINE_SPINLOCK(uvmem_bitmap_lock);
/*
* States of a GFN
@@ -221,13 +221,13 @@
#define KVMPPC_GFN_FLAG_MASK (KVMPPC_GFN_SECURE | KVMPPC_GFN_SHARED)
#define KVMPPC_GFN_PFN_MASK (~KVMPPC_GFN_FLAG_MASK)
-struct kvmppc_uvmem_slot {
+struct uvmem_slot {
struct list_head list;
unsigned long nr_pfns;
unsigned long base_pfn;
unsigned long *pfns;
};
-struct kvmppc_uvmem_page_pvt {
+struct uvmem_page_pvt {
struct kvm *kvm;
unsigned long gpa;
bool skip_page_out;
@@ -237,15 +237,15 @@ struct kvmppc_uvmem_page_pvt {
bool kvmppc_uvmem_available(void)
{
/*
- * If kvmppc_uvmem_bitmap != NULL, then there is an ultravisor
+ * If uvmem_bitmap != NULL, then there is an ultravisor
* and our data structures have been initialized successfully.
*/
- return !!kvmppc_uvmem_bitmap;
+ return !!uvmem_bitmap;
}
-int kvmppc_uvmem_slot_init(struct kvm *kvm, const struct kvm_memory_slot *slot)
+static int uvmem_slot_init(struct kvm *kvm, const struct kvm_memory_slot *slot)
{
- struct kvmppc_uvmem_slot *p;
+ struct uvmem_slot *p;
p = kzalloc(sizeof(*p), GFP_KERNEL);
if (!p)
@@ -268,9 +268,9 @@ int kvmppc_uvmem_slot_init(struct kvm *kvm, const struct kvm_memory_slot *slot)
/*
* All device PFNs are already released by the time we come here.
*/
-void kvmppc_uvmem_slot_free(struct kvm *kvm, const struct kvm_memory_slot *slot)
+static void uvmem_slot_free(struct kvm *kvm, const struct kvm_memory_slot *slot)
{
- struct kvmppc_uvmem_slot *p, *next;
+ struct uvmem_slot *p, *next;
mutex_lock(&kvm->arch.uvmem_lock);
list_for_each_entry_safe(p, next, &kvm->arch.uvmem_pfns, list) {
@@ -284,10 +284,10 @@ void kvmppc_uvmem_slot_free(struct kvm *kvm, const struct kvm_memory_slot *slot)
mutex_unlock(&kvm->arch.uvmem_lock);
}
-static void kvmppc_mark_gfn(unsigned long gfn, struct kvm *kvm,
+static void uvmem_mark_gfn(unsigned long gfn, struct kvm *kvm,
unsigned long flag, unsigned long uvmem_pfn)
{
- struct kvmppc_uvmem_slot *p;
+ struct uvmem_slot *p;
list_for_each_entry(p, &kvm->arch.uvmem_pfns, list) {
if (gfn >= p->base_pfn && gfn < p->base_pfn + p->nr_pfns) {
@@ -303,35 +303,35 @@ static void kvmppc_mark_gfn(unsigned long gfn, struct kvm *kvm,
}
/* mark the GFN as secure-GFN associated with @uvmem pfn device-PFN. */
-static void kvmppc_gfn_secure_uvmem_pfn(unsigned long gfn,
+static void uvmem_gfn_secure_uvmem_pfn(unsigned long gfn,
unsigned long uvmem_pfn, struct kvm *kvm)
{
- kvmppc_mark_gfn(gfn, kvm, KVMPPC_GFN_UVMEM_PFN, uvmem_pfn);
+ uvmem_mark_gfn(gfn, kvm, KVMPPC_GFN_UVMEM_PFN, uvmem_pfn);
}
/* mark the GFN as secure-GFN associated with a memory-PFN. */
-static void kvmppc_gfn_secure_mem_pfn(unsigned long gfn, struct kvm *kvm)
+static void uvmem_gfn_secure_mem_pfn(unsigned long gfn, struct kvm *kvm)
{
- kvmppc_mark_gfn(gfn, kvm, KVMPPC_GFN_MEM_PFN, 0);
+ uvmem_mark_gfn(gfn, kvm, KVMPPC_GFN_MEM_PFN, 0);
}
/* mark the GFN as a shared GFN. */
-static void kvmppc_gfn_shared(unsigned long gfn, struct kvm *kvm)
+static void uvmem_gfn_shared(unsigned long gfn, struct kvm *kvm)
{
- kvmppc_mark_gfn(gfn, kvm, KVMPPC_GFN_SHARED, 0);
+ uvmem_mark_gfn(gfn, kvm, KVMPPC_GFN_SHARED, 0);
}
/* mark the GFN as a non-existent GFN. */
-static void kvmppc_gfn_remove(unsigned long gfn, struct kvm *kvm)
+static void uvmem_gfn_remove(unsigned long gfn, struct kvm *kvm)
{
- kvmppc_mark_gfn(gfn, kvm, 0, 0);
+ uvmem_mark_gfn(gfn, kvm, 0, 0);
}
/* return true, if the GFN is a secure-GFN backed by a secure-PFN */
-static bool kvmppc_gfn_is_uvmem_pfn(unsigned long gfn, struct kvm *kvm,
+static bool uvmem_gfn_is_uvmem_pfn(unsigned long gfn, struct kvm *kvm,
unsigned long *uvmem_pfn)
{
- struct kvmppc_uvmem_slot *p;
+ struct uvmem_slot *p;
list_for_each_entry(p, &kvm->arch.uvmem_pfns, list) {
if (gfn >= p->base_pfn && gfn < p->base_pfn + p->nr_pfns) {
@@ -356,10 +356,10 @@ static bool kvmppc_gfn_is_uvmem_pfn(unsigned long gfn, struct kvm *kvm,
*
* Must be called with kvm->arch.uvmem_lock held.
*/
-static bool kvmppc_next_nontransitioned_gfn(const struct kvm_memory_slot *memslot,
+static bool uvmem_next_nontransitioned_gfn(const struct kvm_memory_slot *memslot,
struct kvm *kvm, unsigned long *gfn)
{
- struct kvmppc_uvmem_slot *p;
+ struct uvmem_slot *p;
bool ret = false;
unsigned long i;
@@ -370,7 +370,7 @@ static bool kvmppc_next_nontransitioned_gfn(const struct kvm_memory_slot *memslo
return ret;
/*
* The code below assumes, one to one correspondence between
- * kvmppc_uvmem_slot and memslot.
+ * uvmem_slot and memslot.
*/
for (i = *gfn; i < p->base_pfn + p->nr_pfns; i++) {
unsigned long index = i - p->base_pfn;
@@ -384,7 +384,7 @@ static bool kvmppc_next_nontransitioned_gfn(const struct kvm_memory_slot *memslo
return ret;
}
-static int kvmppc_memslot_page_merge(struct kvm *kvm,
+static int uvmem_memslot_page_merge(struct kvm *kvm,
const struct kvm_memory_slot *memslot, bool merge)
{
unsigned long gfn = memslot->base_gfn;
@@ -418,23 +418,23 @@ static int kvmppc_memslot_page_merge(struct kvm *kvm,
return ret;
}
-static void __kvmppc_uvmem_memslot_delete(struct kvm *kvm,
+static void __uvmem_memslot_delete(struct kvm *kvm,
const struct kvm_memory_slot *memslot)
{
uv_unregister_mem_slot(kvm->arch.lpid, memslot->id);
- kvmppc_uvmem_slot_free(kvm, memslot);
- kvmppc_memslot_page_merge(kvm, memslot, true);
+ uvmem_slot_free(kvm, memslot);
+ uvmem_memslot_page_merge(kvm, memslot, true);
}
-static int __kvmppc_uvmem_memslot_create(struct kvm *kvm,
+static int __uvmem_memslot_create(struct kvm *kvm,
const struct kvm_memory_slot *memslot)
{
int ret = H_PARAMETER;
- if (kvmppc_memslot_page_merge(kvm, memslot, false))
+ if (uvmem_memslot_page_merge(kvm, memslot, false))
return ret;
- if (kvmppc_uvmem_slot_init(kvm, memslot))
+ if (uvmem_slot_init(kvm, memslot))
goto out1;
ret = uv_register_mem_slot(kvm->arch.lpid,
@@ -447,9 +447,9 @@ static int __kvmppc_uvmem_memslot_create(struct kvm *kvm,
}
return 0;
out:
- kvmppc_uvmem_slot_free(kvm, memslot);
+ uvmem_slot_free(kvm, memslot);
out1:
- kvmppc_memslot_page_merge(kvm, memslot, true);
+ uvmem_memslot_page_merge(kvm, memslot, true);
return ret;
}
@@ -462,7 +462,7 @@ unsigned long kvmppc_h_svm_init_start(struct kvm *kvm)
kvm->arch.secure_guest = KVMPPC_SECURE_INIT_START;
- if (!kvmppc_uvmem_bitmap)
+ if (!uvmem_bitmap)
return H_UNSUPPORTED;
/* Only radix guests can be secure guests */
@@ -478,7 +478,7 @@ unsigned long kvmppc_h_svm_init_start(struct kvm *kvm)
/* register the memslot */
slots = kvm_memslots(kvm);
kvm_for_each_memslot(memslot, slots) {
- ret = __kvmppc_uvmem_memslot_create(kvm, memslot);
+ ret = __uvmem_memslot_create(kvm, memslot);
if (ret)
break;
}
@@ -488,7 +488,7 @@ unsigned long kvmppc_h_svm_init_start(struct kvm *kvm)
kvm_for_each_memslot(m, slots) {
if (m == memslot)
break;
- __kvmppc_uvmem_memslot_delete(kvm, memslot);
+ __uvmem_memslot_delete(kvm, memslot);
}
}
@@ -501,7 +501,7 @@ unsigned long kvmppc_h_svm_init_start(struct kvm *kvm)
* from secure memory using UV_PAGE_OUT uvcall.
* Caller must held kvm->arch.uvmem_lock.
*/
-static int __kvmppc_svm_page_out(struct vm_area_struct *vma,
+static int __uvmem_svm_page_out(struct vm_area_struct *vma,
unsigned long start,
unsigned long end, unsigned long page_shift,
struct kvm *kvm, unsigned long gpa)
@@ -509,7 +509,7 @@ static int __kvmppc_svm_page_out(struct vm_area_struct *vma,
unsigned long src_pfn, dst_pfn = 0;
struct migrate_vma mig;
struct page *dpage, *spage;
- struct kvmppc_uvmem_page_pvt *pvt;
+ struct uvmem_page_pvt *pvt;
unsigned long pfn;
int ret = U_SUCCESS;
@@ -519,11 +519,11 @@ static int __kvmppc_svm_page_out(struct vm_area_struct *vma,
mig.end = end;
mig.src = &src_pfn;
mig.dst = &dst_pfn;
- mig.pgmap_owner = &kvmppc_uvmem_pgmap;
+ mig.pgmap_owner = &uvmem_pgmap;
mig.flags = MIGRATE_VMA_SELECT_DEVICE_PRIVATE;
/* The requested page is already paged-out, nothing to do */
- if (!kvmppc_gfn_is_uvmem_pfn(gpa >> page_shift, kvm, NULL))
+ if (!uvmem_gfn_is_uvmem_pfn(gpa >> page_shift, kvm, NULL))
return ret;
ret = migrate_vma_setup(&mig);
@@ -573,7 +573,7 @@ static int __kvmppc_svm_page_out(struct vm_area_struct *vma,
return ret;
}
-static inline int kvmppc_svm_page_out(struct vm_area_struct *vma,
+static inline int uvmem_svm_page_out(struct vm_area_struct *vma,
unsigned long start, unsigned long end,
unsigned long page_shift,
struct kvm *kvm, unsigned long gpa)
@@ -581,7 +581,7 @@ static inline int kvmppc_svm_page_out(struct vm_area_struct *vma,
int ret;
mutex_lock(&kvm->arch.uvmem_lock);
- ret = __kvmppc_svm_page_out(vma, start, end, page_shift, kvm, gpa);
+ ret = __uvmem_svm_page_out(vma, start, end, page_shift, kvm, gpa);
mutex_unlock(&kvm->arch.uvmem_lock);
return ret;
@@ -599,7 +599,7 @@ void kvmppc_uvmem_drop_pages(const struct kvm_memory_slot *slot,
struct kvm *kvm, bool skip_page_out)
{
int i;
- struct kvmppc_uvmem_page_pvt *pvt;
+ struct uvmem_page_pvt *pvt;
struct page *uvmem_page;
struct vm_area_struct *vma = NULL;
unsigned long uvmem_pfn, gfn;
@@ -623,19 +623,19 @@ void kvmppc_uvmem_drop_pages(const struct kvm_memory_slot *slot,
mutex_lock(&kvm->arch.uvmem_lock);
- if (kvmppc_gfn_is_uvmem_pfn(gfn, kvm, &uvmem_pfn)) {
+ if (uvmem_gfn_is_uvmem_pfn(gfn, kvm, &uvmem_pfn)) {
uvmem_page = pfn_to_page(uvmem_pfn);
pvt = uvmem_page->zone_device_data;
pvt->skip_page_out = skip_page_out;
pvt->remove_gfn = true;
- if (__kvmppc_svm_page_out(vma, addr, addr + PAGE_SIZE,
+ if (__uvmem_svm_page_out(vma, addr, addr + PAGE_SIZE,
PAGE_SHIFT, kvm, pvt->gpa))
pr_err("Can't page out gpa:0x%lx addr:0x%lx\n",
pvt->gpa, addr);
} else {
/* Remove the shared flag if any */
- kvmppc_gfn_remove(gfn, kvm);
+ uvmem_gfn_remove(gfn, kvm);
}
mutex_unlock(&kvm->arch.uvmem_lock);
@@ -680,31 +680,31 @@ unsigned long kvmppc_h_svm_init_abort(struct kvm *kvm)
*
* Called with kvm->arch.uvmem_lock held
*/
-static struct page *kvmppc_uvmem_get_page(unsigned long gpa, struct kvm *kvm)
+static struct page *uvmem_get_page(unsigned long gpa, struct kvm *kvm)
{
struct page *dpage = NULL;
unsigned long bit, uvmem_pfn;
- struct kvmppc_uvmem_page_pvt *pvt;
+ struct uvmem_page_pvt *pvt;
unsigned long pfn_last, pfn_first;
- pfn_first = kvmppc_uvmem_pgmap.res.start >> PAGE_SHIFT;
+ pfn_first = uvmem_pgmap.res.start >> PAGE_SHIFT;
pfn_last = pfn_first +
- (resource_size(&kvmppc_uvmem_pgmap.res) >> PAGE_SHIFT);
+ (resource_size(&uvmem_pgmap.res) >> PAGE_SHIFT);
- spin_lock(&kvmppc_uvmem_bitmap_lock);
- bit = find_first_zero_bit(kvmppc_uvmem_bitmap,
+ spin_lock(&uvmem_bitmap_lock);
+ bit = find_first_zero_bit(uvmem_bitmap,
pfn_last - pfn_first);
if (bit >= (pfn_last - pfn_first))
goto out;
- bitmap_set(kvmppc_uvmem_bitmap, bit, 1);
- spin_unlock(&kvmppc_uvmem_bitmap_lock);
+ bitmap_set(uvmem_bitmap, bit, 1);
+ spin_unlock(&uvmem_bitmap_lock);
pvt = kzalloc(sizeof(*pvt), GFP_KERNEL);
if (!pvt)
goto out_clear;
uvmem_pfn = bit + pfn_first;
- kvmppc_gfn_secure_uvmem_pfn(gpa >> PAGE_SHIFT, uvmem_pfn, kvm);
+ uvmem_gfn_secure_uvmem_pfn(gpa >> PAGE_SHIFT, uvmem_pfn, kvm);
pvt->gpa = gpa;
pvt->kvm = kvm;
@@ -715,10 +715,10 @@ static struct page *kvmppc_uvmem_get_page(unsigned long gpa, struct kvm *kvm)
lock_page(dpage);
return dpage;
out_clear:
- spin_lock(&kvmppc_uvmem_bitmap_lock);
- bitmap_clear(kvmppc_uvmem_bitmap, bit, 1);
+ spin_lock(&uvmem_bitmap_lock);
+ bitmap_clear(uvmem_bitmap, bit, 1);
out:
- spin_unlock(&kvmppc_uvmem_bitmap_lock);
+ spin_unlock(&uvmem_bitmap_lock);
return NULL;
}
@@ -726,7 +726,7 @@ static struct page *kvmppc_uvmem_get_page(unsigned long gpa, struct kvm *kvm)
* Alloc a PFN from private device memory pool. If @pagein is true,
* copy page from normal memory to secure memory using UV_PAGE_IN uvcall.
*/
-static int kvmppc_svm_page_in(struct vm_area_struct *vma,
+static int uvmem_svm_page_in(struct vm_area_struct *vma,
unsigned long start,
unsigned long end, unsigned long gpa, struct kvm *kvm,
unsigned long page_shift,
@@ -756,7 +756,7 @@ static int kvmppc_svm_page_in(struct vm_area_struct *vma,
goto out_finalize;
}
- dpage = kvmppc_uvmem_get_page(gpa, kvm);
+ dpage = uvmem_get_page(gpa, kvm);
if (!dpage) {
ret = -1;
goto out_finalize;
@@ -780,7 +780,7 @@ static int kvmppc_svm_page_in(struct vm_area_struct *vma,
return ret;
}
-static int kvmppc_uv_migrate_mem_slot(struct kvm *kvm,
+static int uvmem_uv_migrate_mem_slot(struct kvm *kvm,
const struct kvm_memory_slot *memslot)
{
unsigned long gfn = memslot->base_gfn;
@@ -790,7 +790,7 @@ static int kvmppc_uv_migrate_mem_slot(struct kvm *kvm,
mmap_read_lock(kvm->mm);
mutex_lock(&kvm->arch.uvmem_lock);
- while (kvmppc_next_nontransitioned_gfn(memslot, kvm, &gfn)) {
+ while (uvmem_next_nontransitioned_gfn(memslot, kvm, &gfn)) {
ret = H_STATE;
start = gfn_to_hva(kvm, gfn);
if (kvm_is_error_hva(start))
@@ -801,7 +801,7 @@ static int kvmppc_uv_migrate_mem_slot(struct kvm *kvm,
if (!vma || vma->vm_start > start || vma->vm_end < end)
break;
- ret = kvmppc_svm_page_in(vma, start, end,
+ ret = uvmem_svm_page_in(vma, start, end,
(gfn << PAGE_SHIFT), kvm, PAGE_SHIFT, false);
if (ret) {
ret = H_STATE;
@@ -830,7 +830,7 @@ unsigned long kvmppc_h_svm_init_done(struct kvm *kvm)
srcu_idx = srcu_read_lock(&kvm->srcu);
slots = kvm_memslots(kvm);
kvm_for_each_memslot(memslot, slots) {
- ret = kvmppc_uv_migrate_mem_slot(kvm, memslot);
+ ret = uvmem_uv_migrate_mem_slot(kvm, memslot);
if (ret) {
/*
* The pages will remain transitioned.
@@ -863,13 +863,13 @@ unsigned long kvmppc_h_svm_init_done(struct kvm *kvm)
* In the former case, uses dev_pagemap_ops.migrate_to_ram handler
* to unmap the device page from QEMU's page tables.
*/
-static unsigned long kvmppc_share_page(struct kvm *kvm, unsigned long gpa,
+static unsigned long uvmem_share_page(struct kvm *kvm, unsigned long gpa,
unsigned long page_shift)
{
int ret = H_PARAMETER;
struct page *uvmem_page;
- struct kvmppc_uvmem_page_pvt *pvt;
+ struct uvmem_page_pvt *pvt;
unsigned long pfn;
unsigned long gfn = gpa >> page_shift;
int srcu_idx;
@@ -877,7 +877,7 @@ static unsigned long kvmppc_share_page(struct kvm *kvm, unsigned long gpa,
srcu_idx = srcu_read_lock(&kvm->srcu);
mutex_lock(&kvm->arch.uvmem_lock);
- if (kvmppc_gfn_is_uvmem_pfn(gfn, kvm, &uvmem_pfn)) {
+ if (uvmem_gfn_is_uvmem_pfn(gfn, kvm, &uvmem_pfn)) {
uvmem_page = pfn_to_page(uvmem_pfn);
pvt = uvmem_page->zone_device_data;
pvt->skip_page_out = true;
@@ -895,7 +895,7 @@ static unsigned long kvmppc_share_page(struct kvm *kvm, unsigned long gpa,
goto out;
mutex_lock(&kvm->arch.uvmem_lock);
- if (kvmppc_gfn_is_uvmem_pfn(gfn, kvm, &uvmem_pfn)) {
+ if (uvmem_gfn_is_uvmem_pfn(gfn, kvm, &uvmem_pfn)) {
uvmem_page = pfn_to_page(uvmem_pfn);
pvt = uvmem_page->zone_device_data;
pvt->skip_page_out = true;
@@ -906,7 +906,7 @@ static unsigned long kvmppc_share_page(struct kvm *kvm, unsigned long gpa,
if (!uv_page_in(kvm->arch.lpid, pfn << page_shift, gpa, 0,
page_shift)) {
- kvmppc_gfn_shared(gfn, kvm);
+ uvmem_gfn_shared(gfn, kvm);
ret = H_SUCCESS;
}
kvm_release_pfn_clean(pfn);
@@ -942,7 +942,7 @@ unsigned long kvmppc_h_svm_page_in(struct kvm *kvm, unsigned long gpa,
return H_P2;
if (flags & H_PAGE_IN_SHARED)
- return kvmppc_share_page(kvm, gpa, page_shift);
+ return uvmem_share_page(kvm, gpa, page_shift);
ret = H_PARAMETER;
srcu_idx = srcu_read_lock(&kvm->srcu);
@@ -954,7 +954,7 @@ unsigned long kvmppc_h_svm_page_in(struct kvm *kvm, unsigned long gpa,
mutex_lock(&kvm->arch.uvmem_lock);
/* Fail the page-in request of an already paged-in page */
- if (kvmppc_gfn_is_uvmem_pfn(gfn, kvm, NULL))
+ if (uvmem_gfn_is_uvmem_pfn(gfn, kvm, NULL))
goto out_unlock;
end = start + (1UL << page_shift);
@@ -962,7 +962,7 @@ unsigned long kvmppc_h_svm_page_in(struct kvm *kvm, unsigned long gpa,
if (!vma || vma->vm_start > start || vma->vm_end < end)
goto out_unlock;
- if (kvmppc_svm_page_in(vma, start, end, gpa, kvm, page_shift,
+ if (uvmem_svm_page_in(vma, start, end, gpa, kvm, page_shift,
true))
goto out_unlock;
@@ -987,9 +987,9 @@ unsigned long kvmppc_h_svm_page_in(struct kvm *kvm, unsigned long gpa,
*/
static vm_fault_t kvmppc_uvmem_migrate_to_ram(struct vm_fault *vmf)
{
- struct kvmppc_uvmem_page_pvt *pvt = vmf->page->zone_device_data;
+ struct uvmem_page_pvt *pvt = vmf->page->zone_device_data;
- if (kvmppc_svm_page_out(vmf->vma, vmf->address,
+ if (uvmem_svm_page_out(vmf->vma, vmf->address,
vmf->address + PAGE_SIZE, PAGE_SHIFT,
pvt->kvm, pvt->gpa))
return VM_FAULT_SIGBUS;
@@ -1007,23 +1007,23 @@ static vm_fault_t kvmppc_uvmem_migrate_to_ram(struct vm_fault *vmf)
static void kvmppc_uvmem_page_free(struct page *page)
{
unsigned long pfn = page_to_pfn(page) -
- (kvmppc_uvmem_pgmap.res.start >> PAGE_SHIFT);
- struct kvmppc_uvmem_page_pvt *pvt;
+ (uvmem_pgmap.res.start >> PAGE_SHIFT);
+ struct uvmem_page_pvt *pvt;
- spin_lock(&kvmppc_uvmem_bitmap_lock);
- bitmap_clear(kvmppc_uvmem_bitmap, pfn, 1);
- spin_unlock(&kvmppc_uvmem_bitmap_lock);
+ spin_lock(&uvmem_bitmap_lock);
+ bitmap_clear(uvmem_bitmap, pfn, 1);
+ spin_unlock(&uvmem_bitmap_lock);
pvt = page->zone_device_data;
page->zone_device_data = NULL;
if (pvt->remove_gfn)
- kvmppc_gfn_remove(pvt->gpa >> PAGE_SHIFT, pvt->kvm);
+ uvmem_gfn_remove(pvt->gpa >> PAGE_SHIFT, pvt->kvm);
else
- kvmppc_gfn_secure_mem_pfn(pvt->gpa >> PAGE_SHIFT, pvt->kvm);
+ uvmem_gfn_secure_mem_pfn(pvt->gpa >> PAGE_SHIFT, pvt->kvm);
kfree(pvt);
}
-static const struct dev_pagemap_ops kvmppc_uvmem_ops = {
+static const struct dev_pagemap_ops uvmem_ops = {
.page_free = kvmppc_uvmem_page_free,
.migrate_to_ram = kvmppc_uvmem_migrate_to_ram,
};
@@ -1062,7 +1062,7 @@ static void kvmppc_uvmem_page_free(struct page *page)
if (!vma || vma->vm_start > start || vma->vm_end < end)
goto out;
- if (!kvmppc_svm_page_out(vma, start, end, page_shift, kvm, gpa))
+ if (!uvmem_svm_page_out(vma, start, end, page_shift, kvm, gpa))
ret = H_SUCCESS;
out:
mmap_read_unlock(kvm->mm);
@@ -1080,7 +1080,7 @@ int kvmppc_send_page_to_uv(struct kvm *kvm, unsigned long gfn)
return -EFAULT;
mutex_lock(&kvm->arch.uvmem_lock);
- if (kvmppc_gfn_is_uvmem_pfn(gfn, kvm, NULL))
+ if (uvmem_gfn_is_uvmem_pfn(gfn, kvm, NULL))
goto out;
ret = uv_page_in(kvm->arch.lpid, pfn << PAGE_SHIFT, gfn << PAGE_SHIFT,
@@ -1093,20 +1093,20 @@ int kvmppc_send_page_to_uv(struct kvm *kvm, unsigned long gfn)
int kvmppc_uvmem_memslot_create(struct kvm *kvm, const struct kvm_memory_slot *new)
{
- int ret = __kvmppc_uvmem_memslot_create(kvm, new);
+ int ret = __uvmem_memslot_create(kvm, new);
if (!ret)
- ret = kvmppc_uv_migrate_mem_slot(kvm, new);
+ ret = uvmem_uv_migrate_mem_slot(kvm, new);
return ret;
}
void kvmppc_uvmem_memslot_delete(struct kvm *kvm, const struct kvm_memory_slot *old)
{
- __kvmppc_uvmem_memslot_delete(kvm, old);
+ __uvmem_memslot_delete(kvm, old);
}
-static u64 kvmppc_get_secmem_size(void)
+static u64 uvmem_get_secmem_size(void)
{
struct device_node *np;
int i, len;
@@ -1152,7 +1152,7 @@ int kvmppc_uvmem_init(void)
void *addr;
unsigned long pfn_last, pfn_first;
- size = kvmppc_get_secmem_size();
+ size = uvmem_get_secmem_size();
if (!size) {
/*
* Don't fail the initialization of kvm-hv module if
@@ -1163,18 +1163,18 @@ int kvmppc_uvmem_init(void)
goto out;
}
- res = request_free_mem_region(&iomem_resource, size, "kvmppc_uvmem");
+ res = request_free_mem_region(&iomem_resource, size, "uvmem");
if (IS_ERR(res)) {
ret = PTR_ERR(res);
goto out;
}
- kvmppc_uvmem_pgmap.type = MEMORY_DEVICE_PRIVATE;
- kvmppc_uvmem_pgmap.res = *res;
- kvmppc_uvmem_pgmap.ops = &kvmppc_uvmem_ops;
+ uvmem_pgmap.type = MEMORY_DEVICE_PRIVATE;
+ uvmem_pgmap.res = *res;
+ uvmem_pgmap.ops = &uvmem_ops;
/* just one global instance: */
- kvmppc_uvmem_pgmap.owner = &kvmppc_uvmem_pgmap;
- addr = memremap_pages(&kvmppc_uvmem_pgmap, NUMA_NO_NODE);
+ uvmem_pgmap.owner = &uvmem_pgmap;
+ addr = memremap_pages(&uvmem_pgmap, NUMA_NO_NODE);
if (IS_ERR(addr)) {
ret = PTR_ERR(addr);
goto out_free_region;
@@ -1182,9 +1182,9 @@ int kvmppc_uvmem_init(void)
pfn_first = res->start >> PAGE_SHIFT;
pfn_last = pfn_first + (resource_size(res) >> PAGE_SHIFT);
- kvmppc_uvmem_bitmap = kcalloc(BITS_TO_LONGS(pfn_last - pfn_first),
+ uvmem_bitmap = kcalloc(BITS_TO_LONGS(pfn_last - pfn_first),
sizeof(unsigned long), GFP_KERNEL);
- if (!kvmppc_uvmem_bitmap) {
+ if (!uvmem_bitmap) {
ret = -ENOMEM;
goto out_unmap;
}
@@ -1192,7 +1192,7 @@ int kvmppc_uvmem_init(void)
pr_info("KVMPPC-UVMEM: Secure Memory size 0x%lx\n", size);
return ret;
out_unmap:
- memunmap_pages(&kvmppc_uvmem_pgmap);
+ memunmap_pages(&uvmem_pgmap);
out_free_region:
release_mem_region(res->start, size);
out:
@@ -1201,11 +1201,11 @@ int kvmppc_uvmem_init(void)
void kvmppc_uvmem_free(void)
{
- if (!kvmppc_uvmem_bitmap)
+ if (!uvmem_bitmap)
return;
- memunmap_pages(&kvmppc_uvmem_pgmap);
- release_mem_region(kvmppc_uvmem_pgmap.res.start,
- resource_size(&kvmppc_uvmem_pgmap.res));
- kfree(kvmppc_uvmem_bitmap);
+ memunmap_pages(&uvmem_pgmap);
+ release_mem_region(uvmem_pgmap.res.start,
+ resource_size(&uvmem_pgmap.res));
+ kfree(uvmem_bitmap);
}
--
1.8.3.1
^ permalink raw reply related
* [RFC v1 0/2] Plumbing to support multiple secure memory backends.
From: Ram Pai @ 2020-10-12 7:27 UTC (permalink / raw)
To: kvm-ppc, linuxppc-dev; +Cc: farosas, linuxram, bharata
Secure VMs are currently supported by the Ultravisor backend.
Enhance the plumbing to support multiple backends. Each backend shall
provide the implementation for the necessary and sufficient calls
in order to support secure VM.
Also as part of this change, modify the ultravisor implementation to
be a plugin that provides an implementation of the backend.
Ram Pai (2):
KVM: PPC: Book3S HV: rename all variables in book3s_hv_uvmem.c
KVM: PPC: Book3S HV: abstract secure VM related calls.
arch/powerpc/include/asm/kvm_book3s_uvmem.h | 100 ---------
arch/powerpc/include/asm/kvmppc_svm_backend.h | 250 ++++++++++++++++++++++
arch/powerpc/kvm/book3s_64_mmu_radix.c | 6 +-
arch/powerpc/kvm/book3s_hv.c | 28 +--
arch/powerpc/kvm/book3s_hv_uvmem.c | 288 +++++++++++++++-----------
5 files changed, 432 insertions(+), 240 deletions(-)
delete mode 100644 arch/powerpc/include/asm/kvm_book3s_uvmem.h
create mode 100644 arch/powerpc/include/asm/kvmppc_svm_backend.h
--
1.8.3.1
^ permalink raw reply
* Re: [PATCH RFC PKS/PMEM 22/58] fs/f2fs: Utilize new kmap_thread()
From: Ira Weiny @ 2020-10-12 6:56 UTC (permalink / raw)
To: Eric Biggers
Cc: linux-aio, linux-efi, kvm, linux-doc, Peter Zijlstra, linux-mmc,
Dave Hansen, dri-devel, linux-mm, target-devel, linux-mtd,
amd-gfx, linux-kselftest, Thomas Gleixner, drbd-dev, devel,
linux-cifs, linux-nilfs, linux-scsi, linux-nvdimm, linux-rdma,
x86, Matthew Wilcox, linux-afs, cluster-devel, Ingo Molnar,
intel-wired-lan, kexec, xen-devel, linux-ext4, bpf, Dan Williams,
Fenghua Yu, intel-gfx, ecryptfs, linux-um, reiserfs-devel,
linux-block, linux-bcache, Borislav Petkov, Andy Lutomirski,
Jaegeuk Kim, ceph-devel, io-uring, linux-cachefs, linux-nfs,
linux-ntfs-dev, netdev, linuxppc-dev, samba-technical,
linux-kernel, linux-f2fs-devel, linux-fsdevel, Andrew Morton,
linux-erofs, linux-btrfs
In-Reply-To: <20201010013036.GD1122@sol.localdomain>
On Fri, Oct 09, 2020 at 06:30:36PM -0700, Eric Biggers wrote:
> On Sat, Oct 10, 2020 at 01:39:54AM +0100, Matthew Wilcox wrote:
> > On Fri, Oct 09, 2020 at 02:34:34PM -0700, Eric Biggers wrote:
> > > On Fri, Oct 09, 2020 at 12:49:57PM -0700, ira.weiny@intel.com wrote:
> > > > The kmap() calls in this FS are localized to a single thread. To avoid
> > > > the over head of global PKRS updates use the new kmap_thread() call.
> > > >
> > > > @@ -2410,12 +2410,12 @@ static inline struct page *f2fs_pagecache_get_page(
> > > >
> > > > static inline void f2fs_copy_page(struct page *src, struct page *dst)
> > > > {
> > > > - char *src_kaddr = kmap(src);
> > > > - char *dst_kaddr = kmap(dst);
> > > > + char *src_kaddr = kmap_thread(src);
> > > > + char *dst_kaddr = kmap_thread(dst);
> > > >
> > > > memcpy(dst_kaddr, src_kaddr, PAGE_SIZE);
> > > > - kunmap(dst);
> > > > - kunmap(src);
> > > > + kunmap_thread(dst);
> > > > + kunmap_thread(src);
> > > > }
> > >
> > > Wouldn't it make more sense to switch cases like this to kmap_atomic()?
> > > The pages are only mapped to do a memcpy(), then they're immediately unmapped.
> >
> > Maybe you missed the earlier thread from Thomas trying to do something
> > similar for rather different reasons ...
> >
> > https://lore.kernel.org/lkml/20200919091751.011116649@linutronix.de/
>
> I did miss it. I'm not subscribed to any of the mailing lists it was sent to.
>
> Anyway, it shouldn't matter. Patchsets should be standalone, and not require
> reading random prior threads on linux-kernel to understand.
Sorry, but I did not think that the discussion above was directly related. If
I'm not mistaken, Thomas' work was directed at relaxing kmap_atomic() into
kmap_thread() calls. While interesting, it is not the point of this series. I
want to restrict kmap() callers into kmap_thread().
For this series it was considered to change the kmap_thread() call sites to
kmap_atomic(). But like I said in the cover letter kmap_atomic() is not the
same semantic. It is too strict. Perhaps I should have expanded that
explanation.
>
> And I still don't really understand. After this patchset, there is still code
> nearly identical to the above (doing a temporary mapping just for a memcpy) that
> would still be using kmap_atomic().
I don't understand. You mean there would be other call sites calling:
kmap_atomic()
memcpy()
kunmap_atomic()
?
> Is the idea that later, such code will be
> converted to use kmap_thread() instead? If not, why use one over the other?
The reason for the new call is that with PKS added behind kmap we have 3 levels
of mapping we want.
global kmap (can span threads and sleep)
'thread' kmap (can sleep but not span threads)
'atomic' kmap (can't sleep nor span threads [by definition])
As Matthew said perhaps 'global kmaps' may be best changed to vmaps? I just
don't know the details of every call site.
And since I don't know the call site details if there are kmap_thread() calls
which are better off as kmap_atomic() calls I think it is worth converting
them. But I made the assumption that kmap users would already be calling
kmap_atomic() if they could (because it is more efficient).
Ira
^ permalink raw reply
* Re: [PATCH RFC PKS/PMEM 57/58] nvdimm/pmem: Stray access protection for pmem->virt_addr
From: Ira Weiny @ 2020-10-12 5:52 UTC (permalink / raw)
To: John Hubbard
Cc: linux-aio, linux-efi, kvm, linux-doc, Peter Zijlstra, linux-mmc,
Dave Hansen, dri-devel, linux-mm, target-devel, linux-mtd,
linux-kselftest, samba-technical, Thomas Gleixner, drbd-dev,
devel, linux-cifs, linux-nilfs, linux-scsi, linux-nvdimm,
linux-rdma, x86, ceph-devel, amd-gfx, io-uring, cluster-devel,
Ingo Molnar, intel-wired-lan, xen-devel, linux-ext4, Fenghua Yu,
linux-afs, linux-um, intel-gfx, ecryptfs, linux-erofs,
reiserfs-devel, linux-block, linux-bcache, Borislav Petkov,
Andy Lutomirski, Dan Williams, Andrew Morton, linux-cachefs,
linux-nfs, linux-ntfs-dev, netdev, kexec, linux-kernel,
linux-f2fs-devel, linux-fsdevel, bpf, linuxppc-dev, linux-btrfs
In-Reply-To: <bd3f5ece-0e7b-4c15-abbc-1b3b943334dc@nvidia.com>
On Fri, Oct 09, 2020 at 07:53:07PM -0700, John Hubbard wrote:
> On 10/9/20 12:50 PM, ira.weiny@intel.com wrote:
> > From: Ira Weiny <ira.weiny@intel.com>
> >
> > The pmem driver uses a cached virtual address to access its memory
> > directly. Because the nvdimm driver is well aware of the special
> > protections it has mapped memory with, we call dev_access_[en|dis]able()
> > around the direct pmem->virt_addr (pmem_addr) usage instead of the
> > unnecessary overhead of trying to get a page to kmap.
> >
> > Signed-off-by: Ira Weiny <ira.weiny@intel.com>
> > ---
> > drivers/nvdimm/pmem.c | 4 ++++
> > 1 file changed, 4 insertions(+)
> >
> > diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
> > index fab29b514372..e4dc1ae990fc 100644
> > --- a/drivers/nvdimm/pmem.c
> > +++ b/drivers/nvdimm/pmem.c
> > @@ -148,7 +148,9 @@ static blk_status_t pmem_do_read(struct pmem_device *pmem,
> > if (unlikely(is_bad_pmem(&pmem->bb, sector, len)))
> > return BLK_STS_IOERR;
> > + dev_access_enable(false);
> > rc = read_pmem(page, page_off, pmem_addr, len);
> > + dev_access_disable(false);
>
> Hi Ira!
>
> The APIs should be tweaked to use a symbol (GLOBAL, PER_THREAD), instead of
> true/false. Try reading the above and you'll see that it sounds like it's
> doing the opposite of what it is ("enable_this(false)" sounds like a clumsy
> API design to *disable*, right?). And there is no hint about the scope.
Sounds reasonable.
>
> And it *could* be so much more readable like this:
>
> dev_access_enable(DEV_ACCESS_THIS_THREAD);
I'll think about the flag name. I'm not liking 'this thread'.
Maybe DEV_ACCESS_[GLOBAL|THREAD]
Ira
^ permalink raw reply
* Re: [PATCH RFC PKS/PMEM 48/58] drivers/md: Utilize new kmap_thread()
From: Ira Weiny @ 2020-10-12 5:28 UTC (permalink / raw)
To: Coly Li
Cc: linux-aio, linux-efi, kvm, linux-doc, Peter Zijlstra, linux-mmc,
Dave Hansen, dri-devel, linux-mm, target-devel, linux-mtd,
linux-kselftest, samba-technical, Thomas Gleixner, drbd-dev,
devel, linux-cifs, linux-nilfs, linux-scsi, linux-nvdimm,
linux-rdma, x86, ceph-devel, amd-gfx, io-uring, cluster-devel,
Ingo Molnar, intel-wired-lan, xen-devel, linux-ext4,
Kent Overstreet, Fenghua Yu, linux-afs, linux-um, intel-gfx,
ecryptfs, linux-erofs, reiserfs-devel, linux-block, linux-bcache,
Borislav Petkov, Andy Lutomirski, Dan Williams, Andrew Morton,
linux-cachefs, linux-nfs, linux-ntfs-dev, netdev, kexec,
linux-kernel, linux-f2fs-devel, linux-fsdevel, bpf, linuxppc-dev,
linux-btrfs
In-Reply-To: <c802fbf4-f67a-b205-536d-9c71b440f9c8@suse.de>
On Sat, Oct 10, 2020 at 10:20:34AM +0800, Coly Li wrote:
> On 2020/10/10 03:50, ira.weiny@intel.com wrote:
> > From: Ira Weiny <ira.weiny@intel.com>
> >
> > These kmap() calls are localized to a single thread. To avoid the over
> > head of global PKRS updates use the new kmap_thread() call.
> >
>
> Hi Ira,
>
> There were a number of options considered.
>
> 1) Attempt to change all the thread local kmap() calls to kmap_atomic()
> 2) Introduce a flags parameter to kmap() to indicate if the mapping
> should be global or not
> 3) Change ~20-30 call sites to 'kmap_global()' to indicate that they
> require a global mapping of the pages
> 4) Change ~209 call sites to 'kmap_thread()' to indicate that the
> mapping is to be used within that thread of execution only
>
>
> I copied the above information from patch 00/58 to this message. The
> idea behind kmap_thread() is fine to me, but as you said the new api is
> very easy to be missed in new code (even for me). I would like to be
> supportive to option 2) introduce a flag to kmap(), then we won't forget
> the new thread-localized kmap method, and people won't ask why a
> _thread() function is called but no kthread created.
Thanks for the feedback.
I'm going to hold off making any changes until others weigh in. FWIW, I kind
of like option 2 as well. But there is already kmap_atomic() so it seemed like
kmap_XXXX() was more in line with the current API.
Thanks,
Ira
>
> Thanks.
>
>
> Coly Li
>
^ permalink raw reply
* Re: [PATCH RFC PKS/PMEM 10/58] drivers/rdma: Utilize new kmap_thread()
From: Ira Weiny @ 2020-10-12 4:47 UTC (permalink / raw)
To: Bernard Metzler
Cc: linux-aio, linux-efi, kvm, linux-doc, Peter Zijlstra, linux-mmc,
Dave Hansen, dri-devel, linux-mm, target-devel, linux-mtd,
linux-kselftest, samba-technical, Thomas Gleixner, devel,
linux-cifs, linux-nilfs, linux-scsi, linux-nvdimm, linux-rdma,
x86, ceph-devel, io-uring, cluster-devel, Jason Gunthorpe,
Doug Ledford, Ingo Molnar, intel-wired-lan, xen-devel, linux-ext4,
Fenghua Yu, linux-afs, Faisal Latif, linux-um, intel-gfx,
ecryptfs, linux-erofs, linux-nfs, reiserfs-devel, linux-block,
linux-bcache, Borislav Petkov, Andy Lutomirski, drbd-dev, amd-gfx,
Dan Williams, Shiraz Saleem, bpf, linux-cachefs, Mike Marciniszyn,
linux-ntfs-dev, netdev, Dennis Dalessandro, kexec, linux-kernel,
linux-f2fs-devel, linux-fsdevel, Andrew Morton, linuxppc-dev,
linux-btrfs
In-Reply-To: <OF849D92D8.F4735ECA-ON002585FD.003F5F27-002585FD.003FCBD6@notes.na.collabserv.com>
On Sat, Oct 10, 2020 at 11:36:49AM +0000, Bernard Metzler wrote:
> -----ira.weiny@intel.com wrote: -----
>
[snip]
> >@@ -505,7 +505,7 @@ static int siw_tx_hdt(struct siw_iwarp_tx *c_tx,
> >struct socket *s)
> > page_array[seg] = p;
> >
> > if (!c_tx->use_sendpage) {
> >- iov[seg].iov_base = kmap(p) + fp_off;
> >+ iov[seg].iov_base = kmap_thread(p) + fp_off;
>
> This misses a corresponding kunmap_thread() in siw_unmap_pages()
> (pls change line 403 in siw_qp_tx.c as well)
Thanks I missed that.
Done.
Ira
>
> Thanks,
> Bernard.
>
^ permalink raw reply
* Re: [PATCH v4 13/13] mm/debug_vm_pgtable: Avoid none pte in pte_clear_test
From: Aneesh Kumar K.V @ 2020-10-12 4:29 UTC (permalink / raw)
To: Guenter Roeck
Cc: Anshuman Khandual, linux-mm, akpm, linuxppc-dev, linux-riscv
In-Reply-To: <20201011200258.GA91021@roeck-us.net>
Guenter Roeck <linux@roeck-us.net> writes:
> On Wed, Sep 02, 2020 at 05:12:22PM +0530, Aneesh Kumar K.V wrote:
>> pte_clear_tests operate on an existing pte entry. Make sure that
>> is not a none pte entry.
>>
>> Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
>
> This patch causes all riscv64 images to crash. Reverting it
> as well as the follow-up patch fixes the problem, but there are
> still several warning messages starting with
> BUG kmem_cache (Not tainted): Freechain corrupt
> I did not try to track down this other problem.
>
> A detailed crash log is at
> https://kerneltests.org/builders/qemu-riscv64-next/builds/523/steps/qemubuildcommand/logs/stdio
>
> Bisect log is attached.
https://lore.kernel.org/linux-mm/87zh5wx51b.fsf@linux.ibm.com
This was mentioned earlier. The RANDOM_OR_VALUE used is interacting with
some of the riscv page table accessors.
-aneesh
^ permalink raw reply
* Re: [PATCH RFC PKS/PMEM 26/58] fs/zonefs: Utilize new kmap_thread()
From: Damien Le Moal @ 2020-10-12 2:30 UTC (permalink / raw)
To: ira.weiny@intel.com, Andrew Morton, Thomas Gleixner, Ingo Molnar,
Borislav Petkov, Andy Lutomirski, Peter Zijlstra
Cc: linux-aio@kvack.org, linux-efi@vger.kernel.org,
kvm@vger.kernel.org, linux-doc@vger.kernel.org,
kexec@lists.infradead.org, Dave Hansen,
dri-devel@lists.freedesktop.org, linux-mm@kvack.org,
target-devel@vger.kernel.org, linux-mtd@lists.infradead.org,
linux-kselftest@vger.kernel.org, samba-technical@lists.samba.org,
ceph-devel@vger.kernel.org, drbd-dev@lists.linbit.com,
Naohiro Aota, linux-cifs@vger.kernel.org,
linux-nilfs@vger.kernel.org, linux-scsi@vger.kernel.org,
linux-nvdimm@lists.01.org, linux-rdma@vger.kernel.org,
x86@kernel.org, amd-gfx@lists.freedesktop.org,
linux-afs@lists.infradead.org, cluster-devel@redhat.com,
linux-cachefs@redhat.com, intel-wired-lan@lists.osuosl.org,
xen-devel@lists.xenproject.org, linux-ext4@vger.kernel.org,
Fenghua Yu, devel@driverdev.osuosl.org,
linux-um@lists.infradead.org, intel-gfx@lists.freedesktop.org,
ecryptfs@vger.kernel.org, linux-erofs@lists.ozlabs.org,
reiserfs-devel@vger.kernel.org, linux-block@vger.kernel.org,
linux-bcache@vger.kernel.org, Dan Williams,
io-uring@vger.kernel.org, linux-nfs@vger.kernel.org,
linux-ntfs-dev@lists.sourceforge.net, netdev@vger.kernel.org,
linux-mmc@vger.kernel.org, linux-kernel@vger.kernel.org,
linux-f2fs-devel@lists.sourceforge.net,
linux-fsdevel@vger.kernel.org, bpf@vger.kernel.org,
linuxppc-dev@lists.ozlabs.org, linux-btrfs@vger.kernel.org
In-Reply-To: <20201009195033.3208459-27-ira.weiny@intel.com>
On 2020/10/10 4:52, ira.weiny@intel.com wrote:
> From: Ira Weiny <ira.weiny@intel.com>
>
> The kmap() calls in this FS are localized to a single thread. To avoid
> the over head of global PKRS updates use the new kmap_thread() call.
>
> Cc: Damien Le Moal <damien.lemoal@wdc.com>
> Cc: Naohiro Aota <naohiro.aota@wdc.com>
> Signed-off-by: Ira Weiny <ira.weiny@intel.com>
> ---
> fs/zonefs/super.c | 4 ++--
> 1 file changed, 2 insertions(+), 2 deletions(-)
>
> diff --git a/fs/zonefs/super.c b/fs/zonefs/super.c
> index 8ec7c8f109d7..2fd6c86beee1 100644
> --- a/fs/zonefs/super.c
> +++ b/fs/zonefs/super.c
> @@ -1297,7 +1297,7 @@ static int zonefs_read_super(struct super_block *sb)
> if (ret)
> goto free_page;
>
> - super = kmap(page);
> + super = kmap_thread(page);
>
> ret = -EINVAL;
> if (le32_to_cpu(super->s_magic) != ZONEFS_MAGIC)
> @@ -1349,7 +1349,7 @@ static int zonefs_read_super(struct super_block *sb)
> ret = 0;
>
> unmap:
> - kunmap(page);
> + kunmap_thread(page);
> free_page:
> __free_page(page);
>
>
acked-by: Damien Le Moal <damien.lemoal@wdc.com>
--
Damien Le Moal
Western Digital Research
^ permalink raw reply
* Re: [PATCH v5 1/5] powerpc/sstep: Emulate prefixed instructions only when CPU_FTR_ARCH_31 is set
From: Daniel Axtens @ 2020-10-12 1:51 UTC (permalink / raw)
To: Ravi Bangoria, mpe
Cc: ravi.bangoria, jniethe5, bala24, paulus, sandipan, naveen.n.rao,
linuxppc-dev
In-Reply-To: <20201011050908.72173-2-ravi.bangoria@linux.ibm.com>
Hi,
Apologies if this has come up in a previous revision.
> case 1:
> + if (!cpu_has_feature(CPU_FTR_ARCH_31))
> + return -1;
> +
> prefix_r = GET_PREFIX_R(word);
> ra = GET_PREFIX_RA(suffix);
The comment above analyse_instr reads in part:
* Return value is 1 if the instruction can be emulated just by
* updating *regs with the information in *op, -1 if we need the
* GPRs but *regs doesn't contain the full register set, or 0
* otherwise.
I was wondering why returning -1 if the instruction isn't supported the
right thing to do - it seemed to me that it should return 0?
I did look and see that there are other cases where the code returns -1
for an unsupported operation, e.g.:
#ifdef __powerpc64__
case 4:
if (!cpu_has_feature(CPU_FTR_ARCH_300))
return -1;
switch (word & 0x3f) {
case 48: /* maddhd */
That's from commit 930d6288a267 ("powerpc: sstep: Add support for
maddhd, maddhdu, maddld instructions"), but it's not explained there either
I see the same pattern in a number of commits: commit 6324320de609
("powerpc sstep: Add support for modsd, modud instructions"), commit
6c180071509a ("powerpc sstep: Add support for modsw, moduw
instructions"), commit a23987ef267a ("powerpc: sstep: Add support for
darn instruction") and a few others, all of which seem to have come
through Sandipan in February 2019. I haven't spotted any explanation for
why -1 was chosen, but I haven't checked the mailing list archives.
If -1 is OK, would it be possible to update the comment to explain why?
Kind regards,
Daniel
^ permalink raw reply
* Re: [PATCH] powerpc/smp: Use GFP_ATOMIC while allocating tmp mask
From: Michael Ellerman @ 2020-10-12 1:45 UTC (permalink / raw)
To: Srikar Dronamraju
Cc: Nathan Lynch, Gautham R Shenoy, Srikar Dronamraju, Qian Cai, LKML,
Valentin Schneider, Peter Zijlstra, linuxppc-dev, Ingo Molnar
In-Reply-To: <20201008034240.34059-1-srikar@linux.vnet.ibm.com>
Srikar Dronamraju <srikar@linux.vnet.ibm.com> writes:
> Qian Cai reported a regression where CPU Hotplug fails with the latest
> powerpc/next
>
> BUG: sleeping function called from invalid context at mm/slab.h:494
> in_atomic(): 1, irqs_disabled(): 1, non_block: 0, pid: 0, name: swapper/88
> no locks held by swapper/88/0.
> irq event stamp: 18074448
> hardirqs last enabled at (18074447): [<c0000000001a2a7c>] tick_nohz_idle_enter+0x9c/0x110
> hardirqs last disabled at (18074448): [<c000000000106798>] do_idle+0x138/0x3b0
> do_idle at kernel/sched/idle.c:253 (discriminator 1)
> softirqs last enabled at (18074440): [<c0000000000bbec4>] irq_enter_rcu+0x94/0xa0
> softirqs last disabled at (18074439): [<c0000000000bbea0>] irq_enter_rcu+0x70/0xa0
> CPU: 88 PID: 0 Comm: swapper/88 Tainted: G W 5.9.0-rc8-next-20201007 #1
> Call Trace:
> [c00020000a4bfcf0] [c000000000649e98] dump_stack+0xec/0x144 (unreliable)
> [c00020000a4bfd30] [c0000000000f6c34] ___might_sleep+0x2f4/0x310
> [c00020000a4bfdb0] [c000000000354f94] slab_pre_alloc_hook.constprop.82+0x124/0x190
> [c00020000a4bfe00] [c00000000035e9e8] __kmalloc_node+0x88/0x3a0
> slab_alloc_node at mm/slub.c:2817
> (inlined by) __kmalloc_node at mm/slub.c:4013
> [c00020000a4bfe80] [c0000000006494d8] alloc_cpumask_var_node+0x38/0x80
> kmalloc_node at include/linux/slab.h:577
> (inlined by) alloc_cpumask_var_node at lib/cpumask.c:116
> [c00020000a4bfef0] [c00000000003eedc] start_secondary+0x27c/0x800
> update_mask_by_l2 at arch/powerpc/kernel/smp.c:1267
> (inlined by) add_cpu_to_masks at arch/powerpc/kernel/smp.c:1387
> (inlined by) start_secondary at arch/powerpc/kernel/smp.c:1420
> [c00020000a4bff90] [c00000000000c468] start_secondary_resume+0x10/0x14
>
> Allocating a temporary mask while performing a CPU Hotplug operation
> with CONFIG_CPUMASK_OFFSTACK enabled, leads to calling a sleepable
> function from a atomic context. Fix this by allocating the temporary
> mask with GFP_ATOMIC flag.
>
> If there is a failure to allocate a mask, scheduler is going to observe
> that this CPU's topology is broken. Instead of having to speculate why
> the topology is broken, add a WARN_ON_ONCE.
>
> Fixes: 70a94089d7f7 ("powerpc/smp: Optimize update_coregroup_mask")
> Fixes: 3ab33d6dc3e9 ("powerpc/smp: Optimize update_mask_by_l2")
> Reported-by: Qian Cai <cai@redhat.com>
> Suggested-by: Qian Cai <cai@redhat.com>
> Signed-off-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
> Cc: linuxppc-dev <linuxppc-dev@lists.ozlabs.org>
> Cc: LKML <linux-kernel@vger.kernel.org>
> Cc: Michael Ellerman <mpe@ellerman.id.au>
> Cc: Nathan Lynch <nathanl@linux.ibm.com>
> Cc: Gautham R Shenoy <ego@linux.vnet.ibm.com>
> Cc: Ingo Molnar <mingo@kernel.org>
> Cc: Peter Zijlstra <peterz@infradead.org>
> Cc: Valentin Schneider <valentin.schneider@arm.com>
> Cc: Qian Cai <cai@redhat.com>
> ---
> arch/powerpc/kernel/smp.c | 6 ++++--
> 1 file changed, 4 insertions(+), 2 deletions(-)
>
> diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
> index 0dc1b85..1268558 100644
> --- a/arch/powerpc/kernel/smp.c
> +++ b/arch/powerpc/kernel/smp.c
> @@ -1264,7 +1264,8 @@ static bool update_mask_by_l2(int cpu)
> return false;
> }
>
> - alloc_cpumask_var_node(&mask, GFP_KERNEL, cpu_to_node(cpu));
> + /* In CPU-hotplug path, hence use GFP_ATOMIC */
> + WARN_ON_ONCE(!alloc_cpumask_var_node(&mask, GFP_ATOMIC, cpu_to_node(cpu)));
A failed memory allocation is not something that should trigger a WARN,
a pr_warn() maybe.
But ...
> cpumask_and(mask, cpu_online_mask, cpu_cpu_mask(cpu));
If the allocation failed this will oops (mask will be NULL).
cheers
^ permalink raw reply
* Re: [PATCH v4 13/13] mm/debug_vm_pgtable: Avoid none pte in pte_clear_test
From: Guenter Roeck @ 2020-10-11 20:02 UTC (permalink / raw)
To: Aneesh Kumar K.V; +Cc: linux-mm, akpm, Anshuman Khandual, linuxppc-dev
In-Reply-To: <20200902114222.181353-14-aneesh.kumar@linux.ibm.com>
On Wed, Sep 02, 2020 at 05:12:22PM +0530, Aneesh Kumar K.V wrote:
> pte_clear_tests operate on an existing pte entry. Make sure that
> is not a none pte entry.
>
> Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
This patch causes all riscv64 images to crash. Reverting it
as well as the follow-up patch fixes the problem, but there are
still several warning messages starting with
BUG kmem_cache (Not tainted): Freechain corrupt
I did not try to track down this other problem.
A detailed crash log is at
https://kerneltests.org/builders/qemu-riscv64-next/builds/523/steps/qemubuildcommand/logs/stdio
Bisect log is attached.
Guenter
---
# bad: [d67bc7812221606e1886620a357b13f906814af7] Add linux-next specific files for 20201009
# good: [549738f15da0e5a00275977623be199fbbf7df50] Linux 5.9-rc8
git bisect start 'HEAD' 'v5.9-rc8'
# good: [b71be15b496cc71a3434a198fc1a1b9e08af6c57] Merge remote-tracking branch 'bpf-next/master' into master
git bisect good b71be15b496cc71a3434a198fc1a1b9e08af6c57
# good: [3542e5a87341bdca83e3d7f061b0f4e0f4c23f73] Merge remote-tracking branch 'spi/for-next' into master
git bisect good 3542e5a87341bdca83e3d7f061b0f4e0f4c23f73
# good: [65f9c957115c749ba79fb469083caf14101a93bb] Merge remote-tracking branch 'char-misc/char-misc-next' into master
git bisect good 65f9c957115c749ba79fb469083caf14101a93bb
# good: [aadfe5ecb55641d5994a5f3b27f074beead8f49b] Merge remote-tracking branch 'scsi-mkp/for-next' into master
git bisect good aadfe5ecb55641d5994a5f3b27f074beead8f49b
# good: [060196553d119d5c252f09ed5b0316929cc25983] Merge remote-tracking branch 'memblock/for-next' into master
git bisect good 060196553d119d5c252f09ed5b0316929cc25983
# bad: [d2340d89ffa6d2643f0689600dbf0969d86fdd3c] x86/setup: simplify initrd relocation and reservation
git bisect bad d2340d89ffa6d2643f0689600dbf0969d86fdd3c
# bad: [4b23734f5ba1a0487b2b569a9e64e4e5360009c1] mm/swapfile.c: remove unnecessary goto out in _swap_info_get()
git bisect bad 4b23734f5ba1a0487b2b569a9e64e4e5360009c1
# good: [b30f5277e97be65a99ca5af3d4337cb9acbf8fa7] device-dax: introduce 'struct dev_dax' typed-driver operations
git bisect good b30f5277e97be65a99ca5af3d4337cb9acbf8fa7
# good: [8c2075296dbbbce685fa14bbf46d29fba54f8a62] mm/debug_vm_pgtable: drop hugetlb_advanced_tests()
git bisect good 8c2075296dbbbce685fa14bbf46d29fba54f8a62
# bad: [52ce97889b3c85826995d22a690cd1430c14f316] mm/filemap: fix filemap_map_pages for THP
git bisect bad 52ce97889b3c85826995d22a690cd1430c14f316
# bad: [1ddc0b707be99faece6cdd77f34544f408c6617d] proc: optimise smaps for shmem entries
git bisect bad 1ddc0b707be99faece6cdd77f34544f408c6617d
# bad: [5d685be3785638202430b6baa2ecde482b52c41e] mm: factor find_get_incore_page out of mincore_page
git bisect bad 5d685be3785638202430b6baa2ecde482b52c41e
# bad: [0797f84d689b9f1e7256d954280b28bfeaf5b1fc] mm/debug_vm_pgtable: avoid doing memory allocation with pgtable_t mapped.
git bisect bad 0797f84d689b9f1e7256d954280b28bfeaf5b1fc
# bad: [4f9a78e6bcd60a25b187adc1526ab3815fc40dae] mm/debug_vm_pgtable: avoid none pte in pte_clear_test
git bisect bad 4f9a78e6bcd60a25b187adc1526ab3815fc40dae
# first bad commit: [4f9a78e6bcd60a25b187adc1526ab3815fc40dae] mm/debug_vm_pgtable: avoid none pte in pte_clear_test
^ permalink raw reply
* Re: [PATCH v5 1/5] powerpc/sstep: Emulate prefixed instructions only when CPU_FTR_ARCH_31 is set
From: Sandipan Das @ 2020-10-11 15:06 UTC (permalink / raw)
To: Ravi Bangoria, bala24; +Cc: naveen.n.rao, linuxppc-dev, paulus, jniethe5
In-Reply-To: <20201011050908.72173-2-ravi.bangoria@linux.ibm.com>
On 11/10/20 10:39 am, Ravi Bangoria wrote:
> From: Balamuruhan S <bala24@linux.ibm.com>
>
> Unconditional emulation of prefixed instructions will allow
> emulation of them on Power10 predecessors which might cause
> issues. Restrict that.
>
> Fixes: 3920742b92f5 ("powerpc sstep: Add support for prefixed fixed-point arithmetic")
> Fixes: 50b80a12e4cc ("powerpc sstep: Add support for prefixed load/stores")
> Signed-off-by: Balamuruhan S <bala24@linux.ibm.com>
> Signed-off-by: Ravi Bangoria <ravi.bangoria@linux.ibm.com>
> ---
> arch/powerpc/lib/sstep.c | 6 ++++++
> 1 file changed, 6 insertions(+)
>
> diff --git a/arch/powerpc/lib/sstep.c b/arch/powerpc/lib/sstep.c
> index e9dcaba9a4f8..e6242744c71b 100644
> --- a/arch/powerpc/lib/sstep.c
> +++ b/arch/powerpc/lib/sstep.c
> @@ -1346,6 +1346,9 @@ int analyse_instr(struct instruction_op *op, const struct pt_regs *regs,
> switch (opcode) {
> #ifdef __powerpc64__
> case 1:
> + if (!cpu_has_feature(CPU_FTR_ARCH_31))
> + return -1;
> +
> prefix_r = GET_PREFIX_R(word);
> ra = GET_PREFIX_RA(suffix);
> rd = (suffix >> 21) & 0x1f;
> @@ -2733,6 +2736,9 @@ int analyse_instr(struct instruction_op *op, const struct pt_regs *regs,
> }
> break;
> case 1: /* Prefixed instructions */
> + if (!cpu_has_feature(CPU_FTR_ARCH_31))
> + return -1;
> +
> prefix_r = GET_PREFIX_R(word);
> ra = GET_PREFIX_RA(suffix);
> op->update_reg = ra;
>
LGTM
Reviewed-by: Sandipan Das <sandipan@linux.ibm.com>
^ permalink raw reply
* [PATCH v5 5/5] powerpc/sstep: Add testcases for VSX vector paired load/store instructions
From: Ravi Bangoria @ 2020-10-11 5:09 UTC (permalink / raw)
To: mpe
Cc: ravi.bangoria, jniethe5, bala24, paulus, sandipan, naveen.n.rao,
linuxppc-dev
In-Reply-To: <20201011050908.72173-1-ravi.bangoria@linux.ibm.com>
From: Balamuruhan S <bala24@linux.ibm.com>
Add testcases for VSX vector paired load/store instructions.
Sample o/p:
emulate_step_test: lxvp : PASS
emulate_step_test: stxvp : PASS
emulate_step_test: lxvpx : PASS
emulate_step_test: stxvpx : PASS
emulate_step_test: plxvp : PASS
emulate_step_test: pstxvp : PASS
Signed-off-by: Balamuruhan S <bala24@linux.ibm.com>
Signed-off-by: Ravi Bangoria <ravi.bangoria@linux.ibm.com>
---
arch/powerpc/lib/test_emulate_step.c | 270 +++++++++++++++++++++++++++
1 file changed, 270 insertions(+)
diff --git a/arch/powerpc/lib/test_emulate_step.c b/arch/powerpc/lib/test_emulate_step.c
index 0a201b771477..783d1b85ecfe 100644
--- a/arch/powerpc/lib/test_emulate_step.c
+++ b/arch/powerpc/lib/test_emulate_step.c
@@ -612,6 +612,273 @@ static void __init test_lxvd2x_stxvd2x(void)
}
#endif /* CONFIG_VSX */
+#ifdef CONFIG_VSX
+static void __init test_lxvp_stxvp(void)
+{
+ struct pt_regs regs;
+ union {
+ vector128 a;
+ u32 b[4];
+ } c[2];
+ u32 cached_b[8];
+ int stepped = -1;
+
+ if (!cpu_has_feature(CPU_FTR_ARCH_31)) {
+ show_result("lxvp", "SKIP (!CPU_FTR_ARCH_31)");
+ show_result("stxvp", "SKIP (!CPU_FTR_ARCH_31)");
+ return;
+ }
+
+ init_pt_regs(®s);
+
+ /*** lxvp ***/
+
+ cached_b[0] = c[0].b[0] = 18233;
+ cached_b[1] = c[0].b[1] = 34863571;
+ cached_b[2] = c[0].b[2] = 834;
+ cached_b[3] = c[0].b[3] = 6138911;
+ cached_b[4] = c[1].b[0] = 1234;
+ cached_b[5] = c[1].b[1] = 5678;
+ cached_b[6] = c[1].b[2] = 91011;
+ cached_b[7] = c[1].b[3] = 121314;
+
+ regs.gpr[4] = (unsigned long)&c[0].a;
+
+ /*
+ * lxvp XTp,DQ(RA)
+ * XTp = 32xTX + 2xTp
+ * let TX=1 Tp=1 RA=4 DQ=0
+ */
+ stepped = emulate_step(®s, ppc_inst(PPC_RAW_LXVP(34, 4, 0)));
+
+ if (stepped == 1 && cpu_has_feature(CPU_FTR_VSX)) {
+ show_result("lxvp", "PASS");
+ } else {
+ if (!cpu_has_feature(CPU_FTR_VSX))
+ show_result("lxvp", "PASS (!CPU_FTR_VSX)");
+ else
+ show_result("lxvp", "FAIL");
+ }
+
+ /*** stxvp ***/
+
+ c[0].b[0] = 21379463;
+ c[0].b[1] = 87;
+ c[0].b[2] = 374234;
+ c[0].b[3] = 4;
+ c[1].b[0] = 90;
+ c[1].b[1] = 122;
+ c[1].b[2] = 555;
+ c[1].b[3] = 32144;
+
+ /*
+ * stxvp XSp,DQ(RA)
+ * XSp = 32xSX + 2xSp
+ * let SX=1 Sp=1 RA=4 DQ=0
+ */
+ stepped = emulate_step(®s, ppc_inst(PPC_RAW_STXVP(34, 4, 0)));
+
+ if (stepped == 1 && cached_b[0] == c[0].b[0] && cached_b[1] == c[0].b[1] &&
+ cached_b[2] == c[0].b[2] && cached_b[3] == c[0].b[3] &&
+ cached_b[4] == c[1].b[0] && cached_b[5] == c[1].b[1] &&
+ cached_b[6] == c[1].b[2] && cached_b[7] == c[1].b[3] &&
+ cpu_has_feature(CPU_FTR_VSX)) {
+ show_result("stxvp", "PASS");
+ } else {
+ if (!cpu_has_feature(CPU_FTR_VSX))
+ show_result("stxvp", "PASS (!CPU_FTR_VSX)");
+ else
+ show_result("stxvp", "FAIL");
+ }
+}
+#else
+static void __init test_lxvp_stxvp(void)
+{
+ show_result("lxvp", "SKIP (CONFIG_VSX is not set)");
+ show_result("stxvp", "SKIP (CONFIG_VSX is not set)");
+}
+#endif /* CONFIG_VSX */
+
+#ifdef CONFIG_VSX
+static void __init test_lxvpx_stxvpx(void)
+{
+ struct pt_regs regs;
+ union {
+ vector128 a;
+ u32 b[4];
+ } c[2];
+ u32 cached_b[8];
+ int stepped = -1;
+
+ if (!cpu_has_feature(CPU_FTR_ARCH_31)) {
+ show_result("lxvpx", "SKIP (!CPU_FTR_ARCH_31)");
+ show_result("stxvpx", "SKIP (!CPU_FTR_ARCH_31)");
+ return;
+ }
+
+ init_pt_regs(®s);
+
+ /*** lxvpx ***/
+
+ cached_b[0] = c[0].b[0] = 18233;
+ cached_b[1] = c[0].b[1] = 34863571;
+ cached_b[2] = c[0].b[2] = 834;
+ cached_b[3] = c[0].b[3] = 6138911;
+ cached_b[4] = c[1].b[0] = 1234;
+ cached_b[5] = c[1].b[1] = 5678;
+ cached_b[6] = c[1].b[2] = 91011;
+ cached_b[7] = c[1].b[3] = 121314;
+
+ regs.gpr[3] = (unsigned long)&c[0].a;
+ regs.gpr[4] = 0;
+
+ /*
+ * lxvpx XTp,RA,RB
+ * XTp = 32xTX + 2xTp
+ * let TX=1 Tp=1 RA=3 RB=4
+ */
+ stepped = emulate_step(®s, ppc_inst(PPC_RAW_LXVPX(34, 3, 4)));
+
+ if (stepped == 1 && cpu_has_feature(CPU_FTR_VSX)) {
+ show_result("lxvpx", "PASS");
+ } else {
+ if (!cpu_has_feature(CPU_FTR_VSX))
+ show_result("lxvpx", "PASS (!CPU_FTR_VSX)");
+ else
+ show_result("lxvpx", "FAIL");
+ }
+
+ /*** stxvpx ***/
+
+ c[0].b[0] = 21379463;
+ c[0].b[1] = 87;
+ c[0].b[2] = 374234;
+ c[0].b[3] = 4;
+ c[1].b[0] = 90;
+ c[1].b[1] = 122;
+ c[1].b[2] = 555;
+ c[1].b[3] = 32144;
+
+ /*
+ * stxvpx XSp,RA,RB
+ * XSp = 32xSX + 2xSp
+ * let SX=1 Sp=1 RA=3 RB=4
+ */
+ stepped = emulate_step(®s, ppc_inst(PPC_RAW_STXVPX(34, 3, 4)));
+
+ if (stepped == 1 && cached_b[0] == c[0].b[0] && cached_b[1] == c[0].b[1] &&
+ cached_b[2] == c[0].b[2] && cached_b[3] == c[0].b[3] &&
+ cached_b[4] == c[1].b[0] && cached_b[5] == c[1].b[1] &&
+ cached_b[6] == c[1].b[2] && cached_b[7] == c[1].b[3] &&
+ cpu_has_feature(CPU_FTR_VSX)) {
+ show_result("stxvpx", "PASS");
+ } else {
+ if (!cpu_has_feature(CPU_FTR_VSX))
+ show_result("stxvpx", "PASS (!CPU_FTR_VSX)");
+ else
+ show_result("stxvpx", "FAIL");
+ }
+}
+#else
+static void __init test_lxvpx_stxvpx(void)
+{
+ show_result("lxvpx", "SKIP (CONFIG_VSX is not set)");
+ show_result("stxvpx", "SKIP (CONFIG_VSX is not set)");
+}
+#endif /* CONFIG_VSX */
+
+#ifdef CONFIG_VSX
+static void __init test_plxvp_pstxvp(void)
+{
+ struct ppc_inst instr;
+ struct pt_regs regs;
+ union {
+ vector128 a;
+ u32 b[4];
+ } c[2];
+ u32 cached_b[8];
+ int stepped = -1;
+
+ if (!cpu_has_feature(CPU_FTR_ARCH_31)) {
+ show_result("plxvp", "SKIP (!CPU_FTR_ARCH_31)");
+ show_result("pstxvp", "SKIP (!CPU_FTR_ARCH_31)");
+ return;
+ }
+
+ /*** plxvp ***/
+
+ cached_b[0] = c[0].b[0] = 18233;
+ cached_b[1] = c[0].b[1] = 34863571;
+ cached_b[2] = c[0].b[2] = 834;
+ cached_b[3] = c[0].b[3] = 6138911;
+ cached_b[4] = c[1].b[0] = 1234;
+ cached_b[5] = c[1].b[1] = 5678;
+ cached_b[6] = c[1].b[2] = 91011;
+ cached_b[7] = c[1].b[3] = 121314;
+
+ init_pt_regs(®s);
+ regs.gpr[3] = (unsigned long)&c[0].a;
+
+ /*
+ * plxvp XTp,D(RA),R
+ * XTp = 32xTX + 2xTp
+ * let RA=3 R=0 D=d0||d1=0 R=0 Tp=1 TX=1
+ */
+ instr = ppc_inst_prefix(PPC_RAW_PLXVP(34, 0, 3, 0) >> 32,
+ PPC_RAW_PLXVP(34, 0, 3, 0) & 0xffffffff);
+
+ stepped = emulate_step(®s, instr);
+ if (stepped == 1 && cpu_has_feature(CPU_FTR_VSX)) {
+ show_result("plxvp", "PASS");
+ } else {
+ if (!cpu_has_feature(CPU_FTR_VSX))
+ show_result("plxvp", "PASS (!CPU_FTR_VSX)");
+ else
+ show_result("plxvp", "FAIL");
+ }
+
+ /*** pstxvp ***/
+
+ c[0].b[0] = 21379463;
+ c[0].b[1] = 87;
+ c[0].b[2] = 374234;
+ c[0].b[3] = 4;
+ c[1].b[0] = 90;
+ c[1].b[1] = 122;
+ c[1].b[2] = 555;
+ c[1].b[3] = 32144;
+
+ /*
+ * pstxvp XSp,D(RA),R
+ * XSp = 32xSX + 2xSp
+ * let RA=3 D=d0||d1=0 R=0 Sp=1 SX=1
+ */
+ instr = ppc_inst_prefix(PPC_RAW_PSTXVP(34, 0, 3, 0) >> 32,
+ PPC_RAW_PSTXVP(34, 0, 3, 0) & 0xffffffff);
+
+ stepped = emulate_step(®s, instr);
+
+ if (stepped == 1 && cached_b[0] == c[0].b[0] && cached_b[1] == c[0].b[1] &&
+ cached_b[2] == c[0].b[2] && cached_b[3] == c[0].b[3] &&
+ cached_b[4] == c[1].b[0] && cached_b[5] == c[1].b[1] &&
+ cached_b[6] == c[1].b[2] && cached_b[7] == c[1].b[3] &&
+ cpu_has_feature(CPU_FTR_VSX)) {
+ show_result("pstxvp", "PASS");
+ } else {
+ if (!cpu_has_feature(CPU_FTR_VSX))
+ show_result("pstxvp", "PASS (!CPU_FTR_VSX)");
+ else
+ show_result("pstxvp", "FAIL");
+ }
+}
+#else
+static void __init test_plxvp_pstxvp(void)
+{
+ show_result("plxvp", "SKIP (CONFIG_VSX is not set)");
+ show_result("pstxvp", "SKIP (CONFIG_VSX is not set)");
+}
+#endif /* CONFIG_VSX */
+
static void __init run_tests_load_store(void)
{
test_ld();
@@ -628,6 +895,9 @@ static void __init run_tests_load_store(void)
test_plfd_pstfd();
test_lvx_stvx();
test_lxvd2x_stxvd2x();
+ test_lxvp_stxvp();
+ test_lxvpx_stxvpx();
+ test_plxvp_pstxvp();
}
struct compute_test {
--
2.26.2
^ permalink raw reply related
* [PATCH v5 4/5] powerpc/ppc-opcode: Add encoding macros for VSX vector paired instructions
From: Ravi Bangoria @ 2020-10-11 5:09 UTC (permalink / raw)
To: mpe
Cc: ravi.bangoria, jniethe5, bala24, paulus, sandipan, naveen.n.rao,
linuxppc-dev
In-Reply-To: <20201011050908.72173-1-ravi.bangoria@linux.ibm.com>
From: Balamuruhan S <bala24@linux.ibm.com>
Add instruction encodings, DQ, D0, D1 immediate, XTP, XSP operands as
macros for new VSX vector paired instructions,
* Load VSX Vector Paired (lxvp)
* Load VSX Vector Paired Indexed (lxvpx)
* Prefixed Load VSX Vector Paired (plxvp)
* Store VSX Vector Paired (stxvp)
* Store VSX Vector Paired Indexed (stxvpx)
* Prefixed Store VSX Vector Paired (pstxvp)
Suggested-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Signed-off-by: Balamuruhan S <bala24@linux.ibm.com>
Signed-off-by: Ravi Bangoria <ravi.bangoria@linux.ibm.com>
---
arch/powerpc/include/asm/ppc-opcode.h | 13 +++++++++++++
1 file changed, 13 insertions(+)
diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h
index a6e3700c4566..5e7918ca4fb7 100644
--- a/arch/powerpc/include/asm/ppc-opcode.h
+++ b/arch/powerpc/include/asm/ppc-opcode.h
@@ -78,6 +78,9 @@
#define IMM_L(i) ((uintptr_t)(i) & 0xffff)
#define IMM_DS(i) ((uintptr_t)(i) & 0xfffc)
+#define IMM_DQ(i) ((uintptr_t)(i) & 0xfff0)
+#define IMM_D0(i) (((uintptr_t)(i) >> 16) & 0x3ffff)
+#define IMM_D1(i) IMM_L(i)
/*
* 16-bit immediate helper macros: HA() is for use with sign-extending instrs
@@ -295,6 +298,8 @@
#define __PPC_XB(b) ((((b) & 0x1f) << 11) | (((b) & 0x20) >> 4))
#define __PPC_XS(s) ((((s) & 0x1f) << 21) | (((s) & 0x20) >> 5))
#define __PPC_XT(s) __PPC_XS(s)
+#define __PPC_XSP(s) ((((s) & 0x1e) | (((s) >> 5) & 0x1)) << 21)
+#define __PPC_XTP(s) __PPC_XSP(s)
#define __PPC_T_TLB(t) (((t) & 0x3) << 21)
#define __PPC_WC(w) (((w) & 0x3) << 21)
#define __PPC_WS(w) (((w) & 0x1f) << 11)
@@ -395,6 +400,14 @@
#define PPC_RAW_XVCPSGNDP(t, a, b) ((0xf0000780 | VSX_XX3((t), (a), (b))))
#define PPC_RAW_VPERMXOR(vrt, vra, vrb, vrc) \
((0x1000002d | ___PPC_RT(vrt) | ___PPC_RA(vra) | ___PPC_RB(vrb) | (((vrc) & 0x1f) << 6)))
+#define PPC_RAW_LXVP(xtp, a, i) (0x18000000 | __PPC_XTP(xtp) | ___PPC_RA(a) | IMM_DQ(i))
+#define PPC_RAW_STXVP(xsp, a, i) (0x18000001 | __PPC_XSP(xsp) | ___PPC_RA(a) | IMM_DQ(i))
+#define PPC_RAW_LXVPX(xtp, a, b) (0x7c00029a | __PPC_XTP(xtp) | ___PPC_RA(a) | ___PPC_RB(b))
+#define PPC_RAW_STXVPX(xsp, a, b) (0x7c00039a | __PPC_XSP(xsp) | ___PPC_RA(a) | ___PPC_RB(b))
+#define PPC_RAW_PLXVP(xtp, i, a, pr) \
+ ((PPC_PREFIX_8LS | __PPC_PRFX_R(pr) | IMM_D0(i)) << 32 | (0xe8000000 | __PPC_XTP(xtp) | ___PPC_RA(a) | IMM_D1(i)))
+#define PPC_RAW_PSTXVP(xsp, i, a, pr) \
+ ((PPC_PREFIX_8LS | __PPC_PRFX_R(pr) | IMM_D0(i)) << 32 | (0xf8000000 | __PPC_XSP(xsp) | ___PPC_RA(a) | IMM_D1(i)))
#define PPC_RAW_NAP (0x4c000364)
#define PPC_RAW_SLEEP (0x4c0003a4)
#define PPC_RAW_WINKLE (0x4c0003e4)
--
2.26.2
^ permalink raw reply related
* [PATCH v5 3/5] powerpc/sstep: Support VSX vector paired storage access instructions
From: Ravi Bangoria @ 2020-10-11 5:09 UTC (permalink / raw)
To: mpe
Cc: ravi.bangoria, jniethe5, bala24, paulus, sandipan, naveen.n.rao,
linuxppc-dev
In-Reply-To: <20201011050908.72173-1-ravi.bangoria@linux.ibm.com>
From: Balamuruhan S <bala24@linux.ibm.com>
VSX Vector Paired instructions loads/stores an octword (32 bytes)
from/to storage into two sequential VSRs. Add emulation support
for these new instructions:
* Load VSX Vector Paired (lxvp)
* Load VSX Vector Paired Indexed (lxvpx)
* Prefixed Load VSX Vector Paired (plxvp)
* Store VSX Vector Paired (stxvp)
* Store VSX Vector Paired Indexed (stxvpx)
* Prefixed Store VSX Vector Paired (pstxvp)
Suggested-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Signed-off-by: Balamuruhan S <bala24@linux.ibm.com>
Signed-off-by: Ravi Bangoria <ravi.bangoria@linux.ibm.com>
[kernel test robot reported a build failure]
Reported-by: kernel test robot <lkp@intel.com>
---
arch/powerpc/lib/sstep.c | 150 +++++++++++++++++++++++++++++++++------
1 file changed, 129 insertions(+), 21 deletions(-)
diff --git a/arch/powerpc/lib/sstep.c b/arch/powerpc/lib/sstep.c
index faf0bbf3efb7..96ca813a65e7 100644
--- a/arch/powerpc/lib/sstep.c
+++ b/arch/powerpc/lib/sstep.c
@@ -32,6 +32,10 @@ extern char system_call_vectored_emulate[];
#define XER_OV32 0x00080000U
#define XER_CA32 0x00040000U
+#ifdef CONFIG_VSX
+#define VSX_REGISTER_XTP(rd) ((((rd) & 1) << 5) | ((rd) & 0xfe))
+#endif
+
#ifdef CONFIG_PPC_FPU
/*
* Functions in ldstfp.S
@@ -279,6 +283,19 @@ static nokprobe_inline void do_byte_reverse(void *ptr, int nb)
up[1] = tmp;
break;
}
+ case 32: {
+ unsigned long *up = (unsigned long *)ptr;
+ unsigned long tmp;
+
+ tmp = byterev_8(up[0]);
+ up[0] = byterev_8(up[3]);
+ up[3] = tmp;
+ tmp = byterev_8(up[2]);
+ up[2] = byterev_8(up[1]);
+ up[1] = tmp;
+ break;
+ }
+
#endif
default:
WARN_ON_ONCE(1);
@@ -709,6 +726,8 @@ void emulate_vsx_load(struct instruction_op *op, union vsx_reg *reg,
reg->d[0] = reg->d[1] = 0;
switch (op->element_size) {
+ case 32:
+ /* [p]lxvp[x] */
case 16:
/* whole vector; lxv[x] or lxvl[l] */
if (size == 0)
@@ -717,7 +736,7 @@ void emulate_vsx_load(struct instruction_op *op, union vsx_reg *reg,
if (IS_LE && (op->vsx_flags & VSX_LDLEFT))
rev = !rev;
if (rev)
- do_byte_reverse(reg, 16);
+ do_byte_reverse(reg, size);
break;
case 8:
/* scalar loads, lxvd2x, lxvdsx */
@@ -793,6 +812,20 @@ void emulate_vsx_store(struct instruction_op *op, const union vsx_reg *reg,
size = GETSIZE(op->type);
switch (op->element_size) {
+ case 32:
+ /* [p]stxvp[x] */
+ if (size == 0)
+ break;
+ if (rev) {
+ /* reverse 32 bytes */
+ buf.d[0] = byterev_8(reg->d[3]);
+ buf.d[1] = byterev_8(reg->d[2]);
+ buf.d[2] = byterev_8(reg->d[1]);
+ buf.d[3] = byterev_8(reg->d[0]);
+ reg = &buf;
+ }
+ memcpy(mem, reg, size);
+ break;
case 16:
/* stxv, stxvx, stxvl, stxvll */
if (size == 0)
@@ -861,28 +894,43 @@ static nokprobe_inline int do_vsx_load(struct instruction_op *op,
bool cross_endian)
{
int reg = op->reg;
- u8 mem[16];
- union vsx_reg buf;
+ int i, j, nr_vsx_regs;
+ u8 mem[32];
+ union vsx_reg buf[2];
int size = GETSIZE(op->type);
if (!address_ok(regs, ea, size) || copy_mem_in(mem, ea, size, regs))
return -EFAULT;
- emulate_vsx_load(op, &buf, mem, cross_endian);
+ nr_vsx_regs = size / sizeof(__vector128);
+ emulate_vsx_load(op, buf, mem, cross_endian);
preempt_disable();
if (reg < 32) {
/* FP regs + extensions */
if (regs->msr & MSR_FP) {
- load_vsrn(reg, &buf);
+ for (i = 0; i < nr_vsx_regs; i++) {
+ j = IS_LE ? nr_vsx_regs - i - 1 : i;
+ load_vsrn(reg + i, &buf[j].v);
+ }
} else {
- current->thread.fp_state.fpr[reg][0] = buf.d[0];
- current->thread.fp_state.fpr[reg][1] = buf.d[1];
+ for (i = 0; i < nr_vsx_regs; i++) {
+ j = IS_LE ? nr_vsx_regs - i - 1 : i;
+ current->thread.fp_state.fpr[reg + i][0] = buf[j].d[0];
+ current->thread.fp_state.fpr[reg + i][1] = buf[j].d[1];
+ }
}
} else {
- if (regs->msr & MSR_VEC)
- load_vsrn(reg, &buf);
- else
- current->thread.vr_state.vr[reg - 32] = buf.v;
+ if (regs->msr & MSR_VEC) {
+ for (i = 0; i < nr_vsx_regs; i++) {
+ j = IS_LE ? nr_vsx_regs - i - 1 : i;
+ load_vsrn(reg + i, &buf[j].v);
+ }
+ } else {
+ for (i = 0; i < nr_vsx_regs; i++) {
+ j = IS_LE ? nr_vsx_regs - i - 1 : i;
+ current->thread.vr_state.vr[reg - 32 + i] = buf[j].v;
+ }
+ }
}
preempt_enable();
return 0;
@@ -893,30 +941,45 @@ static nokprobe_inline int do_vsx_store(struct instruction_op *op,
bool cross_endian)
{
int reg = op->reg;
- u8 mem[16];
- union vsx_reg buf;
+ int i, j, nr_vsx_regs;
+ u8 mem[32];
+ union vsx_reg buf[2];
int size = GETSIZE(op->type);
if (!address_ok(regs, ea, size))
return -EFAULT;
+ nr_vsx_regs = size / sizeof(__vector128);
preempt_disable();
if (reg < 32) {
/* FP regs + extensions */
if (regs->msr & MSR_FP) {
- store_vsrn(reg, &buf);
+ for (i = 0; i < nr_vsx_regs; i++) {
+ j = IS_LE ? nr_vsx_regs - i - 1 : i;
+ store_vsrn(reg + i, &buf[j].v);
+ }
} else {
- buf.d[0] = current->thread.fp_state.fpr[reg][0];
- buf.d[1] = current->thread.fp_state.fpr[reg][1];
+ for (i = 0; i < nr_vsx_regs; i++) {
+ j = IS_LE ? nr_vsx_regs - i - 1 : i;
+ buf[j].d[0] = current->thread.fp_state.fpr[reg + i][0];
+ buf[j].d[1] = current->thread.fp_state.fpr[reg + i][1];
+ }
}
} else {
- if (regs->msr & MSR_VEC)
- store_vsrn(reg, &buf);
- else
- buf.v = current->thread.vr_state.vr[reg - 32];
+ if (regs->msr & MSR_VEC) {
+ for (i = 0; i < nr_vsx_regs; i++) {
+ j = IS_LE ? nr_vsx_regs - i - 1 : i;
+ store_vsrn(reg + i, &buf[j].v);
+ }
+ } else {
+ for (i = 0; i < nr_vsx_regs; i++) {
+ j = IS_LE ? nr_vsx_regs - i - 1 : i;
+ buf[j].v = current->thread.vr_state.vr[reg - 32 + i];
+ }
+ }
}
preempt_enable();
- emulate_vsx_store(op, &buf, mem, cross_endian);
+ emulate_vsx_store(op, buf, mem, cross_endian);
return copy_mem_out(mem, ea, size, regs);
}
#endif /* CONFIG_VSX */
@@ -2403,6 +2466,14 @@ int analyse_instr(struct instruction_op *op, const struct pt_regs *regs,
op->vsx_flags = VSX_SPLAT;
break;
+ case 333: /* lxvpx */
+ if (!cpu_has_feature(CPU_FTR_ARCH_31))
+ return -1;
+ op->reg = VSX_REGISTER_XTP(rd);
+ op->type = MKOP(LOAD_VSX, 0, 32);
+ op->element_size = 32;
+ break;
+
case 364: /* lxvwsx */
op->reg = rd | ((word & 1) << 5);
op->type = MKOP(LOAD_VSX, 0, 4);
@@ -2431,6 +2502,13 @@ int analyse_instr(struct instruction_op *op, const struct pt_regs *regs,
VSX_CHECK_VEC;
break;
}
+ case 461: /* stxvpx */
+ if (!cpu_has_feature(CPU_FTR_ARCH_31))
+ return -1;
+ op->reg = VSX_REGISTER_XTP(rd);
+ op->type = MKOP(STORE_VSX, 0, 32);
+ op->element_size = 32;
+ break;
case 524: /* lxsspx */
op->reg = rd | ((word & 1) << 5);
op->type = MKOP(LOAD_VSX, 0, 4);
@@ -2672,6 +2750,22 @@ int analyse_instr(struct instruction_op *op, const struct pt_regs *regs,
#endif
#ifdef CONFIG_VSX
+ case 6:
+ if (!cpu_has_feature(CPU_FTR_ARCH_31))
+ return -1;
+ op->ea = dqform_ea(word, regs);
+ op->reg = VSX_REGISTER_XTP(rd);
+ op->element_size = 32;
+ switch (word & 0xf) {
+ case 0: /* lxvp */
+ op->type = MKOP(LOAD_VSX, 0, 32);
+ break;
+ case 1: /* stxvp */
+ op->type = MKOP(STORE_VSX, 0, 32);
+ break;
+ }
+ break;
+
case 61: /* stfdp, lxv, stxsd, stxssp, stxv */
switch (word & 7) {
case 0: /* stfdp with LSB of DS field = 0 */
@@ -2805,12 +2899,26 @@ int analyse_instr(struct instruction_op *op, const struct pt_regs *regs,
case 57: /* pld */
op->type = MKOP(LOAD, PREFIXED, 8);
break;
+#ifdef CONFIG_VSX
+ case 58: /* plxvp */
+ op->reg = VSX_REGISTER_XTP(rd);
+ op->type = MKOP(LOAD_VSX, PREFIXED, 32);
+ op->element_size = 32;
+ break;
+#endif /* CONFIG_VSX */
case 60: /* pstq */
op->type = MKOP(STORE, PREFIXED, 16);
break;
case 61: /* pstd */
op->type = MKOP(STORE, PREFIXED, 8);
break;
+#ifdef CONFIG_VSX
+ case 62: /* pstxvp */
+ op->reg = VSX_REGISTER_XTP(rd);
+ op->type = MKOP(STORE_VSX, PREFIXED, 32);
+ op->element_size = 32;
+ break;
+#endif /* CONFIG_VSX */
}
break;
case 1: /* Type 01 Eight-Byte Register-to-Register */
--
2.26.2
^ permalink raw reply related
* [PATCH v5 2/5] powerpc/sstep: Cover new VSX instructions under CONFIG_VSX
From: Ravi Bangoria @ 2020-10-11 5:09 UTC (permalink / raw)
To: mpe
Cc: ravi.bangoria, jniethe5, bala24, paulus, sandipan, naveen.n.rao,
linuxppc-dev
In-Reply-To: <20201011050908.72173-1-ravi.bangoria@linux.ibm.com>
Recently added Power10 prefixed VSX instruction are included
unconditionally in the kernel. If they are executed on a
machine without VSX support, it might create issues. Fix that.
Also fix one mnemonics spelling mistake in comment.
Fixes: 50b80a12e4cc ("powerpc sstep: Add support for prefixed load/stores")
Signed-off-by: Ravi Bangoria <ravi.bangoria@linux.ibm.com>
---
arch/powerpc/lib/sstep.c | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/arch/powerpc/lib/sstep.c b/arch/powerpc/lib/sstep.c
index e6242744c71b..faf0bbf3efb7 100644
--- a/arch/powerpc/lib/sstep.c
+++ b/arch/powerpc/lib/sstep.c
@@ -2757,6 +2757,7 @@ int analyse_instr(struct instruction_op *op, const struct pt_regs *regs,
case 41: /* plwa */
op->type = MKOP(LOAD, PREFIXED | SIGNEXT, 4);
break;
+#ifdef CONFIG_VSX
case 42: /* plxsd */
op->reg = rd + 32;
op->type = MKOP(LOAD_VSX, PREFIXED, 8);
@@ -2797,13 +2798,14 @@ int analyse_instr(struct instruction_op *op, const struct pt_regs *regs,
op->element_size = 16;
op->vsx_flags = VSX_CHECK_VEC;
break;
+#endif /* CONFIG_VSX */
case 56: /* plq */
op->type = MKOP(LOAD, PREFIXED, 16);
break;
case 57: /* pld */
op->type = MKOP(LOAD, PREFIXED, 8);
break;
- case 60: /* stq */
+ case 60: /* pstq */
op->type = MKOP(STORE, PREFIXED, 16);
break;
case 61: /* pstd */
--
2.26.2
^ permalink raw reply related
* [PATCH v5 1/5] powerpc/sstep: Emulate prefixed instructions only when CPU_FTR_ARCH_31 is set
From: Ravi Bangoria @ 2020-10-11 5:09 UTC (permalink / raw)
To: mpe
Cc: ravi.bangoria, jniethe5, bala24, paulus, sandipan, naveen.n.rao,
linuxppc-dev
In-Reply-To: <20201011050908.72173-1-ravi.bangoria@linux.ibm.com>
From: Balamuruhan S <bala24@linux.ibm.com>
Unconditional emulation of prefixed instructions will allow
emulation of them on Power10 predecessors which might cause
issues. Restrict that.
Fixes: 3920742b92f5 ("powerpc sstep: Add support for prefixed fixed-point arithmetic")
Fixes: 50b80a12e4cc ("powerpc sstep: Add support for prefixed load/stores")
Signed-off-by: Balamuruhan S <bala24@linux.ibm.com>
Signed-off-by: Ravi Bangoria <ravi.bangoria@linux.ibm.com>
---
arch/powerpc/lib/sstep.c | 6 ++++++
1 file changed, 6 insertions(+)
diff --git a/arch/powerpc/lib/sstep.c b/arch/powerpc/lib/sstep.c
index e9dcaba9a4f8..e6242744c71b 100644
--- a/arch/powerpc/lib/sstep.c
+++ b/arch/powerpc/lib/sstep.c
@@ -1346,6 +1346,9 @@ int analyse_instr(struct instruction_op *op, const struct pt_regs *regs,
switch (opcode) {
#ifdef __powerpc64__
case 1:
+ if (!cpu_has_feature(CPU_FTR_ARCH_31))
+ return -1;
+
prefix_r = GET_PREFIX_R(word);
ra = GET_PREFIX_RA(suffix);
rd = (suffix >> 21) & 0x1f;
@@ -2733,6 +2736,9 @@ int analyse_instr(struct instruction_op *op, const struct pt_regs *regs,
}
break;
case 1: /* Prefixed instructions */
+ if (!cpu_has_feature(CPU_FTR_ARCH_31))
+ return -1;
+
prefix_r = GET_PREFIX_R(word);
ra = GET_PREFIX_RA(suffix);
op->update_reg = ra;
--
2.26.2
^ permalink raw reply related
* [PATCH v5 0/5] powerpc/sstep: VSX 32-byte vector paired load/store instructions
From: Ravi Bangoria @ 2020-10-11 5:09 UTC (permalink / raw)
To: mpe
Cc: ravi.bangoria, jniethe5, bala24, paulus, sandipan, naveen.n.rao,
linuxppc-dev
VSX vector paired instructions operates with octword (32-byte)
operand for loads and stores between storage and a pair of two
sequential Vector-Scalar Registers (VSRs). There are 4 word
instructions and 2 prefixed instructions that provides this
32-byte storage access operations - lxvp, lxvpx, stxvp, stxvpx,
plxvp, pstxvp.
Emulation infrastructure doesn't have support for these instructions,
to operate with 32-byte storage access and to operate with 2 VSX
registers. This patch series enables the instruction emulation
support and adds test cases for them respectively.
v4: https://lore.kernel.org/r/20201008072726.233086-1-ravi.bangoria@linux.ibm.com
Changes in v5:
-------------
* Fix build breakage reported by Kernel test robote
* Patch #2 is new. CONFIG_VSX check was missing for some VSX
instructions. Patch #2 adds that check.
Changes in v4:
-------------
* Patch #1 is (kind of) new.
* Patch #2 now enables both analyse_instr() and emulate_step()
unlike prev series where both were in separate patches.
* Patch #2 also has important fix for emulation on LE.
* Patch #3 and #4. Added XSP/XTP, D0/D1 instruction operands,
removed *_EX_OP, __PPC_T[P][X] macros which are incorrect,
and adhered to PPC_RAW_* convention.
* Added `CPU_FTR_ARCH_31` check in testcases to avoid failing
in p8/p9.
* Some consmetic changes.
* Rebased to powerpc/next
Changes in v3:
-------------
Worked on review comments and suggestions from Ravi and Naveen,
* Fix the do_vsx_load() to handle vsx instructions if MSR_FP/MSR_VEC
cleared in exception conditions and it reaches to read/write to
thread_struct member fp_state/vr_state respectively.
* Fix wrongly used `__vector128 v[2]` in struct vsx_reg as it should
hold a single vsx register size.
* Remove unnecessary `VSX_CHECK_VEC` flag set and condition to check
`VSX_LDLEFT` that is not applicable for these vsx instructions.
* Fix comments in emulate_vsx_load() that were misleading.
* Rebased on latest powerpc next branch.
Changes in v2:
-------------
* Fix suggestion from Sandipan, wrap ISA 3.1 instructions with
cpu_has_feature(CPU_FTR_ARCH_31) check.
Balamuruhan S (4):
powerpc/sstep: Emulate prefixed instructions only when CPU_FTR_ARCH_31
is set
powerpc/sstep: Support VSX vector paired storage access instructions
powerpc/ppc-opcode: Add encoding macros for VSX vector paired
instructions
powerpc/sstep: Add testcases for VSX vector paired load/store
instructions
Ravi Bangoria (1):
powerpc/sstep: Cover new VSX instructions under CONFIG_VSX
arch/powerpc/include/asm/ppc-opcode.h | 13 ++
arch/powerpc/lib/sstep.c | 160 ++++++++++++---
arch/powerpc/lib/test_emulate_step.c | 270 ++++++++++++++++++++++++++
3 files changed, 421 insertions(+), 22 deletions(-)
--
2.26.2
^ permalink raw reply
* Re: [PATCH RFC PKS/PMEM 09/58] drivers/gpu: Utilize new kmap_thread()
From: Ira Weiny @ 2020-10-10 23:01 UTC (permalink / raw)
To: Andrew Morton, Thomas Gleixner, Ingo Molnar, Borislav Petkov,
Andy Lutomirski, Peter Zijlstra, David Airlie, Patrik Jakobsson,
x86, Dave Hansen, Dan Williams, Fenghua Yu, linux-doc,
linux-kernel, linux-nvdimm, linux-fsdevel, linux-mm,
linux-kselftest, linuxppc-dev, kvm, netdev, bpf, kexec,
linux-bcache, linux-mtd, devel, linux-efi, linux-mmc, linux-scsi,
target-devel, linux-nfs, ceph-devel, linux-ext4, linux-aio,
io-uring, linux-erofs, linux-um, linux-ntfs-dev, reiserfs-devel,
linux-f2fs-devel, linux-nilfs, cluster-devel, ecryptfs,
linux-cifs, linux-btrfs, linux-afs, linux-rdma, amd-gfx,
dri-devel, intel-gfx, drbd-dev, linux-block, xen-devel,
linux-cachefs, samba-technical, intel-wired-lan
In-Reply-To: <20201009220349.GQ438822@phenom.ffwll.local>
On Sat, Oct 10, 2020 at 12:03:49AM +0200, Daniel Vetter wrote:
> On Fri, Oct 09, 2020 at 12:49:44PM -0700, ira.weiny@intel.com wrote:
> > From: Ira Weiny <ira.weiny@intel.com>
> >
> > These kmap() calls in the gpu stack are localized to a single thread.
> > To avoid the over head of global PKRS updates use the new kmap_thread()
> > call.
> >
> > Cc: David Airlie <airlied@linux.ie>
> > Cc: Daniel Vetter <daniel@ffwll.ch>
> > Cc: Patrik Jakobsson <patrik.r.jakobsson@gmail.com>
> > Signed-off-by: Ira Weiny <ira.weiny@intel.com>
>
> I'm guessing the entire pile goes in through some other tree.
>
Apologies for not realizing there were multiple maintainers here.
But, I was thinking it would land together through the mm tree once the core
support lands. I've tried to split these out in a way they can be easily
reviewed/acked by the correct developers.
> If so:
>
> Acked-by: Daniel Vetter <daniel.vetter@ffwll.ch>
>
> If you want this to land through maintainer trees, then we need a
> per-driver split (since aside from amdgpu and radeon they're all different
> subtrees).
It is just RFC for the moment. I need to get the core support accepted first
then this can land.
>
> btw the two kmap calls in drm you highlight in the cover letter should
> also be convertible to kmap_thread. We only hold vmalloc mappings for a
> longer time (or it'd be quite a driver bug). So if you want maybe throw
> those two as two additional patches on top, and we can do some careful
> review & testing for them.
Cool. I'll add them in.
Ira
> -Daniel
>
> > ---
> > drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 12 ++++++------
> > drivers/gpu/drm/gma500/gma_display.c | 4 ++--
> > drivers/gpu/drm/gma500/mmu.c | 10 +++++-----
> > drivers/gpu/drm/i915/gem/i915_gem_shmem.c | 4 ++--
> > .../gpu/drm/i915/gem/selftests/i915_gem_context.c | 4 ++--
> > drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c | 8 ++++----
> > drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c | 4 ++--
> > drivers/gpu/drm/i915/gt/intel_gtt.c | 4 ++--
> > drivers/gpu/drm/i915/gt/shmem_utils.c | 4 ++--
> > drivers/gpu/drm/i915/i915_gem.c | 8 ++++----
> > drivers/gpu/drm/i915/i915_gpu_error.c | 4 ++--
> > drivers/gpu/drm/i915/selftests/i915_perf.c | 4 ++--
> > drivers/gpu/drm/radeon/radeon_ttm.c | 4 ++--
> > 13 files changed, 37 insertions(+), 37 deletions(-)
> >
> > diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
> > index 978bae731398..bd564bccb7a3 100644
> > --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
> > +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
> > @@ -2437,11 +2437,11 @@ static ssize_t amdgpu_ttm_gtt_read(struct file *f, char __user *buf,
> >
> > page = adev->gart.pages[p];
> > if (page) {
> > - ptr = kmap(page);
> > + ptr = kmap_thread(page);
> > ptr += off;
> >
> > r = copy_to_user(buf, ptr, cur_size);
> > - kunmap(adev->gart.pages[p]);
> > + kunmap_thread(adev->gart.pages[p]);
> > } else
> > r = clear_user(buf, cur_size);
> >
> > @@ -2507,9 +2507,9 @@ static ssize_t amdgpu_iomem_read(struct file *f, char __user *buf,
> > if (p->mapping != adev->mman.bdev.dev_mapping)
> > return -EPERM;
> >
> > - ptr = kmap(p);
> > + ptr = kmap_thread(p);
> > r = copy_to_user(buf, ptr + off, bytes);
> > - kunmap(p);
> > + kunmap_thread(p);
> > if (r)
> > return -EFAULT;
> >
> > @@ -2558,9 +2558,9 @@ static ssize_t amdgpu_iomem_write(struct file *f, const char __user *buf,
> > if (p->mapping != adev->mman.bdev.dev_mapping)
> > return -EPERM;
> >
> > - ptr = kmap(p);
> > + ptr = kmap_thread(p);
> > r = copy_from_user(ptr + off, buf, bytes);
> > - kunmap(p);
> > + kunmap_thread(p);
> > if (r)
> > return -EFAULT;
> >
> > diff --git a/drivers/gpu/drm/gma500/gma_display.c b/drivers/gpu/drm/gma500/gma_display.c
> > index 3df6d6e850f5..35f4e55c941f 100644
> > --- a/drivers/gpu/drm/gma500/gma_display.c
> > +++ b/drivers/gpu/drm/gma500/gma_display.c
> > @@ -400,9 +400,9 @@ int gma_crtc_cursor_set(struct drm_crtc *crtc,
> > /* Copy the cursor to cursor mem */
> > tmp_dst = dev_priv->vram_addr + cursor_gt->offset;
> > for (i = 0; i < cursor_pages; i++) {
> > - tmp_src = kmap(gt->pages[i]);
> > + tmp_src = kmap_thread(gt->pages[i]);
> > memcpy(tmp_dst, tmp_src, PAGE_SIZE);
> > - kunmap(gt->pages[i]);
> > + kunmap_thread(gt->pages[i]);
> > tmp_dst += PAGE_SIZE;
> > }
> >
> > diff --git a/drivers/gpu/drm/gma500/mmu.c b/drivers/gpu/drm/gma500/mmu.c
> > index 505044c9a673..fba7a3a461fd 100644
> > --- a/drivers/gpu/drm/gma500/mmu.c
> > +++ b/drivers/gpu/drm/gma500/mmu.c
> > @@ -192,20 +192,20 @@ struct psb_mmu_pd *psb_mmu_alloc_pd(struct psb_mmu_driver *driver,
> > pd->invalid_pte = 0;
> > }
> >
> > - v = kmap(pd->dummy_pt);
> > + v = kmap_thread(pd->dummy_pt);
> > for (i = 0; i < (PAGE_SIZE / sizeof(uint32_t)); ++i)
> > v[i] = pd->invalid_pte;
> >
> > - kunmap(pd->dummy_pt);
> > + kunmap_thread(pd->dummy_pt);
> >
> > - v = kmap(pd->p);
> > + v = kmap_thread(pd->p);
> > for (i = 0; i < (PAGE_SIZE / sizeof(uint32_t)); ++i)
> > v[i] = pd->invalid_pde;
> >
> > - kunmap(pd->p);
> > + kunmap_thread(pd->p);
> >
> > clear_page(kmap(pd->dummy_page));
> > - kunmap(pd->dummy_page);
> > + kunmap_thread(pd->dummy_page);
> >
> > pd->tables = vmalloc_user(sizeof(struct psb_mmu_pt *) * 1024);
> > if (!pd->tables)
> > diff --git a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
> > index 38113d3c0138..274424795fb7 100644
> > --- a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
> > +++ b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
> > @@ -566,9 +566,9 @@ i915_gem_object_create_shmem_from_data(struct drm_i915_private *dev_priv,
> > if (err < 0)
> > goto fail;
> >
> > - vaddr = kmap(page);
> > + vaddr = kmap_thread(page);
> > memcpy(vaddr, data, len);
> > - kunmap(page);
> > + kunmap_thread(page);
> >
> > err = pagecache_write_end(file, file->f_mapping,
> > offset, len, len,
> > diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c
> > index 7ffc3c751432..b466c677d007 100644
> > --- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c
> > +++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c
> > @@ -1754,7 +1754,7 @@ static int check_scratch_page(struct i915_gem_context *ctx, u32 *out)
> > return -EINVAL;
> > }
> >
> > - vaddr = kmap(page);
> > + vaddr = kmap_thread(page);
> > if (!vaddr) {
> > pr_err("No (mappable) scratch page!\n");
> > return -EINVAL;
> > @@ -1765,7 +1765,7 @@ static int check_scratch_page(struct i915_gem_context *ctx, u32 *out)
> > pr_err("Inconsistent initial state of scratch page!\n");
> > err = -EINVAL;
> > }
> > - kunmap(page);
> > + kunmap_thread(page);
> >
> > return err;
> > }
> > diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c
> > index 9c7402ce5bf9..447df22e2e06 100644
> > --- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c
> > +++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c
> > @@ -143,7 +143,7 @@ static int check_partial_mapping(struct drm_i915_gem_object *obj,
> > intel_gt_flush_ggtt_writes(&to_i915(obj->base.dev)->gt);
> >
> > p = i915_gem_object_get_page(obj, offset >> PAGE_SHIFT);
> > - cpu = kmap(p) + offset_in_page(offset);
> > + cpu = kmap_thread(p) + offset_in_page(offset);
> > drm_clflush_virt_range(cpu, sizeof(*cpu));
> > if (*cpu != (u32)page) {
> > pr_err("Partial view for %lu [%u] (offset=%llu, size=%u [%llu, row size %u], fence=%d, tiling=%d, stride=%d) misalignment, expected write to page (%llu + %u [0x%llx]) of 0x%x, found 0x%x\n",
> > @@ -161,7 +161,7 @@ static int check_partial_mapping(struct drm_i915_gem_object *obj,
> > }
> > *cpu = 0;
> > drm_clflush_virt_range(cpu, sizeof(*cpu));
> > - kunmap(p);
> > + kunmap_thread(p);
> >
> > out:
> > __i915_vma_put(vma);
> > @@ -236,7 +236,7 @@ static int check_partial_mappings(struct drm_i915_gem_object *obj,
> > intel_gt_flush_ggtt_writes(&to_i915(obj->base.dev)->gt);
> >
> > p = i915_gem_object_get_page(obj, offset >> PAGE_SHIFT);
> > - cpu = kmap(p) + offset_in_page(offset);
> > + cpu = kmap_thread(p) + offset_in_page(offset);
> > drm_clflush_virt_range(cpu, sizeof(*cpu));
> > if (*cpu != (u32)page) {
> > pr_err("Partial view for %lu [%u] (offset=%llu, size=%u [%llu, row size %u], fence=%d, tiling=%d, stride=%d) misalignment, expected write to page (%llu + %u [0x%llx]) of 0x%x, found 0x%x\n",
> > @@ -254,7 +254,7 @@ static int check_partial_mappings(struct drm_i915_gem_object *obj,
> > }
> > *cpu = 0;
> > drm_clflush_virt_range(cpu, sizeof(*cpu));
> > - kunmap(p);
> > + kunmap_thread(p);
> > if (err)
> > return err;
> >
> > diff --git a/drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c b/drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c
> > index 7fb36b12fe7a..38da348282f1 100644
> > --- a/drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c
> > +++ b/drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c
> > @@ -731,7 +731,7 @@ static void swizzle_page(struct page *page)
> > char *vaddr;
> > int i;
> >
> > - vaddr = kmap(page);
> > + vaddr = kmap_thread(page);
> >
> > for (i = 0; i < PAGE_SIZE; i += 128) {
> > memcpy(temp, &vaddr[i], 64);
> > @@ -739,7 +739,7 @@ static void swizzle_page(struct page *page)
> > memcpy(&vaddr[i + 64], temp, 64);
> > }
> >
> > - kunmap(page);
> > + kunmap_thread(page);
> > }
> >
> > /**
> > diff --git a/drivers/gpu/drm/i915/gt/intel_gtt.c b/drivers/gpu/drm/i915/gt/intel_gtt.c
> > index 2a72cce63fd9..4cfb24e9ed62 100644
> > --- a/drivers/gpu/drm/i915/gt/intel_gtt.c
> > +++ b/drivers/gpu/drm/i915/gt/intel_gtt.c
> > @@ -312,9 +312,9 @@ static void poison_scratch_page(struct page *page, unsigned long size)
> > do {
> > void *vaddr;
> >
> > - vaddr = kmap(page);
> > + vaddr = kmap_thread(page);
> > memset(vaddr, POISON_FREE, PAGE_SIZE);
> > - kunmap(page);
> > + kunmap_thread(page);
> >
> > page = pfn_to_page(page_to_pfn(page) + 1);
> > size -= PAGE_SIZE;
> > diff --git a/drivers/gpu/drm/i915/gt/shmem_utils.c b/drivers/gpu/drm/i915/gt/shmem_utils.c
> > index 43c7acbdc79d..a40d3130cebf 100644
> > --- a/drivers/gpu/drm/i915/gt/shmem_utils.c
> > +++ b/drivers/gpu/drm/i915/gt/shmem_utils.c
> > @@ -142,12 +142,12 @@ static int __shmem_rw(struct file *file, loff_t off,
> > if (IS_ERR(page))
> > return PTR_ERR(page);
> >
> > - vaddr = kmap(page);
> > + vaddr = kmap_thread(page);
> > if (write)
> > memcpy(vaddr + offset_in_page(off), ptr, this);
> > else
> > memcpy(ptr, vaddr + offset_in_page(off), this);
> > - kunmap(page);
> > + kunmap_thread(page);
> > put_page(page);
> >
> > len -= this;
> > diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
> > index 9aa3066cb75d..cae8300fd224 100644
> > --- a/drivers/gpu/drm/i915/i915_gem.c
> > +++ b/drivers/gpu/drm/i915/i915_gem.c
> > @@ -312,14 +312,14 @@ shmem_pread(struct page *page, int offset, int len, char __user *user_data,
> > char *vaddr;
> > int ret;
> >
> > - vaddr = kmap(page);
> > + vaddr = kmap_thread(page);
> >
> > if (needs_clflush)
> > drm_clflush_virt_range(vaddr + offset, len);
> >
> > ret = __copy_to_user(user_data, vaddr + offset, len);
> >
> > - kunmap(page);
> > + kunmap_thread(page);
> >
> > return ret ? -EFAULT : 0;
> > }
> > @@ -708,7 +708,7 @@ shmem_pwrite(struct page *page, int offset, int len, char __user *user_data,
> > char *vaddr;
> > int ret;
> >
> > - vaddr = kmap(page);
> > + vaddr = kmap_thread(page);
> >
> > if (needs_clflush_before)
> > drm_clflush_virt_range(vaddr + offset, len);
> > @@ -717,7 +717,7 @@ shmem_pwrite(struct page *page, int offset, int len, char __user *user_data,
> > if (!ret && needs_clflush_after)
> > drm_clflush_virt_range(vaddr + offset, len);
> >
> > - kunmap(page);
> > + kunmap_thread(page);
> >
> > return ret ? -EFAULT : 0;
> > }
> > diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
> > index 3e6cbb0d1150..aecd469b6b6e 100644
> > --- a/drivers/gpu/drm/i915/i915_gpu_error.c
> > +++ b/drivers/gpu/drm/i915/i915_gpu_error.c
> > @@ -1058,9 +1058,9 @@ i915_vma_coredump_create(const struct intel_gt *gt,
> >
> > drm_clflush_pages(&page, 1);
> >
> > - s = kmap(page);
> > + s = kmap_thread(page);
> > ret = compress_page(compress, s, dst, false);
> > - kunmap(page);
> > + kunmap_thread(page);
> >
> > drm_clflush_pages(&page, 1);
> >
> > diff --git a/drivers/gpu/drm/i915/selftests/i915_perf.c b/drivers/gpu/drm/i915/selftests/i915_perf.c
> > index c2d001d9c0ec..7f7ef2d056f4 100644
> > --- a/drivers/gpu/drm/i915/selftests/i915_perf.c
> > +++ b/drivers/gpu/drm/i915/selftests/i915_perf.c
> > @@ -307,7 +307,7 @@ static int live_noa_gpr(void *arg)
> > }
> >
> > /* Poison the ce->vm so we detect writes not to the GGTT gt->scratch */
> > - scratch = kmap(ce->vm->scratch[0].base.page);
> > + scratch = kmap_thread(ce->vm->scratch[0].base.page);
> > memset(scratch, POISON_FREE, PAGE_SIZE);
> >
> > rq = intel_context_create_request(ce);
> > @@ -405,7 +405,7 @@ static int live_noa_gpr(void *arg)
> > out_rq:
> > i915_request_put(rq);
> > out_ce:
> > - kunmap(ce->vm->scratch[0].base.page);
> > + kunmap_thread(ce->vm->scratch[0].base.page);
> > intel_context_put(ce);
> > out:
> > stream_destroy(stream);
> > diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c
> > index 004344dce140..0aba0cac51e1 100644
> > --- a/drivers/gpu/drm/radeon/radeon_ttm.c
> > +++ b/drivers/gpu/drm/radeon/radeon_ttm.c
> > @@ -1013,11 +1013,11 @@ static ssize_t radeon_ttm_gtt_read(struct file *f, char __user *buf,
> >
> > page = rdev->gart.pages[p];
> > if (page) {
> > - ptr = kmap(page);
> > + ptr = kmap_thread(page);
> > ptr += off;
> >
> > r = copy_to_user(buf, ptr, cur_size);
> > - kunmap(rdev->gart.pages[p]);
> > + kunmap_thread(rdev->gart.pages[p]);
> > } else
> > r = clear_user(buf, cur_size);
> >
> > --
> > 2.28.0.rc0.12.gb6a658bd00c9
> >
>
> --
> Daniel Vetter
> Software Engineer, Intel Corporation
> http://blog.ffwll.ch
^ permalink raw reply
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox