Merge tag 's390-5.4-3' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux
Pull s390 fixes from Vasily Gorbik:
- defconfig updates
- Fix build errors with CC_OPTIMIZE_FOR_SIZE due to usage of "i"
constraint for function arguments. Two kvm changes acked-by Christian
Borntraeger.
- Fix -Wunused-but-set-variable warnings in mm code.
- Avoid a constant misuse in qdio.
- Handle a case when cpumf is temporarily unavailable.
* tag 's390-5.4-3' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux:
KVM: s390: mark __insn32_query() as __always_inline
KVM: s390: fix __insn32_query() inline assembly
s390: update defconfigs
s390/pci: mark function(s) __always_inline
s390/mm: mark function(s) __always_inline
s390/jump_label: mark function(s) __always_inline
s390/cpu_mf: mark function(s) __always_inline
s390/atomic,bitops: mark function(s) __always_inline
s390/mm: fix -Wunused-but-set-variable warnings
s390: mark __cpacf_query() as __always_inline
s390/qdio: clarify size of the QIB parm area
s390/cpumf: Fix indentation in sampling device driver
s390/cpumsf: Check for CPU Measurement sampling
s390/cpumf: Use consistant debug print format
diff --git a/Documentation/devicetree/bindings/dsp/fsl,dsp.yaml b/Documentation/devicetree/bindings/dsp/fsl,dsp.yaml
index 3248595..f04870d 100644
--- a/Documentation/devicetree/bindings/dsp/fsl,dsp.yaml
+++ b/Documentation/devicetree/bindings/dsp/fsl,dsp.yaml
@@ -85,4 +85,5 @@
<&pd IMX_SC_R_DSP_RAM>;
mbox-names = "txdb0", "txdb1", "rxdb0", "rxdb1";
mboxes = <&lsio_mu13 2 0>, <&lsio_mu13 2 1>, <&lsio_mu13 3 0>, <&lsio_mu13 3 1>;
+ memory-region = <&dsp_reserved>;
};
diff --git a/Documentation/devicetree/bindings/iio/adc/adi,ad7192.yaml b/Documentation/devicetree/bindings/iio/adc/adi,ad7192.yaml
index 676ec42..567a33a 100644
--- a/Documentation/devicetree/bindings/iio/adc/adi,ad7192.yaml
+++ b/Documentation/devicetree/bindings/iio/adc/adi,ad7192.yaml
@@ -43,13 +43,9 @@
dvdd-supply:
description: DVdd voltage supply
- items:
- - const: dvdd
avdd-supply:
description: AVdd voltage supply
- items:
- - const: avdd
adi,rejection-60-Hz-enable:
description: |
@@ -99,6 +95,9 @@
examples:
- |
spi0 {
+ #address-cells = <1>;
+ #size-cells = <0>;
+
adc@0 {
compatible = "adi,ad7192";
reg = <0>;
diff --git a/Documentation/devicetree/bindings/media/rc.yaml b/Documentation/devicetree/bindings/media/rc.yaml
index 3d5c154..9054555 100644
--- a/Documentation/devicetree/bindings/media/rc.yaml
+++ b/Documentation/devicetree/bindings/media/rc.yaml
@@ -73,7 +73,6 @@
- rc-genius-tvgo-a11mce
- rc-gotview7135
- rc-hauppauge
- - rc-hauppauge
- rc-hisi-poplar
- rc-hisi-tv-demo
- rc-imon-mce
diff --git a/Documentation/devicetree/bindings/phy/lantiq,vrx200-pcie-phy.yaml b/Documentation/devicetree/bindings/phy/lantiq,vrx200-pcie-phy.yaml
index 8a56a85..a974821 100644
--- a/Documentation/devicetree/bindings/phy/lantiq,vrx200-pcie-phy.yaml
+++ b/Documentation/devicetree/bindings/phy/lantiq,vrx200-pcie-phy.yaml
@@ -37,7 +37,7 @@
- description: exclusive PHY reset line
- description: shared reset line between the PCIe PHY and PCIe controller
- resets-names:
+ reset-names:
items:
- const: phy
- const: pcie
diff --git a/MAINTAINERS b/MAINTAINERS
index 296de2b..55199ef 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -6112,7 +6112,10 @@
M: Chao Yu <yuchao0@huawei.com>
L: linux-erofs@lists.ozlabs.org
S: Maintained
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/xiang/erofs.git
+F: Documentation/filesystems/erofs.txt
F: fs/erofs/
+F: include/trace/events/erofs.h
ERRSEQ ERROR TRACKING INFRASTRUCTURE
M: Jeff Layton <jlayton@kernel.org>
@@ -9075,6 +9078,7 @@
KGDB / KDB /debug_core
M: Jason Wessel <jason.wessel@windriver.com>
M: Daniel Thompson <daniel.thompson@linaro.org>
+R: Douglas Anderson <dianders@chromium.org>
W: http://kgdb.wiki.kernel.org/
L: kgdb-bugreport@lists.sourceforge.net
T: git git://git.kernel.org/pub/scm/linux/kernel/git/jwessel/kgdb.git
diff --git a/arch/arm/include/asm/xen/xen-ops.h b/arch/arm/include/asm/xen/xen-ops.h
deleted file mode 100644
index ec154e7..0000000
--- a/arch/arm/include/asm/xen/xen-ops.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef _ASM_XEN_OPS_H
-#define _ASM_XEN_OPS_H
-
-void xen_efi_runtime_setup(void);
-
-#endif /* _ASM_XEN_OPS_H */
diff --git a/arch/arm/xen/Makefile b/arch/arm/xen/Makefile
index 7ed2898..c32d047 100644
--- a/arch/arm/xen/Makefile
+++ b/arch/arm/xen/Makefile
@@ -1,3 +1,2 @@
# SPDX-License-Identifier: GPL-2.0-only
obj-y := enlighten.o hypercall.o grant-table.o p2m.o mm.o
-obj-$(CONFIG_XEN_EFI) += efi.o
diff --git a/arch/arm/xen/efi.c b/arch/arm/xen/efi.c
deleted file mode 100644
index d687a73..0000000
--- a/arch/arm/xen/efi.c
+++ /dev/null
@@ -1,28 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * Copyright (c) 2015, Linaro Limited, Shannon Zhao
- */
-
-#include <linux/efi.h>
-#include <xen/xen-ops.h>
-#include <asm/xen/xen-ops.h>
-
-/* Set XEN EFI runtime services function pointers. Other fields of struct efi,
- * e.g. efi.systab, will be set like normal EFI.
- */
-void __init xen_efi_runtime_setup(void)
-{
- efi.get_time = xen_efi_get_time;
- efi.set_time = xen_efi_set_time;
- efi.get_wakeup_time = xen_efi_get_wakeup_time;
- efi.set_wakeup_time = xen_efi_set_wakeup_time;
- efi.get_variable = xen_efi_get_variable;
- efi.get_next_variable = xen_efi_get_next_variable;
- efi.set_variable = xen_efi_set_variable;
- efi.query_variable_info = xen_efi_query_variable_info;
- efi.update_capsule = xen_efi_update_capsule;
- efi.query_capsule_caps = xen_efi_query_capsule_caps;
- efi.get_next_high_mono_count = xen_efi_get_next_high_mono_count;
- efi.reset_system = xen_efi_reset_system;
-}
-EXPORT_SYMBOL_GPL(xen_efi_runtime_setup);
diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c
index 1e57692..dd6804a 100644
--- a/arch/arm/xen/enlighten.c
+++ b/arch/arm/xen/enlighten.c
@@ -15,7 +15,6 @@
#include <xen/xen-ops.h>
#include <asm/xen/hypervisor.h>
#include <asm/xen/hypercall.h>
-#include <asm/xen/xen-ops.h>
#include <asm/system_misc.h>
#include <asm/efi.h>
#include <linux/interrupt.h>
@@ -437,7 +436,7 @@ EXPORT_SYMBOL_GPL(HYPERVISOR_memory_op);
EXPORT_SYMBOL_GPL(HYPERVISOR_physdev_op);
EXPORT_SYMBOL_GPL(HYPERVISOR_vcpu_op);
EXPORT_SYMBOL_GPL(HYPERVISOR_tmem_op);
-EXPORT_SYMBOL_GPL(HYPERVISOR_platform_op);
+EXPORT_SYMBOL_GPL(HYPERVISOR_platform_op_raw);
EXPORT_SYMBOL_GPL(HYPERVISOR_multicall);
EXPORT_SYMBOL_GPL(HYPERVISOR_vm_assist);
EXPORT_SYMBOL_GPL(HYPERVISOR_dm_op);
diff --git a/arch/arm/xen/mm.c b/arch/arm/xen/mm.c
index 2b2c208..38fa917 100644
--- a/arch/arm/xen/mm.c
+++ b/arch/arm/xen/mm.c
@@ -28,7 +28,10 @@ unsigned long xen_get_swiotlb_free_pages(unsigned int order)
for_each_memblock(memory, reg) {
if (reg->base < (phys_addr_t)0xffffffff) {
- flags |= __GFP_DMA;
+ if (IS_ENABLED(CONFIG_ZONE_DMA32))
+ flags |= __GFP_DMA32;
+ else
+ flags |= __GFP_DMA;
break;
}
}
diff --git a/arch/arm64/include/asm/kvm_hyp.h b/arch/arm64/include/asm/kvm_hyp.h
index 86825aa..97f21cc 100644
--- a/arch/arm64/include/asm/kvm_hyp.h
+++ b/arch/arm64/include/asm/kvm_hyp.h
@@ -47,30 +47,6 @@
#define read_sysreg_el2(r) read_sysreg_elx(r, _EL2, _EL1)
#define write_sysreg_el2(v,r) write_sysreg_elx(v, r, _EL2, _EL1)
-/**
- * hyp_alternate_select - Generates patchable code sequences that are
- * used to switch between two implementations of a function, depending
- * on the availability of a feature.
- *
- * @fname: a symbol name that will be defined as a function returning a
- * function pointer whose type will match @orig and @alt
- * @orig: A pointer to the default function, as returned by @fname when
- * @cond doesn't hold
- * @alt: A pointer to the alternate function, as returned by @fname
- * when @cond holds
- * @cond: a CPU feature (as described in asm/cpufeature.h)
- */
-#define hyp_alternate_select(fname, orig, alt, cond) \
-typeof(orig) * __hyp_text fname(void) \
-{ \
- typeof(alt) *val = orig; \
- asm volatile(ALTERNATIVE("nop \n", \
- "mov %0, %1 \n", \
- cond) \
- : "+r" (val) : "r" (alt)); \
- return val; \
-}
-
int __vgic_v2_perform_cpuif_access(struct kvm_vcpu *vcpu);
void __vgic_v3_save_state(struct kvm_vcpu *vcpu);
diff --git a/arch/arm64/include/asm/xen/xen-ops.h b/arch/arm64/include/asm/xen/xen-ops.h
deleted file mode 100644
index e6e7840..0000000
--- a/arch/arm64/include/asm/xen/xen-ops.h
+++ /dev/null
@@ -1,7 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_XEN_OPS_H
-#define _ASM_XEN_OPS_H
-
-void xen_efi_runtime_setup(void);
-
-#endif /* _ASM_XEN_OPS_H */
diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c
index bd978ad..3d38150 100644
--- a/arch/arm64/kvm/hyp/switch.c
+++ b/arch/arm64/kvm/hyp/switch.c
@@ -229,20 +229,6 @@ static void __hyp_text __hyp_vgic_restore_state(struct kvm_vcpu *vcpu)
}
}
-static bool __hyp_text __true_value(void)
-{
- return true;
-}
-
-static bool __hyp_text __false_value(void)
-{
- return false;
-}
-
-static hyp_alternate_select(__check_arm_834220,
- __false_value, __true_value,
- ARM64_WORKAROUND_834220);
-
static bool __hyp_text __translate_far_to_hpfar(u64 far, u64 *hpfar)
{
u64 par, tmp;
@@ -298,7 +284,8 @@ static bool __hyp_text __populate_fault_info(struct kvm_vcpu *vcpu)
* resolve the IPA using the AT instruction.
*/
if (!(esr & ESR_ELx_S1PTW) &&
- (__check_arm_834220()() || (esr & ESR_ELx_FSC_TYPE) == FSC_PERM)) {
+ (cpus_have_const_cap(ARM64_WORKAROUND_834220) ||
+ (esr & ESR_ELx_FSC_TYPE) == FSC_PERM)) {
if (!__translate_far_to_hpfar(far, &hpfar))
return false;
} else {
diff --git a/arch/arm64/kvm/hyp/tlb.c b/arch/arm64/kvm/hyp/tlb.c
index c466060..eb0efc5 100644
--- a/arch/arm64/kvm/hyp/tlb.c
+++ b/arch/arm64/kvm/hyp/tlb.c
@@ -67,10 +67,14 @@ static void __hyp_text __tlb_switch_to_guest_nvhe(struct kvm *kvm,
isb();
}
-static hyp_alternate_select(__tlb_switch_to_guest,
- __tlb_switch_to_guest_nvhe,
- __tlb_switch_to_guest_vhe,
- ARM64_HAS_VIRT_HOST_EXTN);
+static void __hyp_text __tlb_switch_to_guest(struct kvm *kvm,
+ struct tlb_inv_context *cxt)
+{
+ if (has_vhe())
+ __tlb_switch_to_guest_vhe(kvm, cxt);
+ else
+ __tlb_switch_to_guest_nvhe(kvm, cxt);
+}
static void __hyp_text __tlb_switch_to_host_vhe(struct kvm *kvm,
struct tlb_inv_context *cxt)
@@ -98,10 +102,14 @@ static void __hyp_text __tlb_switch_to_host_nvhe(struct kvm *kvm,
write_sysreg(0, vttbr_el2);
}
-static hyp_alternate_select(__tlb_switch_to_host,
- __tlb_switch_to_host_nvhe,
- __tlb_switch_to_host_vhe,
- ARM64_HAS_VIRT_HOST_EXTN);
+static void __hyp_text __tlb_switch_to_host(struct kvm *kvm,
+ struct tlb_inv_context *cxt)
+{
+ if (has_vhe())
+ __tlb_switch_to_host_vhe(kvm, cxt);
+ else
+ __tlb_switch_to_host_nvhe(kvm, cxt);
+}
void __hyp_text __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa)
{
@@ -111,7 +119,7 @@ void __hyp_text __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa)
/* Switch to requested VMID */
kvm = kern_hyp_va(kvm);
- __tlb_switch_to_guest()(kvm, &cxt);
+ __tlb_switch_to_guest(kvm, &cxt);
/*
* We could do so much better if we had the VA as well.
@@ -154,7 +162,7 @@ void __hyp_text __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa)
if (!has_vhe() && icache_is_vpipt())
__flush_icache_all();
- __tlb_switch_to_host()(kvm, &cxt);
+ __tlb_switch_to_host(kvm, &cxt);
}
void __hyp_text __kvm_tlb_flush_vmid(struct kvm *kvm)
@@ -165,13 +173,13 @@ void __hyp_text __kvm_tlb_flush_vmid(struct kvm *kvm)
/* Switch to requested VMID */
kvm = kern_hyp_va(kvm);
- __tlb_switch_to_guest()(kvm, &cxt);
+ __tlb_switch_to_guest(kvm, &cxt);
__tlbi(vmalls12e1is);
dsb(ish);
isb();
- __tlb_switch_to_host()(kvm, &cxt);
+ __tlb_switch_to_host(kvm, &cxt);
}
void __hyp_text __kvm_tlb_flush_local_vmid(struct kvm_vcpu *vcpu)
@@ -180,13 +188,13 @@ void __hyp_text __kvm_tlb_flush_local_vmid(struct kvm_vcpu *vcpu)
struct tlb_inv_context cxt;
/* Switch to requested VMID */
- __tlb_switch_to_guest()(kvm, &cxt);
+ __tlb_switch_to_guest(kvm, &cxt);
__tlbi(vmalle1);
dsb(nsh);
isb();
- __tlb_switch_to_host()(kvm, &cxt);
+ __tlb_switch_to_host(kvm, &cxt);
}
void __hyp_text __kvm_flush_vm_context(void)
diff --git a/arch/arm64/xen/Makefile b/arch/arm64/xen/Makefile
index a4fc65f..b66215e 100644
--- a/arch/arm64/xen/Makefile
+++ b/arch/arm64/xen/Makefile
@@ -1,4 +1,3 @@
# SPDX-License-Identifier: GPL-2.0-only
xen-arm-y += $(addprefix ../../arm/xen/, enlighten.o grant-table.o p2m.o mm.o)
obj-y := xen-arm.o hypercall.o
-obj-$(CONFIG_XEN_EFI) += $(addprefix ../../arm/xen/, efi.o)
diff --git a/arch/mips/boot/dts/qca/ar9331.dtsi b/arch/mips/boot/dts/qca/ar9331.dtsi
index 63a9f33..5cfc9d3 100644
--- a/arch/mips/boot/dts/qca/ar9331.dtsi
+++ b/arch/mips/boot/dts/qca/ar9331.dtsi
@@ -99,7 +99,7 @@
miscintc: interrupt-controller@18060010 {
compatible = "qca,ar7240-misc-intc";
- reg = <0x18060010 0x4>;
+ reg = <0x18060010 0x8>;
interrupt-parent = <&cpuintc>;
interrupts = <6>;
diff --git a/arch/mips/fw/arc/memory.c b/arch/mips/fw/arc/memory.c
index af44b35..b4328b3 100644
--- a/arch/mips/fw/arc/memory.c
+++ b/arch/mips/fw/arc/memory.c
@@ -160,7 +160,6 @@ void __init prom_meminit(void)
void __init prom_free_prom_memory(void)
{
- unsigned long addr;
int i;
if (prom_flags & PROM_FLAG_DONT_FREE_TEMP)
diff --git a/arch/mips/include/asm/octeon/cvmx-ipd.h b/arch/mips/include/asm/octeon/cvmx-ipd.h
index cbdc14b..adab7b5 100644
--- a/arch/mips/include/asm/octeon/cvmx-ipd.h
+++ b/arch/mips/include/asm/octeon/cvmx-ipd.h
@@ -36,6 +36,7 @@
#include <asm/octeon/octeon-feature.h>
#include <asm/octeon/cvmx-ipd-defs.h>
+#include <asm/octeon/cvmx-pip-defs.h>
enum cvmx_ipd_mode {
CVMX_IPD_OPC_MODE_STT = 0LL, /* All blocks DRAM, not cached in L2 */
diff --git a/arch/mips/include/asm/unistd.h b/arch/mips/include/asm/unistd.h
index 071053e..5d70bab 100644
--- a/arch/mips/include/asm/unistd.h
+++ b/arch/mips/include/asm/unistd.h
@@ -52,6 +52,7 @@
# endif
#define __ARCH_WANT_SYS_FORK
#define __ARCH_WANT_SYS_CLONE
+#define __ARCH_WANT_SYS_CLONE3
/* whitelists for checksyscalls */
#define __IGNORE_fadvise64_64
diff --git a/arch/mips/kernel/cpu-bugs64.c b/arch/mips/kernel/cpu-bugs64.c
index fa62cd1..6a7afe7 100644
--- a/arch/mips/kernel/cpu-bugs64.c
+++ b/arch/mips/kernel/cpu-bugs64.c
@@ -24,7 +24,8 @@ static char r4kwar[] __initdata =
static char daddiwar[] __initdata =
"Enable CPU_DADDI_WORKAROUNDS to rectify.";
-static inline void align_mod(const int align, const int mod)
+static __always_inline __init
+void align_mod(const int align, const int mod)
{
asm volatile(
".set push\n\t"
@@ -38,8 +39,9 @@ static inline void align_mod(const int align, const int mod)
: "n"(align), "n"(mod));
}
-static __always_inline void mult_sh_align_mod(long *v1, long *v2, long *w,
- const int align, const int mod)
+static __always_inline __init
+void mult_sh_align_mod(long *v1, long *v2, long *w,
+ const int align, const int mod)
{
unsigned long flags;
int m1, m2;
@@ -113,7 +115,7 @@ static __always_inline void mult_sh_align_mod(long *v1, long *v2, long *w,
*w = lw;
}
-static inline void check_mult_sh(void)
+static __always_inline __init void check_mult_sh(void)
{
long v1[8], v2[8], w[8];
int bug, fix, i;
@@ -176,7 +178,7 @@ asmlinkage void __init do_daddi_ov(struct pt_regs *regs)
exception_exit(prev_state);
}
-static inline void check_daddi(void)
+static __init void check_daddi(void)
{
extern asmlinkage void handle_daddi_ov(void);
unsigned long flags;
@@ -242,7 +244,7 @@ static inline void check_daddi(void)
int daddiu_bug = IS_ENABLED(CONFIG_CPU_MIPSR6) ? 0 : -1;
-static inline void check_daddiu(void)
+static __init void check_daddiu(void)
{
long v, w, tmp;
diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c
index b8249c2..5eec13b 100644
--- a/arch/mips/kernel/setup.c
+++ b/arch/mips/kernel/setup.c
@@ -108,6 +108,9 @@ void __init add_memory_region(phys_addr_t start, phys_addr_t size, long type)
return;
}
+ if (start < PHYS_OFFSET)
+ return;
+
memblock_add(start, size);
/* Reserve any memory except the ordinary RAM ranges. */
switch (type) {
@@ -321,7 +324,7 @@ static void __init bootmem_init(void)
* Reserve any memory between the start of RAM and PHYS_OFFSET
*/
if (ramstart > PHYS_OFFSET)
- memblock_reserve(PHYS_OFFSET, PFN_UP(ramstart) - PHYS_OFFSET);
+ memblock_reserve(PHYS_OFFSET, ramstart - PHYS_OFFSET);
if (PFN_UP(ramstart) > ARCH_PFN_OFFSET) {
pr_info("Wasting %lu bytes for tracking %lu unused pages\n",
diff --git a/arch/mips/kernel/syscall.c b/arch/mips/kernel/syscall.c
index b0e25e9..3f16f38 100644
--- a/arch/mips/kernel/syscall.c
+++ b/arch/mips/kernel/syscall.c
@@ -80,6 +80,7 @@ SYSCALL_DEFINE6(mips_mmap2, unsigned long, addr, unsigned long, len,
save_static_function(sys_fork);
save_static_function(sys_clone);
+save_static_function(sys_clone3);
SYSCALL_DEFINE1(set_thread_area, unsigned long, addr)
{
diff --git a/arch/mips/kernel/syscalls/syscall_n32.tbl b/arch/mips/kernel/syscalls/syscall_n32.tbl
index c9c879e..e7c5ab3 100644
--- a/arch/mips/kernel/syscalls/syscall_n32.tbl
+++ b/arch/mips/kernel/syscalls/syscall_n32.tbl
@@ -373,4 +373,4 @@
432 n32 fsmount sys_fsmount
433 n32 fspick sys_fspick
434 n32 pidfd_open sys_pidfd_open
-# 435 reserved for clone3
+435 n32 clone3 __sys_clone3
diff --git a/arch/mips/kernel/syscalls/syscall_n64.tbl b/arch/mips/kernel/syscalls/syscall_n64.tbl
index bbce915..13cd665 100644
--- a/arch/mips/kernel/syscalls/syscall_n64.tbl
+++ b/arch/mips/kernel/syscalls/syscall_n64.tbl
@@ -349,4 +349,4 @@
432 n64 fsmount sys_fsmount
433 n64 fspick sys_fspick
434 n64 pidfd_open sys_pidfd_open
-# 435 reserved for clone3
+435 n64 clone3 __sys_clone3
diff --git a/arch/mips/kernel/syscalls/syscall_o32.tbl b/arch/mips/kernel/syscalls/syscall_o32.tbl
index 9653591..353539e 100644
--- a/arch/mips/kernel/syscalls/syscall_o32.tbl
+++ b/arch/mips/kernel/syscalls/syscall_o32.tbl
@@ -422,4 +422,4 @@
432 o32 fsmount sys_fsmount
433 o32 fspick sys_fspick
434 o32 pidfd_open sys_pidfd_open
-# 435 reserved for clone3
+435 o32 clone3 __sys_clone3
diff --git a/arch/mips/loongson64/common/mem.c b/arch/mips/loongson64/common/mem.c
index 4abb92e..4254ac4 100644
--- a/arch/mips/loongson64/common/mem.c
+++ b/arch/mips/loongson64/common/mem.c
@@ -3,6 +3,7 @@
*/
#include <linux/fs.h>
#include <linux/fcntl.h>
+#include <linux/memblock.h>
#include <linux/mm.h>
#include <asm/bootinfo.h>
@@ -64,24 +65,22 @@ void __init prom_init_memory(void)
node_id = loongson_memmap->map[i].node_id;
mem_type = loongson_memmap->map[i].mem_type;
- if (node_id == 0) {
- switch (mem_type) {
- case SYSTEM_RAM_LOW:
- add_memory_region(loongson_memmap->map[i].mem_start,
- (u64)loongson_memmap->map[i].mem_size << 20,
- BOOT_MEM_RAM);
- break;
- case SYSTEM_RAM_HIGH:
- add_memory_region(loongson_memmap->map[i].mem_start,
- (u64)loongson_memmap->map[i].mem_size << 20,
- BOOT_MEM_RAM);
- break;
- case SYSTEM_RAM_RESERVED:
- add_memory_region(loongson_memmap->map[i].mem_start,
- (u64)loongson_memmap->map[i].mem_size << 20,
- BOOT_MEM_RESERVED);
- break;
- }
+ if (node_id != 0)
+ continue;
+
+ switch (mem_type) {
+ case SYSTEM_RAM_LOW:
+ memblock_add(loongson_memmap->map[i].mem_start,
+ (u64)loongson_memmap->map[i].mem_size << 20);
+ break;
+ case SYSTEM_RAM_HIGH:
+ memblock_add(loongson_memmap->map[i].mem_start,
+ (u64)loongson_memmap->map[i].mem_size << 20);
+ break;
+ case SYSTEM_RAM_RESERVED:
+ memblock_reserve(loongson_memmap->map[i].mem_start,
+ (u64)loongson_memmap->map[i].mem_size << 20);
+ break;
}
}
}
diff --git a/arch/mips/loongson64/common/serial.c b/arch/mips/loongson64/common/serial.c
index ffefc1c..98c3a7f 100644
--- a/arch/mips/loongson64/common/serial.c
+++ b/arch/mips/loongson64/common/serial.c
@@ -110,7 +110,7 @@ static int __init serial_init(void)
}
module_init(serial_init);
-static void __init serial_exit(void)
+static void __exit serial_exit(void)
{
platform_device_unregister(&uart8250_device);
}
diff --git a/arch/mips/loongson64/loongson-3/numa.c b/arch/mips/loongson64/loongson-3/numa.c
index 414e97d..8f20d2c 100644
--- a/arch/mips/loongson64/loongson-3/numa.c
+++ b/arch/mips/loongson64/loongson-3/numa.c
@@ -142,8 +142,6 @@ static void __init szmem(unsigned int node)
(u32)node_id, mem_type, mem_start, mem_size);
pr_info(" start_pfn:0x%llx, end_pfn:0x%llx, num_physpages:0x%lx\n",
start_pfn, end_pfn, num_physpages);
- add_memory_region((node_id << 44) + mem_start,
- (u64)mem_size << 20, BOOT_MEM_RAM);
memblock_add_node(PFN_PHYS(start_pfn),
PFN_PHYS(end_pfn - start_pfn), node);
break;
@@ -156,16 +154,12 @@ static void __init szmem(unsigned int node)
(u32)node_id, mem_type, mem_start, mem_size);
pr_info(" start_pfn:0x%llx, end_pfn:0x%llx, num_physpages:0x%lx\n",
start_pfn, end_pfn, num_physpages);
- add_memory_region((node_id << 44) + mem_start,
- (u64)mem_size << 20, BOOT_MEM_RAM);
memblock_add_node(PFN_PHYS(start_pfn),
PFN_PHYS(end_pfn - start_pfn), node);
break;
case SYSTEM_RAM_RESERVED:
pr_info("Node%d: mem_type:%d, mem_start:0x%llx, mem_size:0x%llx MB\n",
(u32)node_id, mem_type, mem_start, mem_size);
- add_memory_region((node_id << 44) + mem_start,
- (u64)mem_size << 20, BOOT_MEM_RESERVED);
memblock_reserve(((node_id << 44) + mem_start),
mem_size << 20);
break;
@@ -191,8 +185,6 @@ static void __init node_mem_init(unsigned int node)
NODE_DATA(node)->node_start_pfn = start_pfn;
NODE_DATA(node)->node_spanned_pages = end_pfn - start_pfn;
- free_bootmem_with_active_regions(node, end_pfn);
-
if (node == 0) {
/* kernel end address */
unsigned long kernel_end_pfn = PFN_UP(__pa_symbol(&_end));
@@ -209,8 +201,6 @@ static void __init node_mem_init(unsigned int node)
memblock_reserve((node_addrspace_offset | 0xfe000000),
32 << 20);
}
-
- sparse_memory_present_with_active_regions(node);
}
static __init void prom_meminit(void)
@@ -227,6 +217,7 @@ static __init void prom_meminit(void)
cpumask_clear(&__node_data[(node)]->cpumask);
}
}
+ memblocks_present();
max_low_pfn = PHYS_PFN(memblock_end_of_DRAM());
for (cpu = 0; cpu < loongson_sysconf.nr_cpus; cpu++) {
diff --git a/arch/mips/pmcs-msp71xx/msp_prom.c b/arch/mips/pmcs-msp71xx/msp_prom.c
index dfb5279..800a21b 100644
--- a/arch/mips/pmcs-msp71xx/msp_prom.c
+++ b/arch/mips/pmcs-msp71xx/msp_prom.c
@@ -61,6 +61,7 @@ int init_debug = 1;
/* memory blocks */
struct prom_pmemblock mdesc[PROM_MAX_PMEMBLOCKS];
+#define MAX_PROM_MEM 5
static phys_addr_t prom_mem_base[MAX_PROM_MEM] __initdata;
static phys_addr_t prom_mem_size[MAX_PROM_MEM] __initdata;
static unsigned int nr_prom_mem __initdata;
@@ -358,7 +359,7 @@ void __init prom_meminit(void)
p++;
if (type == BOOT_MEM_ROM_DATA) {
- if (nr_prom_mem >= 5) {
+ if (nr_prom_mem >= MAX_PROM_MEM) {
pr_err("Too many ROM DATA regions");
continue;
}
@@ -377,7 +378,6 @@ void __init prom_free_prom_memory(void)
char *ptr;
int len = 0;
int i;
- unsigned long addr;
/*
* preserve environment variables and command line from pmon/bbload
diff --git a/arch/mips/vdso/Makefile b/arch/mips/vdso/Makefile
index 69cfa0a..807f0f7 100644
--- a/arch/mips/vdso/Makefile
+++ b/arch/mips/vdso/Makefile
@@ -59,7 +59,7 @@
ifndef CONFIG_CPU_MIPSR6
ifeq ($(call ld-ifversion, -lt, 225000000, y),y)
$(warning MIPS VDSO requires binutils >= 2.25)
- obj-vdso-y := $(filter-out gettimeofday.o, $(obj-vdso-y))
+ obj-vdso-y := $(filter-out vgettimeofday.o, $(obj-vdso-y))
ccflags-vdso += -DDISABLE_MIPS_VDSO
endif
endif
diff --git a/arch/mips/vdso/gettimeofday.c b/arch/mips/vdso/gettimeofday.c
deleted file mode 100644
index e8243c7..0000000
--- a/arch/mips/vdso/gettimeofday.c
+++ /dev/null
@@ -1,269 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * Copyright (C) 2015 Imagination Technologies
- * Author: Alex Smith <alex.smith@imgtec.com>
- */
-
-#include "vdso.h"
-
-#include <linux/compiler.h>
-#include <linux/time.h>
-
-#include <asm/clocksource.h>
-#include <asm/io.h>
-#include <asm/unistd.h>
-#include <asm/vdso.h>
-
-#ifdef CONFIG_MIPS_CLOCK_VSYSCALL
-
-static __always_inline long gettimeofday_fallback(struct timeval *_tv,
- struct timezone *_tz)
-{
- register struct timezone *tz asm("a1") = _tz;
- register struct timeval *tv asm("a0") = _tv;
- register long ret asm("v0");
- register long nr asm("v0") = __NR_gettimeofday;
- register long error asm("a3");
-
- asm volatile(
- " syscall\n"
- : "=r" (ret), "=r" (error)
- : "r" (tv), "r" (tz), "r" (nr)
- : "$1", "$3", "$8", "$9", "$10", "$11", "$12", "$13",
- "$14", "$15", "$24", "$25", "hi", "lo", "memory");
-
- return error ? -ret : ret;
-}
-
-#endif
-
-static __always_inline long clock_gettime_fallback(clockid_t _clkid,
- struct timespec *_ts)
-{
- register struct timespec *ts asm("a1") = _ts;
- register clockid_t clkid asm("a0") = _clkid;
- register long ret asm("v0");
- register long nr asm("v0") = __NR_clock_gettime;
- register long error asm("a3");
-
- asm volatile(
- " syscall\n"
- : "=r" (ret), "=r" (error)
- : "r" (clkid), "r" (ts), "r" (nr)
- : "$1", "$3", "$8", "$9", "$10", "$11", "$12", "$13",
- "$14", "$15", "$24", "$25", "hi", "lo", "memory");
-
- return error ? -ret : ret;
-}
-
-static __always_inline int do_realtime_coarse(struct timespec *ts,
- const union mips_vdso_data *data)
-{
- u32 start_seq;
-
- do {
- start_seq = vdso_data_read_begin(data);
-
- ts->tv_sec = data->xtime_sec;
- ts->tv_nsec = data->xtime_nsec >> data->cs_shift;
- } while (vdso_data_read_retry(data, start_seq));
-
- return 0;
-}
-
-static __always_inline int do_monotonic_coarse(struct timespec *ts,
- const union mips_vdso_data *data)
-{
- u32 start_seq;
- u64 to_mono_sec;
- u64 to_mono_nsec;
-
- do {
- start_seq = vdso_data_read_begin(data);
-
- ts->tv_sec = data->xtime_sec;
- ts->tv_nsec = data->xtime_nsec >> data->cs_shift;
-
- to_mono_sec = data->wall_to_mono_sec;
- to_mono_nsec = data->wall_to_mono_nsec;
- } while (vdso_data_read_retry(data, start_seq));
-
- ts->tv_sec += to_mono_sec;
- timespec_add_ns(ts, to_mono_nsec);
-
- return 0;
-}
-
-#ifdef CONFIG_CSRC_R4K
-
-static __always_inline u64 read_r4k_count(void)
-{
- unsigned int count;
-
- __asm__ __volatile__(
- " .set push\n"
- " .set mips32r2\n"
- " rdhwr %0, $2\n"
- " .set pop\n"
- : "=r" (count));
-
- return count;
-}
-
-#endif
-
-#ifdef CONFIG_CLKSRC_MIPS_GIC
-
-static __always_inline u64 read_gic_count(const union mips_vdso_data *data)
-{
- void __iomem *gic = get_gic(data);
- u32 hi, hi2, lo;
-
- do {
- hi = __raw_readl(gic + sizeof(lo));
- lo = __raw_readl(gic);
- hi2 = __raw_readl(gic + sizeof(lo));
- } while (hi2 != hi);
-
- return (((u64)hi) << 32) + lo;
-}
-
-#endif
-
-static __always_inline u64 get_ns(const union mips_vdso_data *data)
-{
- u64 cycle_now, delta, nsec;
-
- switch (data->clock_mode) {
-#ifdef CONFIG_CSRC_R4K
- case VDSO_CLOCK_R4K:
- cycle_now = read_r4k_count();
- break;
-#endif
-#ifdef CONFIG_CLKSRC_MIPS_GIC
- case VDSO_CLOCK_GIC:
- cycle_now = read_gic_count(data);
- break;
-#endif
- default:
- return 0;
- }
-
- delta = (cycle_now - data->cs_cycle_last) & data->cs_mask;
-
- nsec = (delta * data->cs_mult) + data->xtime_nsec;
- nsec >>= data->cs_shift;
-
- return nsec;
-}
-
-static __always_inline int do_realtime(struct timespec *ts,
- const union mips_vdso_data *data)
-{
- u32 start_seq;
- u64 ns;
-
- do {
- start_seq = vdso_data_read_begin(data);
-
- if (data->clock_mode == VDSO_CLOCK_NONE)
- return -ENOSYS;
-
- ts->tv_sec = data->xtime_sec;
- ns = get_ns(data);
- } while (vdso_data_read_retry(data, start_seq));
-
- ts->tv_nsec = 0;
- timespec_add_ns(ts, ns);
-
- return 0;
-}
-
-static __always_inline int do_monotonic(struct timespec *ts,
- const union mips_vdso_data *data)
-{
- u32 start_seq;
- u64 ns;
- u64 to_mono_sec;
- u64 to_mono_nsec;
-
- do {
- start_seq = vdso_data_read_begin(data);
-
- if (data->clock_mode == VDSO_CLOCK_NONE)
- return -ENOSYS;
-
- ts->tv_sec = data->xtime_sec;
- ns = get_ns(data);
-
- to_mono_sec = data->wall_to_mono_sec;
- to_mono_nsec = data->wall_to_mono_nsec;
- } while (vdso_data_read_retry(data, start_seq));
-
- ts->tv_sec += to_mono_sec;
- ts->tv_nsec = 0;
- timespec_add_ns(ts, ns + to_mono_nsec);
-
- return 0;
-}
-
-#ifdef CONFIG_MIPS_CLOCK_VSYSCALL
-
-/*
- * This is behind the ifdef so that we don't provide the symbol when there's no
- * possibility of there being a usable clocksource, because there's nothing we
- * can do without it. When libc fails the symbol lookup it should fall back on
- * the standard syscall path.
- */
-int __vdso_gettimeofday(struct timeval *tv, struct timezone *tz)
-{
- const union mips_vdso_data *data = get_vdso_data();
- struct timespec ts;
- int ret;
-
- ret = do_realtime(&ts, data);
- if (ret)
- return gettimeofday_fallback(tv, tz);
-
- if (tv) {
- tv->tv_sec = ts.tv_sec;
- tv->tv_usec = ts.tv_nsec / 1000;
- }
-
- if (tz) {
- tz->tz_minuteswest = data->tz_minuteswest;
- tz->tz_dsttime = data->tz_dsttime;
- }
-
- return 0;
-}
-
-#endif /* CONFIG_MIPS_CLOCK_VSYSCALL */
-
-int __vdso_clock_gettime(clockid_t clkid, struct timespec *ts)
-{
- const union mips_vdso_data *data = get_vdso_data();
- int ret = -1;
-
- switch (clkid) {
- case CLOCK_REALTIME_COARSE:
- ret = do_realtime_coarse(ts, data);
- break;
- case CLOCK_MONOTONIC_COARSE:
- ret = do_monotonic_coarse(ts, data);
- break;
- case CLOCK_REALTIME:
- ret = do_realtime(ts, data);
- break;
- case CLOCK_MONOTONIC:
- ret = do_monotonic(ts, data);
- break;
- default:
- break;
- }
-
- if (ret)
- ret = clock_gettime_fallback(clkid, ts);
-
- return ret;
-}
diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index d7fcdfa..ec2547c 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -36,8 +36,8 @@
#include "book3s.h"
#include "trace.h"
-#define VM_STAT(x) offsetof(struct kvm, stat.x), KVM_STAT_VM
-#define VCPU_STAT(x) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU
+#define VM_STAT(x, ...) offsetof(struct kvm, stat.x), KVM_STAT_VM, ## __VA_ARGS__
+#define VCPU_STAT(x, ...) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU, ## __VA_ARGS__
/* #define EXIT_DEBUG */
@@ -69,8 +69,8 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
{ "pthru_all", VCPU_STAT(pthru_all) },
{ "pthru_host", VCPU_STAT(pthru_host) },
{ "pthru_bad_aff", VCPU_STAT(pthru_bad_aff) },
- { "largepages_2M", VM_STAT(num_2M_pages) },
- { "largepages_1G", VM_STAT(num_1G_pages) },
+ { "largepages_2M", VM_STAT(num_2M_pages, .mode = 0444) },
+ { "largepages_1G", VM_STAT(num_1G_pages, .mode = 0444) },
{ NULL }
};
diff --git a/arch/riscv/include/asm/asm.h b/arch/riscv/include/asm/asm.h
index 5a02b7d..9c992a8 100644
--- a/arch/riscv/include/asm/asm.h
+++ b/arch/riscv/include/asm/asm.h
@@ -22,6 +22,7 @@
#define REG_L __REG_SEL(ld, lw)
#define REG_S __REG_SEL(sd, sw)
+#define REG_SC __REG_SEL(sc.d, sc.w)
#define SZREG __REG_SEL(8, 4)
#define LGREG __REG_SEL(3, 2)
diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S
index da7aa88..2d592da 100644
--- a/arch/riscv/kernel/entry.S
+++ b/arch/riscv/kernel/entry.S
@@ -98,7 +98,26 @@
*/
.macro RESTORE_ALL
REG_L a0, PT_SSTATUS(sp)
- REG_L a2, PT_SEPC(sp)
+ /*
+ * The current load reservation is effectively part of the processor's
+ * state, in the sense that load reservations cannot be shared between
+ * different hart contexts. We can't actually save and restore a load
+ * reservation, so instead here we clear any existing reservation --
+ * it's always legal for implementations to clear load reservations at
+ * any point (as long as the forward progress guarantee is kept, but
+ * we'll ignore that here).
+ *
+ * Dangling load reservations can be the result of taking a trap in the
+ * middle of an LR/SC sequence, but can also be the result of a taken
+ * forward branch around an SC -- which is how we implement CAS. As a
+ * result we need to clear reservations between the last CAS and the
+ * jump back to the new context. While it is unlikely the store
+ * completes, implementations are allowed to expand reservations to be
+ * arbitrarily large.
+ */
+ REG_L a2, PT_SEPC(sp)
+ REG_SC x0, a2, PT_SEPC(sp)
+
csrw CSR_SSTATUS, a0
csrw CSR_SEPC, a2
diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
index f0ba713..83f7d12 100644
--- a/arch/riscv/mm/init.c
+++ b/arch/riscv/mm/init.c
@@ -11,6 +11,7 @@
#include <linux/swap.h>
#include <linux/sizes.h>
#include <linux/of_fdt.h>
+#include <linux/libfdt.h>
#include <asm/fixmap.h>
#include <asm/tlbflush.h>
@@ -82,6 +83,8 @@ static void __init setup_initrd(void)
}
#endif /* CONFIG_BLK_DEV_INITRD */
+static phys_addr_t dtb_early_pa __initdata;
+
void __init setup_bootmem(void)
{
struct memblock_region *reg;
@@ -117,7 +120,12 @@ void __init setup_bootmem(void)
setup_initrd();
#endif /* CONFIG_BLK_DEV_INITRD */
- early_init_fdt_reserve_self();
+ /*
+ * Avoid using early_init_fdt_reserve_self() since __pa() does
+ * not work for DTB pointers that are fixmap addresses
+ */
+ memblock_reserve(dtb_early_pa, fdt_totalsize(dtb_early_va));
+
early_init_fdt_scan_reserved_mem();
memblock_allow_resize();
memblock_dump_all();
@@ -393,6 +401,8 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa)
/* Save pointer to DTB for early FDT parsing */
dtb_early_va = (void *)fix_to_virt(FIX_FDT) + (dtb_pa & ~PAGE_MASK);
+ /* Save physical address for memblock reservation */
+ dtb_early_pa = dtb_pa;
}
static void __init setup_vm_final(void)
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 23edf56..50eb430 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -219,13 +219,6 @@ enum {
PFERR_WRITE_MASK | \
PFERR_PRESENT_MASK)
-/*
- * The mask used to denote special SPTEs, which can be either MMIO SPTEs or
- * Access Tracking SPTEs. We use bit 62 instead of bit 63 to avoid conflicting
- * with the SVE bit in EPT PTEs.
- */
-#define SPTE_SPECIAL_MASK (1ULL << 62)
-
/* apic attention bits */
#define KVM_APIC_CHECK_VAPIC 0
/*
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 6331603..9c5029c 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -485,6 +485,7 @@ static inline int __do_cpuid_func(struct kvm_cpuid_entry2 *entry, u32 function,
/* cpuid 0x80000008.ebx */
const u32 kvm_cpuid_8000_0008_ebx_x86_features =
+ F(CLZERO) | F(XSAVEERPTR) |
F(WBNOINVD) | F(AMD_IBPB) | F(AMD_IBRS) | F(AMD_SSBD) | F(VIRT_SSBD) |
F(AMD_SSB_NO) | F(AMD_STIBP) | F(AMD_STIBP_ALWAYS_ON);
@@ -618,16 +619,20 @@ static inline int __do_cpuid_func(struct kvm_cpuid_entry2 *entry, u32 function,
*/
case 0x1f:
case 0xb: {
- int i, level_type;
+ int i;
- /* read more entries until level_type is zero */
- for (i = 1; ; ++i) {
+ /*
+ * We filled in entry[0] for CPUID(EAX=<function>,
+ * ECX=00H) above. If its level type (ECX[15:8]) is
+ * zero, then the leaf is unimplemented, and we're
+ * done. Otherwise, continue to populate entries
+ * until the level type (ECX[15:8]) of the previously
+ * added entry is zero.
+ */
+ for (i = 1; entry[i - 1].ecx & 0xff00; ++i) {
if (*nent >= maxnent)
goto out;
- level_type = entry[i - 1].ecx & 0xff00;
- if (!level_type)
- break;
do_host_cpuid(&entry[i], function, i);
++*nent;
}
@@ -969,53 +974,66 @@ struct kvm_cpuid_entry2 *kvm_find_cpuid_entry(struct kvm_vcpu *vcpu,
EXPORT_SYMBOL_GPL(kvm_find_cpuid_entry);
/*
- * If no match is found, check whether we exceed the vCPU's limit
- * and return the content of the highest valid _standard_ leaf instead.
- * This is to satisfy the CPUID specification.
+ * If the basic or extended CPUID leaf requested is higher than the
+ * maximum supported basic or extended leaf, respectively, then it is
+ * out of range.
*/
-static struct kvm_cpuid_entry2* check_cpuid_limit(struct kvm_vcpu *vcpu,
- u32 function, u32 index)
+static bool cpuid_function_in_range(struct kvm_vcpu *vcpu, u32 function)
{
- struct kvm_cpuid_entry2 *maxlevel;
+ struct kvm_cpuid_entry2 *max;
- maxlevel = kvm_find_cpuid_entry(vcpu, function & 0x80000000, 0);
- if (!maxlevel || maxlevel->eax >= function)
- return NULL;
- if (function & 0x80000000) {
- maxlevel = kvm_find_cpuid_entry(vcpu, 0, 0);
- if (!maxlevel)
- return NULL;
- }
- return kvm_find_cpuid_entry(vcpu, maxlevel->eax, index);
+ max = kvm_find_cpuid_entry(vcpu, function & 0x80000000, 0);
+ return max && function <= max->eax;
}
bool kvm_cpuid(struct kvm_vcpu *vcpu, u32 *eax, u32 *ebx,
u32 *ecx, u32 *edx, bool check_limit)
{
u32 function = *eax, index = *ecx;
- struct kvm_cpuid_entry2 *best;
- bool entry_found = true;
+ struct kvm_cpuid_entry2 *entry;
+ struct kvm_cpuid_entry2 *max;
+ bool found;
- best = kvm_find_cpuid_entry(vcpu, function, index);
-
- if (!best) {
- entry_found = false;
- if (!check_limit)
- goto out;
-
- best = check_cpuid_limit(vcpu, function, index);
+ entry = kvm_find_cpuid_entry(vcpu, function, index);
+ found = entry;
+ /*
+ * Intel CPUID semantics treats any query for an out-of-range
+ * leaf as if the highest basic leaf (i.e. CPUID.0H:EAX) were
+ * requested. AMD CPUID semantics returns all zeroes for any
+ * undefined leaf, whether or not the leaf is in range.
+ */
+ if (!entry && check_limit && !guest_cpuid_is_amd(vcpu) &&
+ !cpuid_function_in_range(vcpu, function)) {
+ max = kvm_find_cpuid_entry(vcpu, 0, 0);
+ if (max) {
+ function = max->eax;
+ entry = kvm_find_cpuid_entry(vcpu, function, index);
+ }
}
-
-out:
- if (best) {
- *eax = best->eax;
- *ebx = best->ebx;
- *ecx = best->ecx;
- *edx = best->edx;
- } else
+ if (entry) {
+ *eax = entry->eax;
+ *ebx = entry->ebx;
+ *ecx = entry->ecx;
+ *edx = entry->edx;
+ } else {
*eax = *ebx = *ecx = *edx = 0;
- trace_kvm_cpuid(function, *eax, *ebx, *ecx, *edx, entry_found);
- return entry_found;
+ /*
+ * When leaf 0BH or 1FH is defined, CL is pass-through
+ * and EDX is always the x2APIC ID, even for undefined
+ * subleaves. Index 1 will exist iff the leaf is
+ * implemented, so we pass through CL iff leaf 1
+ * exists. EDX can be copied from any existing index.
+ */
+ if (function == 0xb || function == 0x1f) {
+ entry = kvm_find_cpuid_entry(vcpu, function, 1);
+ if (entry) {
+ *ecx = index & 0xff;
+ *edx = entry->edx;
+ }
+ }
+ }
+ trace_kvm_cpuid(function, *eax, *ebx, *ecx, *edx, found);
+ return found;
}
EXPORT_SYMBOL_GPL(kvm_cpuid);
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 3a3a685..87b0fcc 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -66,9 +66,10 @@
#define X2APIC_BROADCAST 0xFFFFFFFFul
static bool lapic_timer_advance_dynamic __read_mostly;
-#define LAPIC_TIMER_ADVANCE_ADJUST_MIN 100
-#define LAPIC_TIMER_ADVANCE_ADJUST_MAX 5000
-#define LAPIC_TIMER_ADVANCE_ADJUST_INIT 1000
+#define LAPIC_TIMER_ADVANCE_ADJUST_MIN 100 /* clock cycles */
+#define LAPIC_TIMER_ADVANCE_ADJUST_MAX 10000 /* clock cycles */
+#define LAPIC_TIMER_ADVANCE_NS_INIT 1000
+#define LAPIC_TIMER_ADVANCE_NS_MAX 5000
/* step-by-step approximation to mitigate fluctuation */
#define LAPIC_TIMER_ADVANCE_ADJUST_STEP 8
@@ -1504,8 +1505,8 @@ static inline void adjust_lapic_timer_advance(struct kvm_vcpu *vcpu,
timer_advance_ns += ns/LAPIC_TIMER_ADVANCE_ADJUST_STEP;
}
- if (unlikely(timer_advance_ns > LAPIC_TIMER_ADVANCE_ADJUST_MAX))
- timer_advance_ns = LAPIC_TIMER_ADVANCE_ADJUST_INIT;
+ if (unlikely(timer_advance_ns > LAPIC_TIMER_ADVANCE_NS_MAX))
+ timer_advance_ns = LAPIC_TIMER_ADVANCE_NS_INIT;
apic->lapic_timer.timer_advance_ns = timer_advance_ns;
}
@@ -2302,7 +2303,7 @@ int kvm_create_lapic(struct kvm_vcpu *vcpu, int timer_advance_ns)
HRTIMER_MODE_ABS_HARD);
apic->lapic_timer.timer.function = apic_timer_fn;
if (timer_advance_ns == -1) {
- apic->lapic_timer.timer_advance_ns = LAPIC_TIMER_ADVANCE_ADJUST_INIT;
+ apic->lapic_timer.timer_advance_ns = LAPIC_TIMER_ADVANCE_NS_INIT;
lapic_timer_advance_dynamic = true;
} else {
apic->lapic_timer.timer_advance_ns = timer_advance_ns;
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 5269aa0..24c23c6 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -83,7 +83,17 @@ module_param(dbg, bool, 0644);
#define PTE_PREFETCH_NUM 8
#define PT_FIRST_AVAIL_BITS_SHIFT 10
-#define PT64_SECOND_AVAIL_BITS_SHIFT 52
+#define PT64_SECOND_AVAIL_BITS_SHIFT 54
+
+/*
+ * The mask used to denote special SPTEs, which can be either MMIO SPTEs or
+ * Access Tracking SPTEs.
+ */
+#define SPTE_SPECIAL_MASK (3ULL << 52)
+#define SPTE_AD_ENABLED_MASK (0ULL << 52)
+#define SPTE_AD_DISABLED_MASK (1ULL << 52)
+#define SPTE_AD_WRPROT_ONLY_MASK (2ULL << 52)
+#define SPTE_MMIO_MASK (3ULL << 52)
#define PT64_LEVEL_BITS 9
@@ -219,12 +229,11 @@ static u64 __read_mostly shadow_present_mask;
static u64 __read_mostly shadow_me_mask;
/*
- * SPTEs used by MMUs without A/D bits are marked with shadow_acc_track_value.
- * Non-present SPTEs with shadow_acc_track_value set are in place for access
- * tracking.
+ * SPTEs used by MMUs without A/D bits are marked with SPTE_AD_DISABLED_MASK;
+ * shadow_acc_track_mask is the set of bits to be cleared in non-accessed
+ * pages.
*/
static u64 __read_mostly shadow_acc_track_mask;
-static const u64 shadow_acc_track_value = SPTE_SPECIAL_MASK;
/*
* The mask/shift to use for saving the original R/X bits when marking the PTE
@@ -304,7 +313,7 @@ void kvm_mmu_set_mmio_spte_mask(u64 mmio_mask, u64 mmio_value, u64 access_mask)
{
BUG_ON((u64)(unsigned)access_mask != access_mask);
BUG_ON((mmio_mask & mmio_value) != mmio_value);
- shadow_mmio_value = mmio_value | SPTE_SPECIAL_MASK;
+ shadow_mmio_value = mmio_value | SPTE_MMIO_MASK;
shadow_mmio_mask = mmio_mask | SPTE_SPECIAL_MASK;
shadow_mmio_access_mask = access_mask;
}
@@ -320,10 +329,27 @@ static inline bool sp_ad_disabled(struct kvm_mmu_page *sp)
return sp->role.ad_disabled;
}
+static inline bool kvm_vcpu_ad_need_write_protect(struct kvm_vcpu *vcpu)
+{
+ /*
+ * When using the EPT page-modification log, the GPAs in the log
+ * would come from L2 rather than L1. Therefore, we need to rely
+ * on write protection to record dirty pages. This also bypasses
+ * PML, since writes now result in a vmexit.
+ */
+ return vcpu->arch.mmu == &vcpu->arch.guest_mmu;
+}
+
static inline bool spte_ad_enabled(u64 spte)
{
MMU_WARN_ON(is_mmio_spte(spte));
- return !(spte & shadow_acc_track_value);
+ return (spte & SPTE_SPECIAL_MASK) != SPTE_AD_DISABLED_MASK;
+}
+
+static inline bool spte_ad_need_write_protect(u64 spte)
+{
+ MMU_WARN_ON(is_mmio_spte(spte));
+ return (spte & SPTE_SPECIAL_MASK) != SPTE_AD_ENABLED_MASK;
}
static inline u64 spte_shadow_accessed_mask(u64 spte)
@@ -461,7 +487,7 @@ void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask,
{
BUG_ON(!dirty_mask != !accessed_mask);
BUG_ON(!accessed_mask && !acc_track_mask);
- BUG_ON(acc_track_mask & shadow_acc_track_value);
+ BUG_ON(acc_track_mask & SPTE_SPECIAL_MASK);
shadow_user_mask = user_mask;
shadow_accessed_mask = accessed_mask;
@@ -1589,16 +1615,16 @@ static bool spte_clear_dirty(u64 *sptep)
rmap_printk("rmap_clear_dirty: spte %p %llx\n", sptep, *sptep);
+ MMU_WARN_ON(!spte_ad_enabled(spte));
spte &= ~shadow_dirty_mask;
-
return mmu_spte_update(sptep, spte);
}
-static bool wrprot_ad_disabled_spte(u64 *sptep)
+static bool spte_wrprot_for_clear_dirty(u64 *sptep)
{
bool was_writable = test_and_clear_bit(PT_WRITABLE_SHIFT,
(unsigned long *)sptep);
- if (was_writable)
+ if (was_writable && !spte_ad_enabled(*sptep))
kvm_set_pfn_dirty(spte_to_pfn(*sptep));
return was_writable;
@@ -1617,10 +1643,10 @@ static bool __rmap_clear_dirty(struct kvm *kvm, struct kvm_rmap_head *rmap_head)
bool flush = false;
for_each_rmap_spte(rmap_head, &iter, sptep)
- if (spte_ad_enabled(*sptep))
- flush |= spte_clear_dirty(sptep);
+ if (spte_ad_need_write_protect(*sptep))
+ flush |= spte_wrprot_for_clear_dirty(sptep);
else
- flush |= wrprot_ad_disabled_spte(sptep);
+ flush |= spte_clear_dirty(sptep);
return flush;
}
@@ -1631,6 +1657,11 @@ static bool spte_set_dirty(u64 *sptep)
rmap_printk("rmap_set_dirty: spte %p %llx\n", sptep, *sptep);
+ /*
+ * Similar to the !kvm_x86_ops->slot_disable_log_dirty case,
+ * do not bother adding back write access to pages marked
+ * SPTE_AD_WRPROT_ONLY_MASK.
+ */
spte |= shadow_dirty_mask;
return mmu_spte_update(sptep, spte);
@@ -2622,7 +2653,7 @@ static void link_shadow_page(struct kvm_vcpu *vcpu, u64 *sptep,
shadow_user_mask | shadow_x_mask | shadow_me_mask;
if (sp_ad_disabled(sp))
- spte |= shadow_acc_track_value;
+ spte |= SPTE_AD_DISABLED_MASK;
else
spte |= shadow_accessed_mask;
@@ -2968,7 +2999,9 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
sp = page_header(__pa(sptep));
if (sp_ad_disabled(sp))
- spte |= shadow_acc_track_value;
+ spte |= SPTE_AD_DISABLED_MASK;
+ else if (kvm_vcpu_ad_need_write_protect(vcpu))
+ spte |= SPTE_AD_WRPROT_ONLY_MASK;
/*
* For the EPT case, shadow_present_mask is 0 if hardware
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 41abc62..e76eb4f 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -2610,7 +2610,7 @@ static int nested_check_vm_entry_controls(struct kvm_vcpu *vcpu,
/* VM-entry exception error code */
if (CC(has_error_code &&
- vmcs12->vm_entry_exception_error_code & GENMASK(31, 15)))
+ vmcs12->vm_entry_exception_error_code & GENMASK(31, 16)))
return -EINVAL;
/* VM-entry interruption-info field: reserved bits */
diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c
index 4dea0e0..3e9c059 100644
--- a/arch/x86/kvm/vmx/pmu_intel.c
+++ b/arch/x86/kvm/vmx/pmu_intel.c
@@ -262,6 +262,7 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
static void intel_pmu_refresh(struct kvm_vcpu *vcpu)
{
struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
+ struct x86_pmu_capability x86_pmu;
struct kvm_cpuid_entry2 *entry;
union cpuid10_eax eax;
union cpuid10_edx edx;
@@ -283,8 +284,10 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu)
if (!pmu->version)
return;
+ perf_get_x86_pmu_capability(&x86_pmu);
+
pmu->nr_arch_gp_counters = min_t(int, eax.split.num_counters,
- INTEL_PMC_MAX_GENERIC);
+ x86_pmu.num_counters_gp);
pmu->counter_bitmask[KVM_PMC_GP] = ((u64)1 << eax.split.bit_width) - 1;
pmu->available_event_types = ~entry->ebx &
((1ull << eax.split.mask_length) - 1);
@@ -294,7 +297,7 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu)
} else {
pmu->nr_arch_fixed_counters =
min_t(int, edx.split.num_counters_fixed,
- INTEL_PMC_MAX_FIXED);
+ x86_pmu.num_counters_fixed);
pmu->counter_bitmask[KVM_PMC_FIXED] =
((u64)1 << edx.split.bit_width_fixed) - 1;
}
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index d4575ff..e7970a2 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -209,6 +209,11 @@ static int vmx_setup_l1d_flush(enum vmx_l1d_flush_state l1tf)
struct page *page;
unsigned int i;
+ if (!boot_cpu_has_bug(X86_BUG_L1TF)) {
+ l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_NOT_REQUIRED;
+ return 0;
+ }
+
if (!enable_ept) {
l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_EPT_DISABLED;
return 0;
@@ -7995,12 +8000,10 @@ static int __init vmx_init(void)
* contain 'auto' which will be turned into the default 'cond'
* mitigation mode.
*/
- if (boot_cpu_has(X86_BUG_L1TF)) {
- r = vmx_setup_l1d_flush(vmentry_l1d_flush_param);
- if (r) {
- vmx_exit();
- return r;
- }
+ r = vmx_setup_l1d_flush(vmentry_l1d_flush_param);
+ if (r) {
+ vmx_exit();
+ return r;
}
#ifdef CONFIG_KEXEC_CORE
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 0ed07d8..661e2bf 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -92,8 +92,8 @@ u64 __read_mostly efer_reserved_bits = ~((u64)(EFER_SCE | EFER_LME | EFER_LMA));
static u64 __read_mostly efer_reserved_bits = ~((u64)EFER_SCE);
#endif
-#define VM_STAT(x) offsetof(struct kvm, stat.x), KVM_STAT_VM
-#define VCPU_STAT(x) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU
+#define VM_STAT(x, ...) offsetof(struct kvm, stat.x), KVM_STAT_VM, ## __VA_ARGS__
+#define VCPU_STAT(x, ...) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU, ## __VA_ARGS__
#define KVM_X2APIC_API_VALID_FLAGS (KVM_X2APIC_API_USE_32BIT_IDS | \
KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK)
@@ -212,7 +212,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
{ "mmu_cache_miss", VM_STAT(mmu_cache_miss) },
{ "mmu_unsync", VM_STAT(mmu_unsync) },
{ "remote_tlb_flush", VM_STAT(remote_tlb_flush) },
- { "largepages", VM_STAT(lpages) },
+ { "largepages", VM_STAT(lpages, .mode = 0444) },
{ "max_mmu_page_hash_collisions",
VM_STAT(max_mmu_page_hash_collisions) },
{ NULL }
@@ -885,34 +885,42 @@ int kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr)
}
EXPORT_SYMBOL_GPL(kvm_set_xcr);
+static int kvm_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
+{
+ if (cr4 & CR4_RESERVED_BITS)
+ return -EINVAL;
+
+ if (!guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) && (cr4 & X86_CR4_OSXSAVE))
+ return -EINVAL;
+
+ if (!guest_cpuid_has(vcpu, X86_FEATURE_SMEP) && (cr4 & X86_CR4_SMEP))
+ return -EINVAL;
+
+ if (!guest_cpuid_has(vcpu, X86_FEATURE_SMAP) && (cr4 & X86_CR4_SMAP))
+ return -EINVAL;
+
+ if (!guest_cpuid_has(vcpu, X86_FEATURE_FSGSBASE) && (cr4 & X86_CR4_FSGSBASE))
+ return -EINVAL;
+
+ if (!guest_cpuid_has(vcpu, X86_FEATURE_PKU) && (cr4 & X86_CR4_PKE))
+ return -EINVAL;
+
+ if (!guest_cpuid_has(vcpu, X86_FEATURE_LA57) && (cr4 & X86_CR4_LA57))
+ return -EINVAL;
+
+ if (!guest_cpuid_has(vcpu, X86_FEATURE_UMIP) && (cr4 & X86_CR4_UMIP))
+ return -EINVAL;
+
+ return 0;
+}
+
int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
{
unsigned long old_cr4 = kvm_read_cr4(vcpu);
unsigned long pdptr_bits = X86_CR4_PGE | X86_CR4_PSE | X86_CR4_PAE |
X86_CR4_SMEP | X86_CR4_SMAP | X86_CR4_PKE;
- if (cr4 & CR4_RESERVED_BITS)
- return 1;
-
- if (!guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) && (cr4 & X86_CR4_OSXSAVE))
- return 1;
-
- if (!guest_cpuid_has(vcpu, X86_FEATURE_SMEP) && (cr4 & X86_CR4_SMEP))
- return 1;
-
- if (!guest_cpuid_has(vcpu, X86_FEATURE_SMAP) && (cr4 & X86_CR4_SMAP))
- return 1;
-
- if (!guest_cpuid_has(vcpu, X86_FEATURE_FSGSBASE) && (cr4 & X86_CR4_FSGSBASE))
- return 1;
-
- if (!guest_cpuid_has(vcpu, X86_FEATURE_PKU) && (cr4 & X86_CR4_PKE))
- return 1;
-
- if (!guest_cpuid_has(vcpu, X86_FEATURE_LA57) && (cr4 & X86_CR4_LA57))
- return 1;
-
- if (!guest_cpuid_has(vcpu, X86_FEATURE_UMIP) && (cr4 & X86_CR4_UMIP))
+ if (kvm_valid_cr4(vcpu, cr4))
return 1;
if (is_long_mode(vcpu)) {
@@ -1161,13 +1169,6 @@ static u32 msrs_to_save[] = {
MSR_ARCH_PERFMON_PERFCTR0 + 12, MSR_ARCH_PERFMON_PERFCTR0 + 13,
MSR_ARCH_PERFMON_PERFCTR0 + 14, MSR_ARCH_PERFMON_PERFCTR0 + 15,
MSR_ARCH_PERFMON_PERFCTR0 + 16, MSR_ARCH_PERFMON_PERFCTR0 + 17,
- MSR_ARCH_PERFMON_PERFCTR0 + 18, MSR_ARCH_PERFMON_PERFCTR0 + 19,
- MSR_ARCH_PERFMON_PERFCTR0 + 20, MSR_ARCH_PERFMON_PERFCTR0 + 21,
- MSR_ARCH_PERFMON_PERFCTR0 + 22, MSR_ARCH_PERFMON_PERFCTR0 + 23,
- MSR_ARCH_PERFMON_PERFCTR0 + 24, MSR_ARCH_PERFMON_PERFCTR0 + 25,
- MSR_ARCH_PERFMON_PERFCTR0 + 26, MSR_ARCH_PERFMON_PERFCTR0 + 27,
- MSR_ARCH_PERFMON_PERFCTR0 + 28, MSR_ARCH_PERFMON_PERFCTR0 + 29,
- MSR_ARCH_PERFMON_PERFCTR0 + 30, MSR_ARCH_PERFMON_PERFCTR0 + 31,
MSR_ARCH_PERFMON_EVENTSEL0, MSR_ARCH_PERFMON_EVENTSEL1,
MSR_ARCH_PERFMON_EVENTSEL0 + 2, MSR_ARCH_PERFMON_EVENTSEL0 + 3,
MSR_ARCH_PERFMON_EVENTSEL0 + 4, MSR_ARCH_PERFMON_EVENTSEL0 + 5,
@@ -1177,13 +1178,6 @@ static u32 msrs_to_save[] = {
MSR_ARCH_PERFMON_EVENTSEL0 + 12, MSR_ARCH_PERFMON_EVENTSEL0 + 13,
MSR_ARCH_PERFMON_EVENTSEL0 + 14, MSR_ARCH_PERFMON_EVENTSEL0 + 15,
MSR_ARCH_PERFMON_EVENTSEL0 + 16, MSR_ARCH_PERFMON_EVENTSEL0 + 17,
- MSR_ARCH_PERFMON_EVENTSEL0 + 18, MSR_ARCH_PERFMON_EVENTSEL0 + 19,
- MSR_ARCH_PERFMON_EVENTSEL0 + 20, MSR_ARCH_PERFMON_EVENTSEL0 + 21,
- MSR_ARCH_PERFMON_EVENTSEL0 + 22, MSR_ARCH_PERFMON_EVENTSEL0 + 23,
- MSR_ARCH_PERFMON_EVENTSEL0 + 24, MSR_ARCH_PERFMON_EVENTSEL0 + 25,
- MSR_ARCH_PERFMON_EVENTSEL0 + 26, MSR_ARCH_PERFMON_EVENTSEL0 + 27,
- MSR_ARCH_PERFMON_EVENTSEL0 + 28, MSR_ARCH_PERFMON_EVENTSEL0 + 29,
- MSR_ARCH_PERFMON_EVENTSEL0 + 30, MSR_ARCH_PERFMON_EVENTSEL0 + 31,
};
static unsigned num_msrs_to_save;
@@ -5097,13 +5091,14 @@ long kvm_arch_vm_ioctl(struct file *filp,
static void kvm_init_msr_list(void)
{
+ struct x86_pmu_capability x86_pmu;
u32 dummy[2];
unsigned i, j;
BUILD_BUG_ON_MSG(INTEL_PMC_MAX_FIXED != 4,
"Please update the fixed PMCs in msrs_to_save[]");
- BUILD_BUG_ON_MSG(INTEL_PMC_MAX_GENERIC != 32,
- "Please update the generic perfctr/eventsel MSRs in msrs_to_save[]");
+
+ perf_get_x86_pmu_capability(&x86_pmu);
for (i = j = 0; i < ARRAY_SIZE(msrs_to_save); i++) {
if (rdmsr_safe(msrs_to_save[i], &dummy[0], &dummy[1]) < 0)
@@ -5145,6 +5140,15 @@ static void kvm_init_msr_list(void)
intel_pt_validate_hw_cap(PT_CAP_num_address_ranges) * 2)
continue;
break;
+ case MSR_ARCH_PERFMON_PERFCTR0 ... MSR_ARCH_PERFMON_PERFCTR0 + 17:
+ if (msrs_to_save[i] - MSR_ARCH_PERFMON_PERFCTR0 >=
+ min(INTEL_PMC_MAX_GENERIC, x86_pmu.num_counters_gp))
+ continue;
+ break;
+ case MSR_ARCH_PERFMON_EVENTSEL0 ... MSR_ARCH_PERFMON_EVENTSEL0 + 17:
+ if (msrs_to_save[i] - MSR_ARCH_PERFMON_EVENTSEL0 >=
+ min(INTEL_PMC_MAX_GENERIC, x86_pmu.num_counters_gp))
+ continue;
}
default:
break;
@@ -8714,10 +8718,6 @@ EXPORT_SYMBOL_GPL(kvm_task_switch);
static int kvm_valid_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
{
- if (!guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) &&
- (sregs->cr4 & X86_CR4_OSXSAVE))
- return -EINVAL;
-
if ((sregs->efer & EFER_LME) && (sregs->cr0 & X86_CR0_PG)) {
/*
* When EFER.LME and CR0.PG are set, the processor is in
@@ -8736,7 +8736,7 @@ static int kvm_valid_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
return -EINVAL;
}
- return 0;
+ return kvm_valid_cr4(vcpu, sregs->cr4);
}
static int __set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
diff --git a/arch/x86/xen/efi.c b/arch/x86/xen/efi.c
index 0d3365c..a04551e 100644
--- a/arch/x86/xen/efi.c
+++ b/arch/x86/xen/efi.c
@@ -57,19 +57,7 @@ static efi_system_table_t __init *xen_efi_probe(void)
return NULL;
/* Here we know that Xen runs on EFI platform. */
-
- efi.get_time = xen_efi_get_time;
- efi.set_time = xen_efi_set_time;
- efi.get_wakeup_time = xen_efi_get_wakeup_time;
- efi.set_wakeup_time = xen_efi_set_wakeup_time;
- efi.get_variable = xen_efi_get_variable;
- efi.get_next_variable = xen_efi_get_next_variable;
- efi.set_variable = xen_efi_set_variable;
- efi.query_variable_info = xen_efi_query_variable_info;
- efi.update_capsule = xen_efi_update_capsule;
- efi.query_capsule_caps = xen_efi_query_capsule_caps;
- efi.get_next_high_mono_count = xen_efi_get_next_high_mono_count;
- efi.reset_system = xen_efi_reset_system;
+ xen_efi_runtime_setup();
efi_systab_xen.tables = info->cfg.addr;
efi_systab_xen.nr_tables = info->cfg.nent;
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 6e3b15f..ec79115 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -1992,10 +1992,14 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
/* bypass scheduler for flush rq */
blk_insert_flush(rq);
blk_mq_run_hw_queue(data.hctx, true);
- } else if (plug && (q->nr_hw_queues == 1 || q->mq_ops->commit_rqs)) {
+ } else if (plug && (q->nr_hw_queues == 1 || q->mq_ops->commit_rqs ||
+ !blk_queue_nonrot(q))) {
/*
* Use plugging if we have a ->commit_rqs() hook as well, as
* we know the driver uses bd->last in a smart fashion.
+ *
+ * Use normal plugging if this disk is slow HDD, as sequential
+ * IO may benefit a lot from plug merging.
*/
unsigned int request_count = plug->rq_count;
struct request *last = NULL;
@@ -2012,6 +2016,8 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
}
blk_add_rq_to_plug(plug, rq);
+ } else if (q->elevator) {
+ blk_mq_sched_insert_request(rq, false, true, true);
} else if (plug && !blk_queue_nomerges(q)) {
/*
* We do limited plugging. If the bio can be merged, do that.
@@ -2035,8 +2041,8 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
blk_mq_try_issue_directly(data.hctx, same_queue_rq,
&cookie);
}
- } else if ((q->nr_hw_queues > 1 && is_sync) || (!q->elevator &&
- !data.hctx->dispatch_busy)) {
+ } else if ((q->nr_hw_queues > 1 && is_sync) ||
+ !data.hctx->dispatch_busy) {
blk_mq_try_issue_directly(data.hctx, rq, &cookie);
} else {
blk_mq_sched_insert_request(rq, false, true, true);
diff --git a/block/sed-opal.c b/block/sed-opal.c
index 4e95a97..b4c7619 100644
--- a/block/sed-opal.c
+++ b/block/sed-opal.c
@@ -129,7 +129,7 @@ static const u8 opaluid[][OPAL_UID_LENGTH] = {
{ 0x00, 0x00, 0x00, 0x09, 0x00, 0x00, 0x84, 0x01 },
/* tables */
- [OPAL_TABLE_TABLE]
+ [OPAL_TABLE_TABLE] =
{ 0x00, 0x00, 0x00, 0x01, 0x00, 0x00, 0x00, 0x01 },
[OPAL_LOCKINGRANGE_GLOBAL] =
{ 0x00, 0x00, 0x08, 0x02, 0x00, 0x00, 0x00, 0x01 },
@@ -372,8 +372,8 @@ static void check_geometry(struct opal_dev *dev, const void *data)
{
const struct d0_geometry_features *geo = data;
- dev->align = geo->alignment_granularity;
- dev->lowest_lba = geo->lowest_aligned_lba;
+ dev->align = be64_to_cpu(geo->alignment_granularity);
+ dev->lowest_lba = be64_to_cpu(geo->lowest_aligned_lba);
}
static int execute_step(struct opal_dev *dev,
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index 1410fa8..f6f77ea 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -994,6 +994,16 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode,
if (!(lo_flags & LO_FLAGS_READ_ONLY) && file->f_op->fsync)
blk_queue_write_cache(lo->lo_queue, true, false);
+ if (io_is_direct(lo->lo_backing_file) && inode->i_sb->s_bdev) {
+ /* In case of direct I/O, match underlying block size */
+ unsigned short bsize = bdev_logical_block_size(
+ inode->i_sb->s_bdev);
+
+ blk_queue_logical_block_size(lo->lo_queue, bsize);
+ blk_queue_physical_block_size(lo->lo_queue, bsize);
+ blk_queue_io_min(lo->lo_queue, bsize);
+ }
+
loop_update_rotational(lo);
loop_update_dio(lo);
set_capacity(lo->lo_disk, size);
diff --git a/drivers/char/random.c b/drivers/char/random.c
index c2f7de9..de434fe 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -2520,4 +2520,4 @@ void add_bootloader_randomness(const void *buf, unsigned int size)
else
add_device_randomness(buf, size);
}
-EXPORT_SYMBOL_GPL(add_bootloader_randomness);
\ No newline at end of file
+EXPORT_SYMBOL_GPL(add_bootloader_randomness);
diff --git a/drivers/clocksource/timer-of.c b/drivers/clocksource/timer-of.c
index d8c2bd4..11ff701 100644
--- a/drivers/clocksource/timer-of.c
+++ b/drivers/clocksource/timer-of.c
@@ -25,7 +25,9 @@ static __init void timer_of_irq_exit(struct of_timer_irq *of_irq)
struct clock_event_device *clkevt = &to->clkevt;
- of_irq->percpu ? free_percpu_irq(of_irq->irq, clkevt) :
+ if (of_irq->percpu)
+ free_percpu_irq(of_irq->irq, clkevt);
+ else
free_irq(of_irq->irq, clkevt);
}
diff --git a/drivers/gpu/drm/amd/amdgpu/Makefile b/drivers/gpu/drm/amd/amdgpu/Makefile
index 42e2c1f..00962a6 100644
--- a/drivers/gpu/drm/amd/amdgpu/Makefile
+++ b/drivers/gpu/drm/amd/amdgpu/Makefile
@@ -54,7 +54,7 @@
amdgpu_gtt_mgr.o amdgpu_vram_mgr.o amdgpu_virt.o amdgpu_atomfirmware.o \
amdgpu_vf_error.o amdgpu_sched.o amdgpu_debugfs.o amdgpu_ids.o \
amdgpu_gmc.o amdgpu_xgmi.o amdgpu_csa.o amdgpu_ras.o amdgpu_vm_cpu.o \
- amdgpu_vm_sdma.o amdgpu_pmu.o amdgpu_discovery.o amdgpu_ras_eeprom.o smu_v11_0_i2c.o
+ amdgpu_vm_sdma.o amdgpu_discovery.o amdgpu_ras_eeprom.o smu_v11_0_i2c.o
amdgpu-$(CONFIG_PERF_EVENTS) += amdgpu_pmu.o
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c
index eba42c7..82155ac 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c
@@ -189,7 +189,7 @@ static int acp_hw_init(void *handle)
u32 val = 0;
u32 count = 0;
struct device *dev;
- struct i2s_platform_data *i2s_pdata;
+ struct i2s_platform_data *i2s_pdata = NULL;
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
@@ -231,20 +231,21 @@ static int acp_hw_init(void *handle)
adev->acp.acp_cell = kcalloc(ACP_DEVS, sizeof(struct mfd_cell),
GFP_KERNEL);
- if (adev->acp.acp_cell == NULL)
- return -ENOMEM;
+ if (adev->acp.acp_cell == NULL) {
+ r = -ENOMEM;
+ goto failure;
+ }
adev->acp.acp_res = kcalloc(5, sizeof(struct resource), GFP_KERNEL);
if (adev->acp.acp_res == NULL) {
- kfree(adev->acp.acp_cell);
- return -ENOMEM;
+ r = -ENOMEM;
+ goto failure;
}
i2s_pdata = kcalloc(3, sizeof(struct i2s_platform_data), GFP_KERNEL);
if (i2s_pdata == NULL) {
- kfree(adev->acp.acp_res);
- kfree(adev->acp.acp_cell);
- return -ENOMEM;
+ r = -ENOMEM;
+ goto failure;
}
switch (adev->asic_type) {
@@ -341,14 +342,14 @@ static int acp_hw_init(void *handle)
r = mfd_add_hotplug_devices(adev->acp.parent, adev->acp.acp_cell,
ACP_DEVS);
if (r)
- return r;
+ goto failure;
for (i = 0; i < ACP_DEVS ; i++) {
dev = get_mfd_cell_dev(adev->acp.acp_cell[i].name, i);
r = pm_genpd_add_device(&adev->acp.acp_genpd->gpd, dev);
if (r) {
dev_err(dev, "Failed to add dev to genpd\n");
- return r;
+ goto failure;
}
}
@@ -367,7 +368,8 @@ static int acp_hw_init(void *handle)
break;
if (--count == 0) {
dev_err(&adev->pdev->dev, "Failed to reset ACP\n");
- return -ETIMEDOUT;
+ r = -ETIMEDOUT;
+ goto failure;
}
udelay(100);
}
@@ -384,7 +386,8 @@ static int acp_hw_init(void *handle)
break;
if (--count == 0) {
dev_err(&adev->pdev->dev, "Failed to reset ACP\n");
- return -ETIMEDOUT;
+ r = -ETIMEDOUT;
+ goto failure;
}
udelay(100);
}
@@ -393,6 +396,13 @@ static int acp_hw_init(void *handle)
val &= ~ACP_SOFT_RESET__SoftResetAud_MASK;
cgs_write_register(adev->acp.cgs_device, mmACP_SOFT_RESET, val);
return 0;
+
+failure:
+ kfree(i2s_pdata);
+ kfree(adev->acp.acp_res);
+ kfree(adev->acp.acp_cell);
+ kfree(adev->acp.acp_genpd);
+ return r;
}
/**
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 264677a..6f8aaf6 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -81,9 +81,10 @@
* - 3.32.0 - Add syncobj timeline support to AMDGPU_CS.
* - 3.33.0 - Fixes for GDS ENOMEM failures in AMDGPU_CS.
* - 3.34.0 - Non-DC can flip correctly between buffers with different pitches
+ * - 3.35.0 - Add drm_amdgpu_info_device::tcc_disabled_mask
*/
#define KMS_DRIVER_MAJOR 3
-#define KMS_DRIVER_MINOR 34
+#define KMS_DRIVER_MINOR 35
#define KMS_DRIVER_PATCHLEVEL 0
#define AMDGPU_MAX_TIMEOUT_PARAM_LENTH 256
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h
index 554a59b..6ee4021 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h
@@ -165,6 +165,7 @@ struct amdgpu_gfx_config {
uint32_t num_sc_per_sh;
uint32_t num_packer_per_sc;
uint32_t pa_sc_tile_steering_override;
+ uint64_t tcc_disabled_mask;
};
struct amdgpu_cu_info {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
index f614752..f2c0979 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
@@ -787,6 +787,8 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file
dev_info.pa_sc_tile_steering_override =
adev->gfx.config.pa_sc_tile_steering_override;
+ dev_info.tcc_disabled_mask = adev->gfx.config.tcc_disabled_mask;
+
return copy_to_user(out, &dev_info,
min((size_t)size, sizeof(dev_info))) ? -EFAULT : 0;
}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index e2fb141..5251352 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -603,14 +603,12 @@ void amdgpu_vm_move_to_lru_tail(struct amdgpu_device *adev,
struct ttm_bo_global *glob = adev->mman.bdev.glob;
struct amdgpu_vm_bo_base *bo_base;
-#if 0
if (vm->bulk_moveable) {
spin_lock(&glob->lru_lock);
ttm_bo_bulk_move_lru_tail(&vm->lru_bulk_move);
spin_unlock(&glob->lru_lock);
return;
}
-#endif
memset(&vm->lru_bulk_move, 0, sizeof(vm->lru_bulk_move));
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
index 638c821..957811b 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
@@ -1691,6 +1691,17 @@ static void gfx_v10_0_tcp_harvest(struct amdgpu_device *adev)
}
}
+static void gfx_v10_0_get_tcc_info(struct amdgpu_device *adev)
+{
+ /* TCCs are global (not instanced). */
+ uint32_t tcc_disable = RREG32_SOC15(GC, 0, mmCGTS_TCC_DISABLE) |
+ RREG32_SOC15(GC, 0, mmCGTS_USER_TCC_DISABLE);
+
+ adev->gfx.config.tcc_disabled_mask =
+ REG_GET_FIELD(tcc_disable, CGTS_TCC_DISABLE, TCC_DISABLE) |
+ (REG_GET_FIELD(tcc_disable, CGTS_TCC_DISABLE, HI_TCC_DISABLE) << 16);
+}
+
static void gfx_v10_0_constants_init(struct amdgpu_device *adev)
{
u32 tmp;
@@ -1702,6 +1713,7 @@ static void gfx_v10_0_constants_init(struct amdgpu_device *adev)
gfx_v10_0_setup_rb(adev);
gfx_v10_0_get_cu_info(adev, &adev->gfx.cu_info);
+ gfx_v10_0_get_tcc_info(adev);
adev->gfx.config.pa_sc_tile_steering_override =
gfx_v10_0_init_pa_sc_tile_steering_override(adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/nv.c b/drivers/gpu/drm/amd/amdgpu/nv.c
index 85393a9..de9b995 100644
--- a/drivers/gpu/drm/amd/amdgpu/nv.c
+++ b/drivers/gpu/drm/amd/amdgpu/nv.c
@@ -317,10 +317,12 @@ static int nv_asic_reset(struct amdgpu_device *adev)
struct smu_context *smu = &adev->smu;
if (nv_asic_reset_method(adev) == AMD_RESET_METHOD_BACO) {
- amdgpu_inc_vram_lost(adev);
+ if (!adev->in_suspend)
+ amdgpu_inc_vram_lost(adev);
ret = smu_baco_reset(smu);
} else {
- amdgpu_inc_vram_lost(adev);
+ if (!adev->in_suspend)
+ amdgpu_inc_vram_lost(adev);
ret = nv_asic_mode1_reset(adev);
}
diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c
index f70658a..f8ab80c 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc15.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc15.c
@@ -558,12 +558,14 @@ static int soc15_asic_reset(struct amdgpu_device *adev)
{
switch (soc15_asic_reset_method(adev)) {
case AMD_RESET_METHOD_BACO:
- amdgpu_inc_vram_lost(adev);
+ if (!adev->in_suspend)
+ amdgpu_inc_vram_lost(adev);
return soc15_asic_baco_reset(adev);
case AMD_RESET_METHOD_MODE2:
return soc15_mode2_reset(adev);
default:
- amdgpu_inc_vram_lost(adev);
+ if (!adev->in_suspend)
+ amdgpu_inc_vram_lost(adev);
return soc15_asic_mode1_reset(adev);
}
}
@@ -771,8 +773,6 @@ int soc15_set_ip_blocks(struct amdgpu_device *adev)
#if defined(CONFIG_DRM_AMD_DC)
else if (amdgpu_device_has_dc_support(adev))
amdgpu_device_ip_block_add(adev, &dm_ip_block);
-#else
-# warning "Enable CONFIG_DRM_AMD_DC for display support on SOC15."
#endif
amdgpu_device_ip_block_add(adev, &vcn_v2_0_ip_block);
break;
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index 8cab6da..a52f0b1 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -2385,8 +2385,6 @@ static int amdgpu_dm_initialize_drm_device(struct amdgpu_device *adev)
if (adev->asic_type != CHIP_CARRIZO && adev->asic_type != CHIP_STONEY)
dm->dc->debug.disable_stutter = amdgpu_pp_feature_mask & PP_STUTTER_MODE ? false : true;
- if (adev->asic_type == CHIP_RENOIR)
- dm->dc->debug.disable_stutter = true;
return 0;
fail:
@@ -6019,7 +6017,9 @@ static void amdgpu_dm_enable_crtc_interrupts(struct drm_device *dev,
struct drm_crtc *crtc;
struct drm_crtc_state *old_crtc_state, *new_crtc_state;
int i;
+#ifdef CONFIG_DEBUG_FS
enum amdgpu_dm_pipe_crc_source source;
+#endif
for_each_oldnew_crtc_in_state(state, crtc, old_crtc_state,
new_crtc_state, i) {
diff --git a/drivers/gpu/drm/amd/display/dc/dce100/dce100_resource.c b/drivers/gpu/drm/amd/display/dc/dce100/dce100_resource.c
index 1787b9b..76d5488 100644
--- a/drivers/gpu/drm/amd/display/dc/dce100/dce100_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dce100/dce100_resource.c
@@ -668,6 +668,7 @@ struct clock_source *dce100_clock_source_create(
return &clk_src->base;
}
+ kfree(clk_src);
BREAK_TO_DEBUGGER();
return NULL;
}
diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c
index 318e9c2..89620ad 100644
--- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c
@@ -714,6 +714,7 @@ struct clock_source *dce110_clock_source_create(
return &clk_src->base;
}
+ kfree(clk_src);
BREAK_TO_DEBUGGER();
return NULL;
}
diff --git a/drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.c b/drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.c
index 83e1878..21a657e 100644
--- a/drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.c
@@ -687,6 +687,7 @@ struct clock_source *dce112_clock_source_create(
return &clk_src->base;
}
+ kfree(clk_src);
BREAK_TO_DEBUGGER();
return NULL;
}
diff --git a/drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c b/drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c
index 8b85e52..7c52f7f 100644
--- a/drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c
@@ -500,6 +500,7 @@ static struct clock_source *dce120_clock_source_create(
return &clk_src->base;
}
+ kfree(clk_src);
BREAK_TO_DEBUGGER();
return NULL;
}
diff --git a/drivers/gpu/drm/amd/display/dc/dce80/dce80_resource.c b/drivers/gpu/drm/amd/display/dc/dce80/dce80_resource.c
index 4625df9..643ccb0 100644
--- a/drivers/gpu/drm/amd/display/dc/dce80/dce80_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dce80/dce80_resource.c
@@ -701,6 +701,7 @@ struct clock_source *dce80_clock_source_create(
return &clk_src->base;
}
+ kfree(clk_src);
BREAK_TO_DEBUGGER();
return NULL;
}
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
index 59305e4..1599bb9 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
@@ -786,6 +786,7 @@ struct clock_source *dcn10_clock_source_create(
return &clk_src->base;
}
+ kfree(clk_src);
BREAK_TO_DEBUGGER();
return NULL;
}
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
index b4e3ce2..5a2763d 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
@@ -1077,6 +1077,7 @@ struct clock_source *dcn20_clock_source_create(
return &clk_src->base;
}
+ kfree(clk_src);
BREAK_TO_DEBUGGER();
return NULL;
}
diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/Makefile b/drivers/gpu/drm/amd/display/dc/dcn21/Makefile
index 8cd9de8..ef673bf 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn21/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dcn21/Makefile
@@ -3,7 +3,17 @@
DCN21 = dcn21_hubp.o dcn21_hubbub.o dcn21_resource.o
-CFLAGS_$(AMDDALPATH)/dc/dcn21/dcn21_resource.o := -mhard-float -msse -mpreferred-stack-boundary=4
+ifneq ($(call cc-option, -mpreferred-stack-boundary=4),)
+ cc_stack_align := -mpreferred-stack-boundary=4
+else ifneq ($(call cc-option, -mstack-alignment=16),)
+ cc_stack_align := -mstack-alignment=16
+endif
+
+CFLAGS_$(AMDDALPATH)/dc/dcn21/dcn21_resource.o := -mhard-float -msse $(cc_stack_align)
+
+ifdef CONFIG_CC_IS_CLANG
+CFLAGS_$(AMDDALPATH)/dc/dcn21/dcn21_resource.o += -msse2
+endif
AMD_DAL_DCN21 = $(addprefix $(AMDDALPATH)/dc/dcn21/,$(DCN21))
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_mode_vba_21.c b/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_mode_vba_21.c
index 456cd0e..3b6ed60 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_mode_vba_21.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_mode_vba_21.c
@@ -39,9 +39,6 @@
* ways. Unless there is something clearly wrong with it the code should
* remain as-is as it provides us with a guarantee from HW that it is correct.
*/
-
-typedef unsigned int uint;
-
typedef struct {
double DPPCLK;
double DISPCLK;
@@ -4774,7 +4771,7 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
mode_lib->vba.MaximumReadBandwidthWithoutPrefetch = 0.0;
mode_lib->vba.MaximumReadBandwidthWithPrefetch = 0.0;
for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) {
- uint m;
+ unsigned int m;
locals->cursor_bw[k] = 0;
locals->cursor_bw_pre[k] = 0;
@@ -5285,7 +5282,7 @@ static void CalculateWatermarksAndDRAMSpeedChangeSupport(
double SecondMinActiveDRAMClockChangeMarginOneDisplayInVBLank;
double FullDETBufferingTimeYStutterCriticalPlane = 0;
double TimeToFinishSwathTransferStutterCriticalPlane = 0;
- uint k, j;
+ unsigned int k, j;
mode_lib->vba.TotalActiveDPP = 0;
mode_lib->vba.TotalDCCActiveDPP = 0;
@@ -5507,7 +5504,7 @@ static void CalculateDCFCLKDeepSleep(
double DPPCLK[],
double *DCFCLKDeepSleep)
{
- uint k;
+ unsigned int k;
double DisplayPipeLineDeliveryTimeLuma;
double DisplayPipeLineDeliveryTimeChroma;
//double DCFCLKDeepSleepPerPlane[DC__NUM_DPP__MAX];
@@ -5727,7 +5724,7 @@ static void CalculatePixelDeliveryTimes(
double DisplayPipeRequestDeliveryTimeChromaPrefetch[])
{
double req_per_swath_ub;
- uint k;
+ unsigned int k;
for (k = 0; k < NumberOfActivePlanes; ++k) {
if (VRatio[k] <= 1) {
@@ -5869,7 +5866,7 @@ static void CalculateMetaAndPTETimes(
unsigned int dpte_groups_per_row_chroma_ub;
unsigned int num_group_per_lower_vm_stage;
unsigned int num_req_per_lower_vm_stage;
- uint k;
+ unsigned int k;
for (k = 0; k < NumberOfActivePlanes; ++k) {
if (GPUVMEnable == true) {
diff --git a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c b/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c
index 33960fb..4acf139 100644
--- a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c
+++ b/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c
@@ -843,6 +843,8 @@ static int smu_sw_init(void *handle)
smu->smu_baco.state = SMU_BACO_STATE_EXIT;
smu->smu_baco.platform_support = false;
+ mutex_init(&smu->sensor_lock);
+
smu->watermarks_bitmap = 0;
smu->power_profile_mode = PP_SMC_POWER_PROFILE_BOOTUP_DEFAULT;
smu->default_power_profile_mode = PP_SMC_POWER_PROFILE_BOOTUP_DEFAULT;
diff --git a/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c b/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c
index f1f0720..d493a3f 100644
--- a/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c
+++ b/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c
@@ -1018,6 +1018,7 @@ static int arcturus_read_sensor(struct smu_context *smu,
if (!data || !size)
return -EINVAL;
+ mutex_lock(&smu->sensor_lock);
switch (sensor) {
case AMDGPU_PP_SENSOR_MAX_FAN_RPM:
*(uint32_t *)data = pptable->FanMaximumRpm;
@@ -1044,6 +1045,7 @@ static int arcturus_read_sensor(struct smu_context *smu,
default:
ret = smu_smc_read_sensor(smu, sensor, data, size);
}
+ mutex_unlock(&smu->sensor_lock);
return ret;
}
diff --git a/drivers/gpu/drm/amd/powerplay/inc/amdgpu_smu.h b/drivers/gpu/drm/amd/powerplay/inc/amdgpu_smu.h
index 6109815..23171a4 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/amdgpu_smu.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/amdgpu_smu.h
@@ -344,6 +344,7 @@ struct smu_context
const struct smu_funcs *funcs;
const struct pptable_funcs *ppt_funcs;
struct mutex mutex;
+ struct mutex sensor_lock;
uint64_t pool_size;
struct smu_table_context smu_table;
diff --git a/drivers/gpu/drm/amd/powerplay/navi10_ppt.c b/drivers/gpu/drm/amd/powerplay/navi10_ppt.c
index 12c0e46..0b46140 100644
--- a/drivers/gpu/drm/amd/powerplay/navi10_ppt.c
+++ b/drivers/gpu/drm/amd/powerplay/navi10_ppt.c
@@ -547,7 +547,7 @@ static int navi10_get_metrics_table(struct smu_context *smu,
struct smu_table_context *smu_table= &smu->smu_table;
int ret = 0;
- if (!smu_table->metrics_time || time_after(jiffies, smu_table->metrics_time + HZ / 1000)) {
+ if (!smu_table->metrics_time || time_after(jiffies, smu_table->metrics_time + msecs_to_jiffies(100))) {
ret = smu_update_table(smu, SMU_TABLE_SMU_METRICS, 0,
(void *)smu_table->metrics_table, false);
if (ret) {
@@ -1386,6 +1386,7 @@ static int navi10_read_sensor(struct smu_context *smu,
if(!data || !size)
return -EINVAL;
+ mutex_lock(&smu->sensor_lock);
switch (sensor) {
case AMDGPU_PP_SENSOR_MAX_FAN_RPM:
*(uint32_t *)data = pptable->FanMaximumRpm;
@@ -1409,6 +1410,7 @@ static int navi10_read_sensor(struct smu_context *smu,
default:
ret = smu_smc_read_sensor(smu, sensor, data, size);
}
+ mutex_unlock(&smu->sensor_lock);
return ret;
}
diff --git a/drivers/gpu/drm/amd/powerplay/vega20_ppt.c b/drivers/gpu/drm/amd/powerplay/vega20_ppt.c
index 64386ee..bbd8ebd5 100644
--- a/drivers/gpu/drm/amd/powerplay/vega20_ppt.c
+++ b/drivers/gpu/drm/amd/powerplay/vega20_ppt.c
@@ -3023,6 +3023,7 @@ static int vega20_read_sensor(struct smu_context *smu,
if(!data || !size)
return -EINVAL;
+ mutex_lock(&smu->sensor_lock);
switch (sensor) {
case AMDGPU_PP_SENSOR_MAX_FAN_RPM:
*(uint32_t *)data = pptable->FanMaximumRpm;
@@ -3048,6 +3049,7 @@ static int vega20_read_sensor(struct smu_context *smu,
default:
ret = smu_smc_read_sensor(smu, sensor, data, size);
}
+ mutex_unlock(&smu->sensor_lock);
return ret;
}
diff --git a/drivers/gpu/drm/arm/display/komeda/komeda_wb_connector.c b/drivers/gpu/drm/arm/display/komeda/komeda_wb_connector.c
index 2851cac..b72840c 100644
--- a/drivers/gpu/drm/arm/display/komeda/komeda_wb_connector.c
+++ b/drivers/gpu/drm/arm/display/komeda/komeda_wb_connector.c
@@ -43,9 +43,8 @@ komeda_wb_encoder_atomic_check(struct drm_encoder *encoder,
struct komeda_data_flow_cfg dflow;
int err;
- if (!writeback_job || !writeback_job->fb) {
+ if (!writeback_job)
return 0;
- }
if (!crtc_st->active) {
DRM_DEBUG_ATOMIC("Cannot write the composition result out on a inactive CRTC.\n");
@@ -166,8 +165,10 @@ static int komeda_wb_connector_add(struct komeda_kms_dev *kms,
&komeda_wb_encoder_helper_funcs,
formats, n_formats);
komeda_put_fourcc_list(formats);
- if (err)
+ if (err) {
+ kfree(kwb_conn);
return err;
+ }
drm_connector_helper_add(&wb_conn->base, &komeda_wb_conn_helper_funcs);
diff --git a/drivers/gpu/drm/arm/malidp_mw.c b/drivers/gpu/drm/arm/malidp_mw.c
index 22c0847..875a3a9 100644
--- a/drivers/gpu/drm/arm/malidp_mw.c
+++ b/drivers/gpu/drm/arm/malidp_mw.c
@@ -131,7 +131,7 @@ malidp_mw_encoder_atomic_check(struct drm_encoder *encoder,
struct drm_framebuffer *fb;
int i, n_planes;
- if (!conn_state->writeback_job || !conn_state->writeback_job->fb)
+ if (!conn_state->writeback_job)
return 0;
fb = conn_state->writeback_job->fb;
@@ -248,7 +248,7 @@ void malidp_mw_atomic_commit(struct drm_device *drm,
mw_state = to_mw_state(conn_state);
- if (conn_state->writeback_job && conn_state->writeback_job->fb) {
+ if (conn_state->writeback_job) {
struct drm_framebuffer *fb = conn_state->writeback_job->fb;
DRM_DEV_DEBUG_DRIVER(drm->dev,
diff --git a/drivers/gpu/drm/drm_atomic.c b/drivers/gpu/drm/drm_atomic.c
index 419381a..14aeaf7 100644
--- a/drivers/gpu/drm/drm_atomic.c
+++ b/drivers/gpu/drm/drm_atomic.c
@@ -430,10 +430,15 @@ static int drm_atomic_connector_check(struct drm_connector *connector,
return -EINVAL;
}
- if (writeback_job->out_fence && !writeback_job->fb) {
- DRM_DEBUG_ATOMIC("[CONNECTOR:%d:%s] requesting out-fence without framebuffer\n",
- connector->base.id, connector->name);
- return -EINVAL;
+ if (!writeback_job->fb) {
+ if (writeback_job->out_fence) {
+ DRM_DEBUG_ATOMIC("[CONNECTOR:%d:%s] requesting out-fence without framebuffer\n",
+ connector->base.id, connector->name);
+ return -EINVAL;
+ }
+
+ drm_writeback_cleanup_job(writeback_job);
+ state->writeback_job = NULL;
}
return 0;
diff --git a/drivers/gpu/drm/drm_writeback.c b/drivers/gpu/drm/drm_writeback.c
index ff138b6..43d9e3b 100644
--- a/drivers/gpu/drm/drm_writeback.c
+++ b/drivers/gpu/drm/drm_writeback.c
@@ -324,6 +324,9 @@ void drm_writeback_cleanup_job(struct drm_writeback_job *job)
if (job->fb)
drm_framebuffer_put(job->fb);
+ if (job->out_fence)
+ dma_fence_put(job->out_fence);
+
kfree(job);
}
EXPORT_SYMBOL(drm_writeback_cleanup_job);
@@ -366,25 +369,29 @@ drm_writeback_signal_completion(struct drm_writeback_connector *wb_connector,
{
unsigned long flags;
struct drm_writeback_job *job;
+ struct dma_fence *out_fence;
spin_lock_irqsave(&wb_connector->job_lock, flags);
job = list_first_entry_or_null(&wb_connector->job_queue,
struct drm_writeback_job,
list_entry);
- if (job) {
+ if (job)
list_del(&job->list_entry);
- if (job->out_fence) {
- if (status)
- dma_fence_set_error(job->out_fence, status);
- dma_fence_signal(job->out_fence);
- dma_fence_put(job->out_fence);
- }
- }
+
spin_unlock_irqrestore(&wb_connector->job_lock, flags);
if (WARN_ON(!job))
return;
+ out_fence = job->out_fence;
+ if (out_fence) {
+ if (status)
+ dma_fence_set_error(out_fence, status);
+ dma_fence_signal(out_fence);
+ dma_fence_put(out_fence);
+ job->out_fence = NULL;
+ }
+
INIT_WORK(&job->cleanup_work, cleanup_work);
queue_work(system_long_wq, &job->cleanup_work);
}
diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index b51d1ce..ce05e80 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -7261,7 +7261,7 @@ static int ironlake_fdi_compute_config(struct intel_crtc *intel_crtc,
pipe_config->fdi_lanes = lane;
intel_link_compute_m_n(pipe_config->pipe_bpp, lane, fdi_dotclock,
- link_bw, &pipe_config->fdi_m_n, false);
+ link_bw, &pipe_config->fdi_m_n, false, false);
ret = ironlake_check_fdi_lanes(dev, intel_crtc->pipe, pipe_config);
if (ret == -EDEADLK)
@@ -7508,11 +7508,15 @@ void
intel_link_compute_m_n(u16 bits_per_pixel, int nlanes,
int pixel_clock, int link_clock,
struct intel_link_m_n *m_n,
- bool constant_n)
+ bool constant_n, bool fec_enable)
{
- m_n->tu = 64;
+ u32 data_clock = bits_per_pixel * pixel_clock;
- compute_m_n(bits_per_pixel * pixel_clock,
+ if (fec_enable)
+ data_clock = intel_dp_mode_to_fec_clock(data_clock);
+
+ m_n->tu = 64;
+ compute_m_n(data_clock,
link_clock * nlanes * 8,
&m_n->gmch_m, &m_n->gmch_n,
constant_n);
diff --git a/drivers/gpu/drm/i915/display/intel_display.h b/drivers/gpu/drm/i915/display/intel_display.h
index e57e696..01fa87a 100644
--- a/drivers/gpu/drm/i915/display/intel_display.h
+++ b/drivers/gpu/drm/i915/display/intel_display.h
@@ -414,7 +414,7 @@ enum phy_fia {
void intel_link_compute_m_n(u16 bpp, int nlanes,
int pixel_clock, int link_clock,
struct intel_link_m_n *m_n,
- bool constant_n);
+ bool constant_n, bool fec_enable);
bool is_ccs_modifier(u64 modifier);
void lpt_disable_clkout_dp(struct drm_i915_private *dev_priv);
u32 intel_plane_fb_max_stride(struct drm_i915_private *dev_priv,
diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c
index 921ad0a..57e9f0b 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.c
+++ b/drivers/gpu/drm/i915/display/intel_dp.c
@@ -78,8 +78,8 @@
#define DP_DSC_MAX_ENC_THROUGHPUT_0 340000
#define DP_DSC_MAX_ENC_THROUGHPUT_1 400000
-/* DP DSC FEC Overhead factor = (100 - 2.4)/100 */
-#define DP_DSC_FEC_OVERHEAD_FACTOR 976
+/* DP DSC FEC Overhead factor = 1/(0.972261) */
+#define DP_DSC_FEC_OVERHEAD_FACTOR 972261
/* Compliance test status bits */
#define INTEL_DP_RESOLUTION_SHIFT_MASK 0
@@ -494,6 +494,97 @@ int intel_dp_get_link_train_fallback_values(struct intel_dp *intel_dp,
return 0;
}
+u32 intel_dp_mode_to_fec_clock(u32 mode_clock)
+{
+ return div_u64(mul_u32_u32(mode_clock, 1000000U),
+ DP_DSC_FEC_OVERHEAD_FACTOR);
+}
+
+static u16 intel_dp_dsc_get_output_bpp(u32 link_clock, u32 lane_count,
+ u32 mode_clock, u32 mode_hdisplay)
+{
+ u32 bits_per_pixel, max_bpp_small_joiner_ram;
+ int i;
+
+ /*
+ * Available Link Bandwidth(Kbits/sec) = (NumberOfLanes)*
+ * (LinkSymbolClock)* 8 * (TimeSlotsPerMTP)
+ * for SST -> TimeSlotsPerMTP is 1,
+ * for MST -> TimeSlotsPerMTP has to be calculated
+ */
+ bits_per_pixel = (link_clock * lane_count * 8) /
+ intel_dp_mode_to_fec_clock(mode_clock);
+ DRM_DEBUG_KMS("Max link bpp: %u\n", bits_per_pixel);
+
+ /* Small Joiner Check: output bpp <= joiner RAM (bits) / Horiz. width */
+ max_bpp_small_joiner_ram = DP_DSC_MAX_SMALL_JOINER_RAM_BUFFER / mode_hdisplay;
+ DRM_DEBUG_KMS("Max small joiner bpp: %u\n", max_bpp_small_joiner_ram);
+
+ /*
+ * Greatest allowed DSC BPP = MIN (output BPP from available Link BW
+ * check, output bpp from small joiner RAM check)
+ */
+ bits_per_pixel = min(bits_per_pixel, max_bpp_small_joiner_ram);
+
+ /* Error out if the max bpp is less than smallest allowed valid bpp */
+ if (bits_per_pixel < valid_dsc_bpp[0]) {
+ DRM_DEBUG_KMS("Unsupported BPP %u, min %u\n",
+ bits_per_pixel, valid_dsc_bpp[0]);
+ return 0;
+ }
+
+ /* Find the nearest match in the array of known BPPs from VESA */
+ for (i = 0; i < ARRAY_SIZE(valid_dsc_bpp) - 1; i++) {
+ if (bits_per_pixel < valid_dsc_bpp[i + 1])
+ break;
+ }
+ bits_per_pixel = valid_dsc_bpp[i];
+
+ /*
+ * Compressed BPP in U6.4 format so multiply by 16, for Gen 11,
+ * fractional part is 0
+ */
+ return bits_per_pixel << 4;
+}
+
+static u8 intel_dp_dsc_get_slice_count(struct intel_dp *intel_dp,
+ int mode_clock, int mode_hdisplay)
+{
+ u8 min_slice_count, i;
+ int max_slice_width;
+
+ if (mode_clock <= DP_DSC_PEAK_PIXEL_RATE)
+ min_slice_count = DIV_ROUND_UP(mode_clock,
+ DP_DSC_MAX_ENC_THROUGHPUT_0);
+ else
+ min_slice_count = DIV_ROUND_UP(mode_clock,
+ DP_DSC_MAX_ENC_THROUGHPUT_1);
+
+ max_slice_width = drm_dp_dsc_sink_max_slice_width(intel_dp->dsc_dpcd);
+ if (max_slice_width < DP_DSC_MIN_SLICE_WIDTH_VALUE) {
+ DRM_DEBUG_KMS("Unsupported slice width %d by DP DSC Sink device\n",
+ max_slice_width);
+ return 0;
+ }
+ /* Also take into account max slice width */
+ min_slice_count = min_t(u8, min_slice_count,
+ DIV_ROUND_UP(mode_hdisplay,
+ max_slice_width));
+
+ /* Find the closest match to the valid slice count values */
+ for (i = 0; i < ARRAY_SIZE(valid_dsc_slicecount); i++) {
+ if (valid_dsc_slicecount[i] >
+ drm_dp_dsc_sink_max_slice_count(intel_dp->dsc_dpcd,
+ false))
+ break;
+ if (min_slice_count <= valid_dsc_slicecount[i])
+ return valid_dsc_slicecount[i];
+ }
+
+ DRM_DEBUG_KMS("Unsupported Slice Count %d\n", min_slice_count);
+ return 0;
+}
+
static enum drm_mode_status
intel_dp_mode_valid(struct drm_connector *connector,
struct drm_display_mode *mode)
@@ -2226,7 +2317,7 @@ intel_dp_compute_config(struct intel_encoder *encoder,
adjusted_mode->crtc_clock,
pipe_config->port_clock,
&pipe_config->dp_m_n,
- constant_n);
+ constant_n, pipe_config->fec_enable);
if (intel_connector->panel.downclock_mode != NULL &&
dev_priv->drrs.type == SEAMLESS_DRRS_SUPPORT) {
@@ -2236,7 +2327,7 @@ intel_dp_compute_config(struct intel_encoder *encoder,
intel_connector->panel.downclock_mode->clock,
pipe_config->port_clock,
&pipe_config->dp_m2_n2,
- constant_n);
+ constant_n, pipe_config->fec_enable);
}
if (!HAS_DDI(dev_priv))
@@ -4323,91 +4414,6 @@ intel_dp_get_sink_irq_esi(struct intel_dp *intel_dp, u8 *sink_irq_vector)
DP_DPRX_ESI_LEN;
}
-u16 intel_dp_dsc_get_output_bpp(int link_clock, u8 lane_count,
- int mode_clock, int mode_hdisplay)
-{
- u16 bits_per_pixel, max_bpp_small_joiner_ram;
- int i;
-
- /*
- * Available Link Bandwidth(Kbits/sec) = (NumberOfLanes)*
- * (LinkSymbolClock)* 8 * ((100-FECOverhead)/100)*(TimeSlotsPerMTP)
- * FECOverhead = 2.4%, for SST -> TimeSlotsPerMTP is 1,
- * for MST -> TimeSlotsPerMTP has to be calculated
- */
- bits_per_pixel = (link_clock * lane_count * 8 *
- DP_DSC_FEC_OVERHEAD_FACTOR) /
- mode_clock;
-
- /* Small Joiner Check: output bpp <= joiner RAM (bits) / Horiz. width */
- max_bpp_small_joiner_ram = DP_DSC_MAX_SMALL_JOINER_RAM_BUFFER /
- mode_hdisplay;
-
- /*
- * Greatest allowed DSC BPP = MIN (output BPP from avaialble Link BW
- * check, output bpp from small joiner RAM check)
- */
- bits_per_pixel = min(bits_per_pixel, max_bpp_small_joiner_ram);
-
- /* Error out if the max bpp is less than smallest allowed valid bpp */
- if (bits_per_pixel < valid_dsc_bpp[0]) {
- DRM_DEBUG_KMS("Unsupported BPP %d\n", bits_per_pixel);
- return 0;
- }
-
- /* Find the nearest match in the array of known BPPs from VESA */
- for (i = 0; i < ARRAY_SIZE(valid_dsc_bpp) - 1; i++) {
- if (bits_per_pixel < valid_dsc_bpp[i + 1])
- break;
- }
- bits_per_pixel = valid_dsc_bpp[i];
-
- /*
- * Compressed BPP in U6.4 format so multiply by 16, for Gen 11,
- * fractional part is 0
- */
- return bits_per_pixel << 4;
-}
-
-u8 intel_dp_dsc_get_slice_count(struct intel_dp *intel_dp,
- int mode_clock,
- int mode_hdisplay)
-{
- u8 min_slice_count, i;
- int max_slice_width;
-
- if (mode_clock <= DP_DSC_PEAK_PIXEL_RATE)
- min_slice_count = DIV_ROUND_UP(mode_clock,
- DP_DSC_MAX_ENC_THROUGHPUT_0);
- else
- min_slice_count = DIV_ROUND_UP(mode_clock,
- DP_DSC_MAX_ENC_THROUGHPUT_1);
-
- max_slice_width = drm_dp_dsc_sink_max_slice_width(intel_dp->dsc_dpcd);
- if (max_slice_width < DP_DSC_MIN_SLICE_WIDTH_VALUE) {
- DRM_DEBUG_KMS("Unsupported slice width %d by DP DSC Sink device\n",
- max_slice_width);
- return 0;
- }
- /* Also take into account max slice width */
- min_slice_count = min_t(u8, min_slice_count,
- DIV_ROUND_UP(mode_hdisplay,
- max_slice_width));
-
- /* Find the closest match to the valid slice count values */
- for (i = 0; i < ARRAY_SIZE(valid_dsc_slicecount); i++) {
- if (valid_dsc_slicecount[i] >
- drm_dp_dsc_sink_max_slice_count(intel_dp->dsc_dpcd,
- false))
- break;
- if (min_slice_count <= valid_dsc_slicecount[i])
- return valid_dsc_slicecount[i];
- }
-
- DRM_DEBUG_KMS("Unsupported Slice Count %d\n", min_slice_count);
- return 0;
-}
-
static void
intel_pixel_encoding_setup_vsc(struct intel_dp *intel_dp,
const struct intel_crtc_state *crtc_state)
diff --git a/drivers/gpu/drm/i915/display/intel_dp.h b/drivers/gpu/drm/i915/display/intel_dp.h
index 657bbb1..00981fb 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.h
+++ b/drivers/gpu/drm/i915/display/intel_dp.h
@@ -102,10 +102,6 @@ bool intel_dp_source_supports_hbr2(struct intel_dp *intel_dp);
bool intel_dp_source_supports_hbr3(struct intel_dp *intel_dp);
bool
intel_dp_get_link_status(struct intel_dp *intel_dp, u8 *link_status);
-u16 intel_dp_dsc_get_output_bpp(int link_clock, u8 lane_count,
- int mode_clock, int mode_hdisplay);
-u8 intel_dp_dsc_get_slice_count(struct intel_dp *intel_dp, int mode_clock,
- int mode_hdisplay);
bool intel_dp_read_dpcd(struct intel_dp *intel_dp);
bool intel_dp_get_colorimetry_status(struct intel_dp *intel_dp);
@@ -118,4 +114,6 @@ static inline unsigned int intel_dp_unused_lane_mask(int lane_count)
return ~((1 << lane_count) - 1) & 0xf;
}
+u32 intel_dp_mode_to_fec_clock(u32 mode_clock);
+
#endif /* __INTEL_DP_H__ */
diff --git a/drivers/gpu/drm/i915/display/intel_dp_mst.c b/drivers/gpu/drm/i915/display/intel_dp_mst.c
index 6df240a..600873c 100644
--- a/drivers/gpu/drm/i915/display/intel_dp_mst.c
+++ b/drivers/gpu/drm/i915/display/intel_dp_mst.c
@@ -81,7 +81,7 @@ static int intel_dp_mst_compute_link_config(struct intel_encoder *encoder,
adjusted_mode->crtc_clock,
crtc_state->port_clock,
&crtc_state->dp_m_n,
- constant_n);
+ constant_n, crtc_state->fec_enable);
crtc_state->dp_m_n.tu = slots;
return 0;
@@ -615,7 +615,7 @@ intel_dp_create_fake_mst_encoder(struct intel_digital_port *intel_dig_port, enum
intel_encoder->type = INTEL_OUTPUT_DP_MST;
intel_encoder->power_domain = intel_dig_port->base.power_domain;
intel_encoder->port = intel_dig_port->base.port;
- intel_encoder->crtc_mask = BIT(pipe);
+ intel_encoder->crtc_mask = 0x7;
intel_encoder->cloneable = 0;
intel_encoder->compute_config = intel_dp_mst_compute_config;
diff --git a/drivers/gpu/drm/i915/display/intel_sprite.c b/drivers/gpu/drm/i915/display/intel_sprite.c
index dea63be..cae25e4 100644
--- a/drivers/gpu/drm/i915/display/intel_sprite.c
+++ b/drivers/gpu/drm/i915/display/intel_sprite.c
@@ -1528,6 +1528,7 @@ g4x_sprite_check_scaling(struct intel_crtc_state *crtc_state,
int src_x, src_w, src_h, crtc_w, crtc_h;
const struct drm_display_mode *adjusted_mode =
&crtc_state->base.adjusted_mode;
+ unsigned int stride = plane_state->color_plane[0].stride;
unsigned int cpp = fb->format->cpp[0];
unsigned int width_bytes;
int min_width, min_height;
@@ -1569,9 +1570,9 @@ g4x_sprite_check_scaling(struct intel_crtc_state *crtc_state,
return -EINVAL;
}
- if (width_bytes > 4096 || fb->pitches[0] > 4096) {
+ if (stride > 4096) {
DRM_DEBUG_KMS("Stride (%u) exceeds hardware max with scaling (%u)\n",
- fb->pitches[0], 4096);
+ stride, 4096);
return -EINVAL;
}
diff --git a/drivers/gpu/drm/omapdrm/dss/dss.c b/drivers/gpu/drm/omapdrm/dss/dss.c
index e226324..4bdd63b 100644
--- a/drivers/gpu/drm/omapdrm/dss/dss.c
+++ b/drivers/gpu/drm/omapdrm/dss/dss.c
@@ -1083,7 +1083,7 @@ static const struct dss_features omap34xx_dss_feats = {
static const struct dss_features omap3630_dss_feats = {
.model = DSS_MODEL_OMAP3,
- .fck_div_max = 32,
+ .fck_div_max = 31,
.fck_freq_max = 173000000,
.dss_fck_multiplier = 1,
.parent_clk_name = "dpll4_ck",
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_writeback.c b/drivers/gpu/drm/rcar-du/rcar_du_writeback.c
index ae07290..04efa78d 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_writeback.c
+++ b/drivers/gpu/drm/rcar-du/rcar_du_writeback.c
@@ -147,7 +147,7 @@ static int rcar_du_wb_enc_atomic_check(struct drm_encoder *encoder,
struct drm_device *dev = encoder->dev;
struct drm_framebuffer *fb;
- if (!conn_state->writeback_job || !conn_state->writeback_job->fb)
+ if (!conn_state->writeback_job)
return 0;
fb = conn_state->writeback_job->fb;
@@ -221,7 +221,7 @@ void rcar_du_writeback_setup(struct rcar_du_crtc *rcrtc,
unsigned int i;
state = rcrtc->writeback.base.state;
- if (!state || !state->writeback_job || !state->writeback_job->fb)
+ if (!state || !state->writeback_job)
return;
fb = state->writeback_job->fb;
diff --git a/drivers/gpu/drm/tilcdc/tilcdc_tfp410.c b/drivers/gpu/drm/tilcdc/tilcdc_tfp410.c
index 525dc1c..530edb3 100644
--- a/drivers/gpu/drm/tilcdc/tilcdc_tfp410.c
+++ b/drivers/gpu/drm/tilcdc/tilcdc_tfp410.c
@@ -7,6 +7,7 @@
#include <linux/gpio.h>
#include <linux/mod_devicetable.h>
#include <linux/of_gpio.h>
+#include <linux/pinctrl/consumer.h>
#include <linux/platform_device.h>
#include <drm/drm_atomic_helper.h>
diff --git a/drivers/gpu/drm/vc4/vc4_txp.c b/drivers/gpu/drm/vc4/vc4_txp.c
index 1ce4d71..bf72020 100644
--- a/drivers/gpu/drm/vc4/vc4_txp.c
+++ b/drivers/gpu/drm/vc4/vc4_txp.c
@@ -231,7 +231,7 @@ static int vc4_txp_connector_atomic_check(struct drm_connector *conn,
int i;
conn_state = drm_atomic_get_new_connector_state(state, conn);
- if (!conn_state->writeback_job || !conn_state->writeback_job->fb)
+ if (!conn_state->writeback_job)
return 0;
crtc_state = drm_atomic_get_new_crtc_state(state, conn_state->crtc);
@@ -271,8 +271,7 @@ static void vc4_txp_connector_atomic_commit(struct drm_connector *conn,
u32 ctrl;
int i;
- if (WARN_ON(!conn_state->writeback_job ||
- !conn_state->writeback_job->fb))
+ if (WARN_ON(!conn_state->writeback_job))
return;
mode = &conn_state->crtc->state->adjusted_mode;
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 108f60b..fd7dea3 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -102,10 +102,13 @@ static void nvme_set_queue_dying(struct nvme_ns *ns)
*/
if (!ns->disk || test_and_set_bit(NVME_NS_DEAD, &ns->flags))
return;
- revalidate_disk(ns->disk);
blk_set_queue_dying(ns->queue);
/* Forcibly unquiesce queues to avoid blocking dispatch */
blk_mq_unquiesce_queue(ns->queue);
+ /*
+ * Revalidate after unblocking dispatchers that may be holding bd_butex
+ */
+ revalidate_disk(ns->disk);
}
static void nvme_queue_scan(struct nvme_ctrl *ctrl)
@@ -847,7 +850,7 @@ static void *nvme_add_user_metadata(struct bio *bio, void __user *ubuf,
static int nvme_submit_user_cmd(struct request_queue *q,
struct nvme_command *cmd, void __user *ubuffer,
unsigned bufflen, void __user *meta_buffer, unsigned meta_len,
- u32 meta_seed, u32 *result, unsigned timeout)
+ u32 meta_seed, u64 *result, unsigned timeout)
{
bool write = nvme_is_write(cmd);
struct nvme_ns *ns = q->queuedata;
@@ -888,7 +891,7 @@ static int nvme_submit_user_cmd(struct request_queue *q,
else
ret = nvme_req(req)->status;
if (result)
- *result = le32_to_cpu(nvme_req(req)->result.u32);
+ *result = le64_to_cpu(nvme_req(req)->result.u64);
if (meta && !ret && !write) {
if (copy_to_user(meta_buffer, meta, meta_len))
ret = -EFAULT;
@@ -1335,6 +1338,54 @@ static int nvme_user_cmd(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
struct nvme_command c;
unsigned timeout = 0;
u32 effects;
+ u64 result;
+ int status;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EACCES;
+ if (copy_from_user(&cmd, ucmd, sizeof(cmd)))
+ return -EFAULT;
+ if (cmd.flags)
+ return -EINVAL;
+
+ memset(&c, 0, sizeof(c));
+ c.common.opcode = cmd.opcode;
+ c.common.flags = cmd.flags;
+ c.common.nsid = cpu_to_le32(cmd.nsid);
+ c.common.cdw2[0] = cpu_to_le32(cmd.cdw2);
+ c.common.cdw2[1] = cpu_to_le32(cmd.cdw3);
+ c.common.cdw10 = cpu_to_le32(cmd.cdw10);
+ c.common.cdw11 = cpu_to_le32(cmd.cdw11);
+ c.common.cdw12 = cpu_to_le32(cmd.cdw12);
+ c.common.cdw13 = cpu_to_le32(cmd.cdw13);
+ c.common.cdw14 = cpu_to_le32(cmd.cdw14);
+ c.common.cdw15 = cpu_to_le32(cmd.cdw15);
+
+ if (cmd.timeout_ms)
+ timeout = msecs_to_jiffies(cmd.timeout_ms);
+
+ effects = nvme_passthru_start(ctrl, ns, cmd.opcode);
+ status = nvme_submit_user_cmd(ns ? ns->queue : ctrl->admin_q, &c,
+ (void __user *)(uintptr_t)cmd.addr, cmd.data_len,
+ (void __user *)(uintptr_t)cmd.metadata,
+ cmd.metadata_len, 0, &result, timeout);
+ nvme_passthru_end(ctrl, effects);
+
+ if (status >= 0) {
+ if (put_user(result, &ucmd->result))
+ return -EFAULT;
+ }
+
+ return status;
+}
+
+static int nvme_user_cmd64(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
+ struct nvme_passthru_cmd64 __user *ucmd)
+{
+ struct nvme_passthru_cmd64 cmd;
+ struct nvme_command c;
+ unsigned timeout = 0;
+ u32 effects;
int status;
if (!capable(CAP_SYS_ADMIN))
@@ -1405,6 +1456,41 @@ static void nvme_put_ns_from_disk(struct nvme_ns_head *head, int idx)
srcu_read_unlock(&head->srcu, idx);
}
+static bool is_ctrl_ioctl(unsigned int cmd)
+{
+ if (cmd == NVME_IOCTL_ADMIN_CMD || cmd == NVME_IOCTL_ADMIN64_CMD)
+ return true;
+ if (is_sed_ioctl(cmd))
+ return true;
+ return false;
+}
+
+static int nvme_handle_ctrl_ioctl(struct nvme_ns *ns, unsigned int cmd,
+ void __user *argp,
+ struct nvme_ns_head *head,
+ int srcu_idx)
+{
+ struct nvme_ctrl *ctrl = ns->ctrl;
+ int ret;
+
+ nvme_get_ctrl(ns->ctrl);
+ nvme_put_ns_from_disk(head, srcu_idx);
+
+ switch (cmd) {
+ case NVME_IOCTL_ADMIN_CMD:
+ ret = nvme_user_cmd(ctrl, NULL, argp);
+ break;
+ case NVME_IOCTL_ADMIN64_CMD:
+ ret = nvme_user_cmd64(ctrl, NULL, argp);
+ break;
+ default:
+ ret = sed_ioctl(ctrl->opal_dev, cmd, argp);
+ break;
+ }
+ nvme_put_ctrl(ctrl);
+ return ret;
+}
+
static int nvme_ioctl(struct block_device *bdev, fmode_t mode,
unsigned int cmd, unsigned long arg)
{
@@ -1422,20 +1508,8 @@ static int nvme_ioctl(struct block_device *bdev, fmode_t mode,
* seperately and drop the ns SRCU reference early. This avoids a
* deadlock when deleting namespaces using the passthrough interface.
*/
- if (cmd == NVME_IOCTL_ADMIN_CMD || is_sed_ioctl(cmd)) {
- struct nvme_ctrl *ctrl = ns->ctrl;
-
- nvme_get_ctrl(ns->ctrl);
- nvme_put_ns_from_disk(head, srcu_idx);
-
- if (cmd == NVME_IOCTL_ADMIN_CMD)
- ret = nvme_user_cmd(ctrl, NULL, argp);
- else
- ret = sed_ioctl(ctrl->opal_dev, cmd, argp);
-
- nvme_put_ctrl(ctrl);
- return ret;
- }
+ if (is_ctrl_ioctl(cmd))
+ return nvme_handle_ctrl_ioctl(ns, cmd, argp, head, srcu_idx);
switch (cmd) {
case NVME_IOCTL_ID:
@@ -1448,6 +1522,9 @@ static int nvme_ioctl(struct block_device *bdev, fmode_t mode,
case NVME_IOCTL_SUBMIT_IO:
ret = nvme_submit_io(ns, argp);
break;
+ case NVME_IOCTL_IO64_CMD:
+ ret = nvme_user_cmd64(ns->ctrl, ns, argp);
+ break;
default:
if (ns->ndev)
ret = nvme_nvm_ioctl(ns, cmd, arg);
@@ -2289,6 +2366,16 @@ static const struct nvme_core_quirk_entry core_quirks[] = {
.vid = 0x14a4,
.fr = "22301111",
.quirks = NVME_QUIRK_SIMPLE_SUSPEND,
+ },
+ {
+ /*
+ * This Kingston E8FK11.T firmware version has no interrupt
+ * after resume with actions related to suspend to idle
+ * https://bugzilla.kernel.org/show_bug.cgi?id=204887
+ */
+ .vid = 0x2646,
+ .fr = "E8FK11.T",
+ .quirks = NVME_QUIRK_SIMPLE_SUSPEND,
}
};
@@ -2540,8 +2627,9 @@ static int nvme_init_subsystem(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id)
list_add_tail(&subsys->entry, &nvme_subsystems);
}
- if (sysfs_create_link(&subsys->dev.kobj, &ctrl->device->kobj,
- dev_name(ctrl->device))) {
+ ret = sysfs_create_link(&subsys->dev.kobj, &ctrl->device->kobj,
+ dev_name(ctrl->device));
+ if (ret) {
dev_err(ctrl->device,
"failed to create sysfs link from subsystem.\n");
goto out_put_subsystem;
@@ -2838,6 +2926,8 @@ static long nvme_dev_ioctl(struct file *file, unsigned int cmd,
switch (cmd) {
case NVME_IOCTL_ADMIN_CMD:
return nvme_user_cmd(ctrl, NULL, argp);
+ case NVME_IOCTL_ADMIN64_CMD:
+ return nvme_user_cmd64(ctrl, NULL, argp);
case NVME_IOCTL_IO_CMD:
return nvme_dev_user_cmd(ctrl, argp);
case NVME_IOCTL_RESET:
@@ -3045,6 +3135,8 @@ static DEVICE_ATTR(field, S_IRUGO, field##_show, NULL);
nvme_show_int_function(cntlid);
nvme_show_int_function(numa_node);
+nvme_show_int_function(queue_count);
+nvme_show_int_function(sqsize);
static ssize_t nvme_sysfs_delete(struct device *dev,
struct device_attribute *attr, const char *buf,
@@ -3125,6 +3217,8 @@ static struct attribute *nvme_dev_attrs[] = {
&dev_attr_address.attr,
&dev_attr_state.attr,
&dev_attr_numa_node.attr,
+ &dev_attr_queue_count.attr,
+ &dev_attr_sqsize.attr,
NULL
};
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index b5013c1..38a83ef 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -221,6 +221,7 @@ struct nvme_ctrl {
u16 oacs;
u16 nssa;
u16 nr_streams;
+ u16 sqsize;
u32 max_namespaces;
atomic_t abort_limit;
u8 vwc;
@@ -269,7 +270,6 @@ struct nvme_ctrl {
u16 hmmaxd;
/* Fabrics only */
- u16 sqsize;
u32 ioccsz;
u32 iorcsz;
u16 icdoff;
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index c0808f9..bb88681 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -2946,11 +2946,21 @@ static int nvme_suspend(struct device *dev)
if (ret < 0)
goto unfreeze;
+ /*
+ * A saved state prevents pci pm from generically controlling the
+ * device's power. If we're using protocol specific settings, we don't
+ * want pci interfering.
+ */
+ pci_save_state(pdev);
+
ret = nvme_set_power_state(ctrl, ctrl->npss);
if (ret < 0)
goto unfreeze;
if (ret) {
+ /* discard the saved state */
+ pci_load_saved_state(pdev, NULL);
+
/*
* Clearing npss forces a controller reset on resume. The
* correct value will be resdicovered then.
@@ -2958,14 +2968,7 @@ static int nvme_suspend(struct device *dev)
nvme_dev_disable(ndev, true);
ctrl->npss = 0;
ret = 0;
- goto unfreeze;
}
- /*
- * A saved state prevents pci pm from generically controlling the
- * device's power. If we're using protocol specific settings, we don't
- * want pci interfering.
- */
- pci_save_state(pdev);
unfreeze:
nvme_unfreeze(ctrl);
return ret;
@@ -3090,6 +3093,9 @@ static const struct pci_device_id nvme_id_table[] = {
.driver_data = NVME_QUIRK_LIGHTNVM, },
{ PCI_DEVICE(0x10ec, 0x5762), /* ADATA SX6000LNP */
.driver_data = NVME_QUIRK_IGNORE_DEV_SUBNQN, },
+ { PCI_DEVICE(0x1cc1, 0x8201), /* ADATA SX8200PNP 512GB */
+ .driver_data = NVME_QUIRK_NO_DEEPEST_PS |
+ NVME_QUIRK_IGNORE_DEV_SUBNQN, },
{ PCI_DEVICE_CLASS(PCI_CLASS_STORAGE_EXPRESS, 0xffffff) },
{ PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2001) },
{ PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2003) },
diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index dfa07bb..4d28016 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -427,7 +427,7 @@ static void nvme_rdma_destroy_queue_ib(struct nvme_rdma_queue *queue)
static int nvme_rdma_get_max_fr_pages(struct ib_device *ibdev)
{
return min_t(u32, NVME_RDMA_MAX_SEGMENTS,
- ibdev->attrs.max_fast_reg_page_list_len);
+ ibdev->attrs.max_fast_reg_page_list_len - 1);
}
static int nvme_rdma_create_queue_ib(struct nvme_rdma_queue *queue)
@@ -437,7 +437,7 @@ static int nvme_rdma_create_queue_ib(struct nvme_rdma_queue *queue)
const int cq_factor = send_wr_factor + 1; /* + RECV */
int comp_vector, idx = nvme_rdma_queue_idx(queue);
enum ib_poll_context poll_ctx;
- int ret;
+ int ret, pages_per_mr;
queue->device = nvme_rdma_find_get_device(queue->cm_id);
if (!queue->device) {
@@ -479,10 +479,16 @@ static int nvme_rdma_create_queue_ib(struct nvme_rdma_queue *queue)
goto out_destroy_qp;
}
+ /*
+ * Currently we don't use SG_GAPS MR's so if the first entry is
+ * misaligned we'll end up using two entries for a single data page,
+ * so one additional entry is required.
+ */
+ pages_per_mr = nvme_rdma_get_max_fr_pages(ibdev) + 1;
ret = ib_mr_pool_init(queue->qp, &queue->qp->rdma_mrs,
queue->queue_size,
IB_MR_TYPE_MEM_REG,
- nvme_rdma_get_max_fr_pages(ibdev), 0);
+ pages_per_mr, 0);
if (ret) {
dev_err(queue->ctrl->ctrl.device,
"failed to initialize MR pool sized %d for QID %d\n",
@@ -614,7 +620,8 @@ static int nvme_rdma_start_queue(struct nvme_rdma_ctrl *ctrl, int idx)
if (!ret) {
set_bit(NVME_RDMA_Q_LIVE, &queue->flags);
} else {
- __nvme_rdma_stop_queue(queue);
+ if (test_bit(NVME_RDMA_Q_ALLOCATED, &queue->flags))
+ __nvme_rdma_stop_queue(queue);
dev_info(ctrl->ctrl.device,
"failed to connect queue: %d ret=%d\n", idx, ret);
}
@@ -820,8 +827,8 @@ static int nvme_rdma_configure_admin_queue(struct nvme_rdma_ctrl *ctrl,
if (error)
goto out_stop_queue;
- ctrl->ctrl.max_hw_sectors =
- (ctrl->max_fr_pages - 1) << (ilog2(SZ_4K) - 9);
+ ctrl->ctrl.max_segments = ctrl->max_fr_pages;
+ ctrl->ctrl.max_hw_sectors = ctrl->max_fr_pages << (ilog2(SZ_4K) - 9);
blk_mq_unquiesce_queue(ctrl->ctrl.admin_q);
diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index 4ffd595..385a521 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -1042,7 +1042,7 @@ static void nvme_tcp_io_work(struct work_struct *w)
{
struct nvme_tcp_queue *queue =
container_of(w, struct nvme_tcp_queue, io_work);
- unsigned long start = jiffies + msecs_to_jiffies(1);
+ unsigned long deadline = jiffies + msecs_to_jiffies(1);
do {
bool pending = false;
@@ -1067,7 +1067,7 @@ static void nvme_tcp_io_work(struct work_struct *w)
if (!pending)
return;
- } while (time_after(jiffies, start)); /* quota is exhausted */
+ } while (!time_after(jiffies, deadline)); /* quota is exhausted */
queue_work_on(queue->io_cpu, nvme_tcp_wq, &queue->io_work);
}
diff --git a/drivers/nvme/target/io-cmd-bdev.c b/drivers/nvme/target/io-cmd-bdev.c
index de0bff7..32008d8 100644
--- a/drivers/nvme/target/io-cmd-bdev.c
+++ b/drivers/nvme/target/io-cmd-bdev.c
@@ -11,10 +11,10 @@
void nvmet_bdev_set_limits(struct block_device *bdev, struct nvme_id_ns *id)
{
const struct queue_limits *ql = &bdev_get_queue(bdev)->limits;
- /* Number of physical blocks per logical block. */
- const u32 ppl = ql->physical_block_size / ql->logical_block_size;
- /* Physical blocks per logical block, 0's based. */
- const __le16 ppl0b = to0based(ppl);
+ /* Number of logical blocks per physical block. */
+ const u32 lpp = ql->physical_block_size / ql->logical_block_size;
+ /* Logical blocks per physical block, 0's based. */
+ const __le16 lpp0b = to0based(lpp);
/*
* For NVMe 1.2 and later, bit 1 indicates that the fields NAWUN,
@@ -25,9 +25,9 @@ void nvmet_bdev_set_limits(struct block_device *bdev, struct nvme_id_ns *id)
* field from the identify controller data structure should be used.
*/
id->nsfeat |= 1 << 1;
- id->nawun = ppl0b;
- id->nawupf = ppl0b;
- id->nacwu = ppl0b;
+ id->nawun = lpp0b;
+ id->nawupf = lpp0b;
+ id->nacwu = lpp0b;
/*
* Bit 4 indicates that the fields NPWG, NPWA, NPDG, NPDA, and
@@ -36,7 +36,7 @@ void nvmet_bdev_set_limits(struct block_device *bdev, struct nvme_id_ns *id)
*/
id->nsfeat |= 1 << 4;
/* NPWG = Namespace Preferred Write Granularity. 0's based */
- id->npwg = ppl0b;
+ id->npwg = lpp0b;
/* NPWA = Namespace Preferred Write Alignment. 0's based */
id->npwa = id->npwg;
/* NPDG = Namespace Preferred Deallocate Granularity. 0's based */
diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c
index bf4f034..d535080 100644
--- a/drivers/nvme/target/tcp.c
+++ b/drivers/nvme/target/tcp.c
@@ -348,8 +348,7 @@ static int nvmet_tcp_map_data(struct nvmet_tcp_cmd *cmd)
return 0;
err:
- if (cmd->req.sg_cnt)
- sgl_free(cmd->req.sg);
+ sgl_free(cmd->req.sg);
return NVME_SC_INTERNAL;
}
@@ -554,8 +553,7 @@ static int nvmet_try_send_data(struct nvmet_tcp_cmd *cmd)
if (queue->nvme_sq.sqhd_disabled) {
kfree(cmd->iov);
- if (cmd->req.sg_cnt)
- sgl_free(cmd->req.sg);
+ sgl_free(cmd->req.sg);
}
return 1;
@@ -586,8 +584,7 @@ static int nvmet_try_send_response(struct nvmet_tcp_cmd *cmd,
return -EAGAIN;
kfree(cmd->iov);
- if (cmd->req.sg_cnt)
- sgl_free(cmd->req.sg);
+ sgl_free(cmd->req.sg);
cmd->queue->snd_cmd = NULL;
nvmet_tcp_put_cmd(cmd);
return 1;
@@ -1310,8 +1307,7 @@ static void nvmet_tcp_finish_cmd(struct nvmet_tcp_cmd *cmd)
nvmet_req_uninit(&cmd->req);
nvmet_tcp_unmap_pdu_iovec(cmd);
kfree(cmd->iov);
- if (cmd->req.sg_cnt)
- sgl_free(cmd->req.sg);
+ sgl_free(cmd->req.sg);
}
static void nvmet_tcp_uninit_data_in_cmds(struct nvmet_tcp_queue *queue)
diff --git a/drivers/s390/block/dasd_eckd.c b/drivers/s390/block/dasd_eckd.c
index fc53e1e..c94184d 100644
--- a/drivers/s390/block/dasd_eckd.c
+++ b/drivers/s390/block/dasd_eckd.c
@@ -1553,8 +1553,8 @@ static int dasd_eckd_read_vol_info(struct dasd_device *device)
if (rc == 0) {
memcpy(&private->vsq, vsq, sizeof(*vsq));
} else {
- dev_warn(&device->cdev->dev,
- "Reading the volume storage information failed with rc=%d\n", rc);
+ DBF_EVENT_DEVID(DBF_WARNING, device->cdev,
+ "Reading the volume storage information failed with rc=%d", rc);
}
if (useglobal)
@@ -1737,8 +1737,8 @@ static int dasd_eckd_read_ext_pool_info(struct dasd_device *device)
if (rc == 0) {
dasd_eckd_cpy_ext_pool_data(device, lcq);
} else {
- dev_warn(&device->cdev->dev,
- "Reading the logical configuration failed with rc=%d\n", rc);
+ DBF_EVENT_DEVID(DBF_WARNING, device->cdev,
+ "Reading the logical configuration failed with rc=%d", rc);
}
dasd_sfree_request(cqr, cqr->memdev);
@@ -2020,14 +2020,10 @@ dasd_eckd_check_characteristics(struct dasd_device *device)
dasd_eckd_read_features(device);
/* Read Volume Information */
- rc = dasd_eckd_read_vol_info(device);
- if (rc)
- goto out_err3;
+ dasd_eckd_read_vol_info(device);
/* Read Extent Pool Information */
- rc = dasd_eckd_read_ext_pool_info(device);
- if (rc)
- goto out_err3;
+ dasd_eckd_read_ext_pool_info(device);
/* Read Device Characteristics */
rc = dasd_generic_read_dev_chars(device, DASD_ECKD_MAGIC,
@@ -2059,9 +2055,6 @@ dasd_eckd_check_characteristics(struct dasd_device *device)
if (readonly)
set_bit(DASD_FLAG_DEVICE_RO, &device->flags);
- if (dasd_eckd_is_ese(device))
- dasd_set_feature(device->cdev, DASD_FEATURE_DISCARD, 1);
-
dev_info(&device->cdev->dev, "New DASD %04X/%02X (CU %04X/%02X) "
"with %d cylinders, %d heads, %d sectors%s\n",
private->rdc_data.dev_type,
@@ -3695,14 +3688,6 @@ static int dasd_eckd_release_space(struct dasd_device *device,
return -EINVAL;
}
-static struct dasd_ccw_req *
-dasd_eckd_build_cp_discard(struct dasd_device *device, struct dasd_block *block,
- struct request *req, sector_t first_trk,
- sector_t last_trk)
-{
- return dasd_eckd_dso_ras(device, block, req, first_trk, last_trk, 1);
-}
-
static struct dasd_ccw_req *dasd_eckd_build_cp_cmd_single(
struct dasd_device *startdev,
struct dasd_block *block,
@@ -4447,10 +4432,6 @@ static struct dasd_ccw_req *dasd_eckd_build_cp(struct dasd_device *startdev,
cmdwtd = private->features.feature[12] & 0x40;
use_prefix = private->features.feature[8] & 0x01;
- if (req_op(req) == REQ_OP_DISCARD)
- return dasd_eckd_build_cp_discard(startdev, block, req,
- first_trk, last_trk);
-
cqr = NULL;
if (cdlspecial || dasd_page_cache) {
/* do nothing, just fall through to the cmd mode single case */
@@ -4729,14 +4710,12 @@ static struct dasd_ccw_req *dasd_eckd_build_alias_cp(struct dasd_device *base,
struct dasd_block *block,
struct request *req)
{
- struct dasd_device *startdev = NULL;
struct dasd_eckd_private *private;
- struct dasd_ccw_req *cqr;
+ struct dasd_device *startdev;
unsigned long flags;
+ struct dasd_ccw_req *cqr;
- /* Discard requests can only be processed on base devices */
- if (req_op(req) != REQ_OP_DISCARD)
- startdev = dasd_alias_get_start_dev(base);
+ startdev = dasd_alias_get_start_dev(base);
if (!startdev)
startdev = base;
private = startdev->private;
@@ -5663,14 +5642,10 @@ static int dasd_eckd_restore_device(struct dasd_device *device)
dasd_eckd_read_features(device);
/* Read Volume Information */
- rc = dasd_eckd_read_vol_info(device);
- if (rc)
- goto out_err2;
+ dasd_eckd_read_vol_info(device);
/* Read Extent Pool Information */
- rc = dasd_eckd_read_ext_pool_info(device);
- if (rc)
- goto out_err2;
+ dasd_eckd_read_ext_pool_info(device);
/* Read Device Characteristics */
rc = dasd_generic_read_dev_chars(device, DASD_ECKD_MAGIC,
@@ -6521,20 +6496,8 @@ static void dasd_eckd_setup_blk_queue(struct dasd_block *block)
unsigned int logical_block_size = block->bp_block;
struct request_queue *q = block->request_queue;
struct dasd_device *device = block->base;
- struct dasd_eckd_private *private;
- unsigned int max_discard_sectors;
- unsigned int max_bytes;
- unsigned int ext_bytes; /* Extent Size in Bytes */
- int recs_per_trk;
- int trks_per_cyl;
- int ext_limit;
- int ext_size; /* Extent Size in Cylinders */
int max;
- private = device->private;
- trks_per_cyl = private->rdc_data.trk_per_cyl;
- recs_per_trk = recs_per_track(&private->rdc_data, 0, logical_block_size);
-
if (device->features & DASD_FEATURE_USERAW) {
/*
* the max_blocks value for raw_track access is 256
@@ -6555,28 +6518,6 @@ static void dasd_eckd_setup_blk_queue(struct dasd_block *block)
/* With page sized segments each segment can be translated into one idaw/tidaw */
blk_queue_max_segment_size(q, PAGE_SIZE);
blk_queue_segment_boundary(q, PAGE_SIZE - 1);
-
- if (dasd_eckd_is_ese(device)) {
- /*
- * Depending on the extent size, up to UINT_MAX bytes can be
- * accepted. However, neither DASD_ECKD_RAS_EXTS_MAX nor the
- * device limits should be exceeded.
- */
- ext_size = dasd_eckd_ext_size(device);
- ext_limit = min(private->real_cyl / ext_size, DASD_ECKD_RAS_EXTS_MAX);
- ext_bytes = ext_size * trks_per_cyl * recs_per_trk *
- logical_block_size;
- max_bytes = UINT_MAX - (UINT_MAX % ext_bytes);
- if (max_bytes / ext_bytes > ext_limit)
- max_bytes = ext_bytes * ext_limit;
-
- max_discard_sectors = max_bytes / 512;
-
- blk_queue_max_discard_sectors(q, max_discard_sectors);
- blk_queue_flag_set(QUEUE_FLAG_DISCARD, q);
- q->limits.discard_granularity = ext_bytes;
- q->limits.discard_alignment = ext_bytes;
- }
}
static struct ccw_driver dasd_eckd_driver = {
diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c
index 4e11de6..5bae515 100644
--- a/drivers/xen/balloon.c
+++ b/drivers/xen/balloon.c
@@ -156,8 +156,10 @@ static DECLARE_DELAYED_WORK(balloon_worker, balloon_process);
(GFP_HIGHUSER | __GFP_NOWARN | __GFP_NORETRY | __GFP_NOMEMALLOC)
/* balloon_append: add the given page to the balloon. */
-static void __balloon_append(struct page *page)
+static void balloon_append(struct page *page)
{
+ __SetPageOffline(page);
+
/* Lowmem is re-populated first, so highmem pages go at list tail. */
if (PageHighMem(page)) {
list_add_tail(&page->lru, &ballooned_pages);
@@ -169,11 +171,6 @@ static void __balloon_append(struct page *page)
wake_up(&balloon_wq);
}
-static void balloon_append(struct page *page)
-{
- __balloon_append(page);
-}
-
/* balloon_retrieve: rescue a page from the balloon, if it is not empty. */
static struct page *balloon_retrieve(bool require_lowmem)
{
@@ -192,6 +189,7 @@ static struct page *balloon_retrieve(bool require_lowmem)
else
balloon_stats.balloon_low--;
+ __ClearPageOffline(page);
return page;
}
@@ -377,8 +375,7 @@ static void xen_online_page(struct page *page, unsigned int order)
for (i = 0; i < size; i++) {
p = pfn_to_page(start_pfn + i);
__online_page_set_limits(p);
- __SetPageOffline(p);
- __balloon_append(p);
+ balloon_append(p);
}
mutex_unlock(&balloon_mutex);
}
@@ -444,7 +441,6 @@ static enum bp_state increase_reservation(unsigned long nr_pages)
xenmem_reservation_va_mapping_update(1, &page, &frame_list[i]);
/* Relinquish the page back to the allocator. */
- __ClearPageOffline(page);
free_reserved_page(page);
}
@@ -471,7 +467,6 @@ static enum bp_state decrease_reservation(unsigned long nr_pages, gfp_t gfp)
state = BP_EAGAIN;
break;
}
- __SetPageOffline(page);
adjust_managed_page_count(page, -1);
xenmem_reservation_scrub_page(page);
list_add(&page->lru, &pages);
@@ -611,7 +606,6 @@ int alloc_xenballooned_pages(int nr_pages, struct page **pages)
while (pgno < nr_pages) {
page = balloon_retrieve(true);
if (page) {
- __ClearPageOffline(page);
pages[pgno++] = page;
#ifdef CONFIG_XEN_HAVE_PVMMU
/*
@@ -653,10 +647,8 @@ void free_xenballooned_pages(int nr_pages, struct page **pages)
mutex_lock(&balloon_mutex);
for (i = 0; i < nr_pages; i++) {
- if (pages[i]) {
- __SetPageOffline(pages[i]);
+ if (pages[i])
balloon_append(pages[i]);
- }
}
balloon_stats.target_unpopulated -= nr_pages;
@@ -674,7 +666,6 @@ static void __init balloon_add_region(unsigned long start_pfn,
unsigned long pages)
{
unsigned long pfn, extra_pfn_end;
- struct page *page;
/*
* If the amount of usable memory has been limited (e.g., with
@@ -684,11 +675,10 @@ static void __init balloon_add_region(unsigned long start_pfn,
extra_pfn_end = min(max_pfn, start_pfn + pages);
for (pfn = start_pfn; pfn < extra_pfn_end; pfn++) {
- page = pfn_to_page(pfn);
/* totalram_pages and totalhigh_pages do not
include the boot-time balloon extension, so
don't subtract from it. */
- __balloon_append(page);
+ balloon_append(pfn_to_page(pfn));
}
balloon_stats.total_pages += extra_pfn_end - start_pfn;
diff --git a/drivers/xen/efi.c b/drivers/xen/efi.c
index 89d60f8..d1ff218 100644
--- a/drivers/xen/efi.c
+++ b/drivers/xen/efi.c
@@ -40,7 +40,7 @@
#define efi_data(op) (op.u.efi_runtime_call)
-efi_status_t xen_efi_get_time(efi_time_t *tm, efi_time_cap_t *tc)
+static efi_status_t xen_efi_get_time(efi_time_t *tm, efi_time_cap_t *tc)
{
struct xen_platform_op op = INIT_EFI_OP(get_time);
@@ -61,9 +61,8 @@ efi_status_t xen_efi_get_time(efi_time_t *tm, efi_time_cap_t *tc)
return efi_data(op).status;
}
-EXPORT_SYMBOL_GPL(xen_efi_get_time);
-efi_status_t xen_efi_set_time(efi_time_t *tm)
+static efi_status_t xen_efi_set_time(efi_time_t *tm)
{
struct xen_platform_op op = INIT_EFI_OP(set_time);
@@ -75,10 +74,10 @@ efi_status_t xen_efi_set_time(efi_time_t *tm)
return efi_data(op).status;
}
-EXPORT_SYMBOL_GPL(xen_efi_set_time);
-efi_status_t xen_efi_get_wakeup_time(efi_bool_t *enabled, efi_bool_t *pending,
- efi_time_t *tm)
+static efi_status_t xen_efi_get_wakeup_time(efi_bool_t *enabled,
+ efi_bool_t *pending,
+ efi_time_t *tm)
{
struct xen_platform_op op = INIT_EFI_OP(get_wakeup_time);
@@ -98,9 +97,8 @@ efi_status_t xen_efi_get_wakeup_time(efi_bool_t *enabled, efi_bool_t *pending,
return efi_data(op).status;
}
-EXPORT_SYMBOL_GPL(xen_efi_get_wakeup_time);
-efi_status_t xen_efi_set_wakeup_time(efi_bool_t enabled, efi_time_t *tm)
+static efi_status_t xen_efi_set_wakeup_time(efi_bool_t enabled, efi_time_t *tm)
{
struct xen_platform_op op = INIT_EFI_OP(set_wakeup_time);
@@ -117,11 +115,10 @@ efi_status_t xen_efi_set_wakeup_time(efi_bool_t enabled, efi_time_t *tm)
return efi_data(op).status;
}
-EXPORT_SYMBOL_GPL(xen_efi_set_wakeup_time);
-efi_status_t xen_efi_get_variable(efi_char16_t *name, efi_guid_t *vendor,
- u32 *attr, unsigned long *data_size,
- void *data)
+static efi_status_t xen_efi_get_variable(efi_char16_t *name, efi_guid_t *vendor,
+ u32 *attr, unsigned long *data_size,
+ void *data)
{
struct xen_platform_op op = INIT_EFI_OP(get_variable);
@@ -141,11 +138,10 @@ efi_status_t xen_efi_get_variable(efi_char16_t *name, efi_guid_t *vendor,
return efi_data(op).status;
}
-EXPORT_SYMBOL_GPL(xen_efi_get_variable);
-efi_status_t xen_efi_get_next_variable(unsigned long *name_size,
- efi_char16_t *name,
- efi_guid_t *vendor)
+static efi_status_t xen_efi_get_next_variable(unsigned long *name_size,
+ efi_char16_t *name,
+ efi_guid_t *vendor)
{
struct xen_platform_op op = INIT_EFI_OP(get_next_variable_name);
@@ -165,11 +161,10 @@ efi_status_t xen_efi_get_next_variable(unsigned long *name_size,
return efi_data(op).status;
}
-EXPORT_SYMBOL_GPL(xen_efi_get_next_variable);
-efi_status_t xen_efi_set_variable(efi_char16_t *name, efi_guid_t *vendor,
- u32 attr, unsigned long data_size,
- void *data)
+static efi_status_t xen_efi_set_variable(efi_char16_t *name, efi_guid_t *vendor,
+ u32 attr, unsigned long data_size,
+ void *data)
{
struct xen_platform_op op = INIT_EFI_OP(set_variable);
@@ -186,11 +181,10 @@ efi_status_t xen_efi_set_variable(efi_char16_t *name, efi_guid_t *vendor,
return efi_data(op).status;
}
-EXPORT_SYMBOL_GPL(xen_efi_set_variable);
-efi_status_t xen_efi_query_variable_info(u32 attr, u64 *storage_space,
- u64 *remaining_space,
- u64 *max_variable_size)
+static efi_status_t xen_efi_query_variable_info(u32 attr, u64 *storage_space,
+ u64 *remaining_space,
+ u64 *max_variable_size)
{
struct xen_platform_op op = INIT_EFI_OP(query_variable_info);
@@ -208,9 +202,8 @@ efi_status_t xen_efi_query_variable_info(u32 attr, u64 *storage_space,
return efi_data(op).status;
}
-EXPORT_SYMBOL_GPL(xen_efi_query_variable_info);
-efi_status_t xen_efi_get_next_high_mono_count(u32 *count)
+static efi_status_t xen_efi_get_next_high_mono_count(u32 *count)
{
struct xen_platform_op op = INIT_EFI_OP(get_next_high_monotonic_count);
@@ -221,10 +214,9 @@ efi_status_t xen_efi_get_next_high_mono_count(u32 *count)
return efi_data(op).status;
}
-EXPORT_SYMBOL_GPL(xen_efi_get_next_high_mono_count);
-efi_status_t xen_efi_update_capsule(efi_capsule_header_t **capsules,
- unsigned long count, unsigned long sg_list)
+static efi_status_t xen_efi_update_capsule(efi_capsule_header_t **capsules,
+ unsigned long count, unsigned long sg_list)
{
struct xen_platform_op op = INIT_EFI_OP(update_capsule);
@@ -241,11 +233,9 @@ efi_status_t xen_efi_update_capsule(efi_capsule_header_t **capsules,
return efi_data(op).status;
}
-EXPORT_SYMBOL_GPL(xen_efi_update_capsule);
-efi_status_t xen_efi_query_capsule_caps(efi_capsule_header_t **capsules,
- unsigned long count, u64 *max_size,
- int *reset_type)
+static efi_status_t xen_efi_query_capsule_caps(efi_capsule_header_t **capsules,
+ unsigned long count, u64 *max_size, int *reset_type)
{
struct xen_platform_op op = INIT_EFI_OP(query_capsule_capabilities);
@@ -264,10 +254,9 @@ efi_status_t xen_efi_query_capsule_caps(efi_capsule_header_t **capsules,
return efi_data(op).status;
}
-EXPORT_SYMBOL_GPL(xen_efi_query_capsule_caps);
-void xen_efi_reset_system(int reset_type, efi_status_t status,
- unsigned long data_size, efi_char16_t *data)
+static void xen_efi_reset_system(int reset_type, efi_status_t status,
+ unsigned long data_size, efi_char16_t *data)
{
switch (reset_type) {
case EFI_RESET_COLD:
@@ -281,4 +270,25 @@ void xen_efi_reset_system(int reset_type, efi_status_t status,
BUG();
}
}
-EXPORT_SYMBOL_GPL(xen_efi_reset_system);
+
+/*
+ * Set XEN EFI runtime services function pointers. Other fields of struct efi,
+ * e.g. efi.systab, will be set like normal EFI.
+ */
+void __init xen_efi_runtime_setup(void)
+{
+ efi.get_time = xen_efi_get_time;
+ efi.set_time = xen_efi_set_time;
+ efi.get_wakeup_time = xen_efi_get_wakeup_time;
+ efi.set_wakeup_time = xen_efi_set_wakeup_time;
+ efi.get_variable = xen_efi_get_variable;
+ efi.get_next_variable = xen_efi_get_next_variable;
+ efi.set_variable = xen_efi_set_variable;
+ efi.set_variable_nonblocking = xen_efi_set_variable;
+ efi.query_variable_info = xen_efi_query_variable_info;
+ efi.query_variable_info_nonblocking = xen_efi_query_variable_info;
+ efi.update_capsule = xen_efi_update_capsule;
+ efi.query_capsule_caps = xen_efi_query_capsule_caps;
+ efi.get_next_high_mono_count = xen_efi_get_next_high_mono_count;
+ efi.reset_system = xen_efi_reset_system;
+}
diff --git a/drivers/xen/xenbus/xenbus_dev_frontend.c b/drivers/xen/xenbus/xenbus_dev_frontend.c
index 08adc59..597af45 100644
--- a/drivers/xen/xenbus/xenbus_dev_frontend.c
+++ b/drivers/xen/xenbus/xenbus_dev_frontend.c
@@ -55,6 +55,7 @@
#include <linux/string.h>
#include <linux/slab.h>
#include <linux/miscdevice.h>
+#include <linux/workqueue.h>
#include <xen/xenbus.h>
#include <xen/xen.h>
@@ -116,6 +117,8 @@ struct xenbus_file_priv {
wait_queue_head_t read_waitq;
struct kref kref;
+
+ struct work_struct wq;
};
/* Read out any raw xenbus messages queued up. */
@@ -300,14 +303,14 @@ static void watch_fired(struct xenbus_watch *watch,
mutex_unlock(&adap->dev_data->reply_mutex);
}
-static void xenbus_file_free(struct kref *kref)
+static void xenbus_worker(struct work_struct *wq)
{
struct xenbus_file_priv *u;
struct xenbus_transaction_holder *trans, *tmp;
struct watch_adapter *watch, *tmp_watch;
struct read_buffer *rb, *tmp_rb;
- u = container_of(kref, struct xenbus_file_priv, kref);
+ u = container_of(wq, struct xenbus_file_priv, wq);
/*
* No need for locking here because there are no other users,
@@ -333,6 +336,18 @@ static void xenbus_file_free(struct kref *kref)
kfree(u);
}
+static void xenbus_file_free(struct kref *kref)
+{
+ struct xenbus_file_priv *u;
+
+ /*
+ * We might be called in xenbus_thread().
+ * Use workqueue to avoid deadlock.
+ */
+ u = container_of(kref, struct xenbus_file_priv, kref);
+ schedule_work(&u->wq);
+}
+
static struct xenbus_transaction_holder *xenbus_get_transaction(
struct xenbus_file_priv *u, uint32_t tx_id)
{
@@ -650,6 +665,7 @@ static int xenbus_file_open(struct inode *inode, struct file *filp)
INIT_LIST_HEAD(&u->watches);
INIT_LIST_HEAD(&u->read_buffers);
init_waitqueue_head(&u->read_waitq);
+ INIT_WORK(&u->wq, xenbus_worker);
mutex_init(&u->reply_mutex);
mutex_init(&u->msgbuffer_mutex);
diff --git a/fs/erofs/data.c b/fs/erofs/data.c
index 8a9fcbd..fc3a8d8 100644
--- a/fs/erofs/data.c
+++ b/fs/erofs/data.c
@@ -34,11 +34,15 @@ static void erofs_readendio(struct bio *bio)
struct page *erofs_get_meta_page(struct super_block *sb, erofs_blk_t blkaddr)
{
- struct inode *const bd_inode = sb->s_bdev->bd_inode;
- struct address_space *const mapping = bd_inode->i_mapping;
+ struct address_space *const mapping = sb->s_bdev->bd_inode->i_mapping;
+ struct page *page;
- return read_cache_page_gfp(mapping, blkaddr,
+ page = read_cache_page_gfp(mapping, blkaddr,
mapping_gfp_constraint(mapping, ~__GFP_FS));
+ /* should already be PageUptodate */
+ if (!IS_ERR(page))
+ lock_page(page);
+ return page;
}
static int erofs_map_blocks_flatmode(struct inode *inode,
diff --git a/fs/erofs/super.c b/fs/erofs/super.c
index caf9a951..0e36949 100644
--- a/fs/erofs/super.c
+++ b/fs/erofs/super.c
@@ -105,9 +105,9 @@ static int erofs_read_superblock(struct super_block *sb)
int ret;
page = read_mapping_page(sb->s_bdev->bd_inode->i_mapping, 0, NULL);
- if (!page) {
+ if (IS_ERR(page)) {
erofs_err(sb, "cannot read erofs superblock");
- return -EIO;
+ return PTR_ERR(page);
}
sbi = EROFS_SB(sb);
diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c
index 96e34c9..fad80c9 100644
--- a/fs/erofs/zdata.c
+++ b/fs/erofs/zdata.c
@@ -575,7 +575,7 @@ static int z_erofs_do_read_page(struct z_erofs_decompress_frontend *fe,
struct erofs_map_blocks *const map = &fe->map;
struct z_erofs_collector *const clt = &fe->clt;
const loff_t offset = page_offset(page);
- bool tight = (clt->mode >= COLLECT_PRIMARY_HOOKED);
+ bool tight = true;
enum z_erofs_cache_alloctype cache_strategy;
enum z_erofs_page_type page_type;
@@ -628,8 +628,16 @@ static int z_erofs_do_read_page(struct z_erofs_decompress_frontend *fe,
preload_compressed_pages(clt, MNGD_MAPPING(sbi),
cache_strategy, pagepool);
- tight &= (clt->mode >= COLLECT_PRIMARY_HOOKED);
hitted:
+ /*
+ * Ensure the current partial page belongs to this submit chain rather
+ * than other concurrent submit chains or the noio(bypass) chain since
+ * those chains are handled asynchronously thus the page cannot be used
+ * for inplace I/O or pagevec (should be processed in strict order.)
+ */
+ tight &= (clt->mode >= COLLECT_PRIMARY_HOOKED &&
+ clt->mode != COLLECT_PRIMARY_FOLLOWED_NOINPLACE);
+
cur = end - min_t(unsigned int, offset + end - map->m_la, end);
if (!(map->m_flags & EROFS_MAP_MAPPED)) {
zero_user_segment(page, cur, end);
diff --git a/fs/io_uring.c b/fs/io_uring.c
index aa8ac55..8a0381f 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -1892,15 +1892,15 @@ static int io_timeout(struct io_kiocb *req, const struct io_uring_sqe *sqe)
unsigned count, req_dist, tail_index;
struct io_ring_ctx *ctx = req->ctx;
struct list_head *entry;
- struct timespec ts;
+ struct timespec64 ts;
if (unlikely(ctx->flags & IORING_SETUP_IOPOLL))
return -EINVAL;
if (sqe->flags || sqe->ioprio || sqe->buf_index || sqe->timeout_flags ||
sqe->len != 1)
return -EINVAL;
- if (copy_from_user(&ts, (void __user *) (unsigned long) sqe->addr,
- sizeof(ts)))
+
+ if (get_timespec64(&ts, u64_to_user_ptr(sqe->addr)))
return -EFAULT;
/*
@@ -1934,7 +1934,7 @@ static int io_timeout(struct io_kiocb *req, const struct io_uring_sqe *sqe)
hrtimer_init(&req->timeout.timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
req->timeout.timer.function = io_timeout_fn;
- hrtimer_start(&req->timeout.timer, timespec_to_ktime(ts),
+ hrtimer_start(&req->timeout.timer, timespec64_to_ktime(ts),
HRTIMER_MODE_REL);
return 0;
}
diff --git a/fs/statfs.c b/fs/statfs.c
index eea7af6..2616424 100644
--- a/fs/statfs.c
+++ b/fs/statfs.c
@@ -318,19 +318,10 @@ COMPAT_SYSCALL_DEFINE2(fstatfs, unsigned int, fd, struct compat_statfs __user *,
static int put_compat_statfs64(struct compat_statfs64 __user *ubuf, struct kstatfs *kbuf)
{
struct compat_statfs64 buf;
- if (sizeof(ubuf->f_bsize) == 4) {
- if ((kbuf->f_type | kbuf->f_bsize | kbuf->f_namelen |
- kbuf->f_frsize | kbuf->f_flags) & 0xffffffff00000000ULL)
- return -EOVERFLOW;
- /* f_files and f_ffree may be -1; it's okay
- * to stuff that into 32 bits */
- if (kbuf->f_files != 0xffffffffffffffffULL
- && (kbuf->f_files & 0xffffffff00000000ULL))
- return -EOVERFLOW;
- if (kbuf->f_ffree != 0xffffffffffffffffULL
- && (kbuf->f_ffree & 0xffffffff00000000ULL))
- return -EOVERFLOW;
- }
+
+ if ((kbuf->f_bsize | kbuf->f_frsize) & 0xffffffff00000000ULL)
+ return -EOVERFLOW;
+
memset(&buf, 0, sizeof(struct compat_statfs64));
buf.f_type = kbuf->f_type;
buf.f_bsize = kbuf->f_bsize;
diff --git a/include/linux/bitops.h b/include/linux/bitops.h
index cf074bc..c94a9ff 100644
--- a/include/linux/bitops.h
+++ b/include/linux/bitops.h
@@ -4,6 +4,13 @@
#include <asm/types.h>
#include <linux/bits.h>
+/* Set bits in the first 'n' bytes when loaded from memory */
+#ifdef __LITTLE_ENDIAN
+# define aligned_byte_mask(n) ((1UL << 8*(n))-1)
+#else
+# define aligned_byte_mask(n) (~0xffUL << (BITS_PER_LONG - 8 - 8*(n)))
+#endif
+
#define BITS_PER_TYPE(type) (sizeof(type) * BITS_PER_BYTE)
#define BITS_TO_LONGS(nr) DIV_ROUND_UP(nr, BITS_PER_TYPE(long))
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index fcb46b3..719fc3e 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -1090,6 +1090,7 @@ enum kvm_stat_kind {
struct kvm_stat_data {
int offset;
+ int mode;
struct kvm *kvm;
};
@@ -1097,6 +1098,7 @@ struct kvm_stats_debugfs_item {
const char *name;
int offset;
enum kvm_stat_kind kind;
+ int mode;
};
extern struct kvm_stats_debugfs_item debugfs_entries[];
extern struct dentry *kvm_debugfs_dir;
diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h
index 70bbdc3..e47d052 100644
--- a/include/linux/uaccess.h
+++ b/include/linux/uaccess.h
@@ -231,6 +231,76 @@ __copy_from_user_inatomic_nocache(void *to, const void __user *from,
#endif /* ARCH_HAS_NOCACHE_UACCESS */
+extern __must_check int check_zeroed_user(const void __user *from, size_t size);
+
+/**
+ * copy_struct_from_user: copy a struct from userspace
+ * @dst: Destination address, in kernel space. This buffer must be @ksize
+ * bytes long.
+ * @ksize: Size of @dst struct.
+ * @src: Source address, in userspace.
+ * @usize: (Alleged) size of @src struct.
+ *
+ * Copies a struct from userspace to kernel space, in a way that guarantees
+ * backwards-compatibility for struct syscall arguments (as long as future
+ * struct extensions are made such that all new fields are *appended* to the
+ * old struct, and zeroed-out new fields have the same meaning as the old
+ * struct).
+ *
+ * @ksize is just sizeof(*dst), and @usize should've been passed by userspace.
+ * The recommended usage is something like the following:
+ *
+ * SYSCALL_DEFINE2(foobar, const struct foo __user *, uarg, size_t, usize)
+ * {
+ * int err;
+ * struct foo karg = {};
+ *
+ * if (usize > PAGE_SIZE)
+ * return -E2BIG;
+ * if (usize < FOO_SIZE_VER0)
+ * return -EINVAL;
+ *
+ * err = copy_struct_from_user(&karg, sizeof(karg), uarg, usize);
+ * if (err)
+ * return err;
+ *
+ * // ...
+ * }
+ *
+ * There are three cases to consider:
+ * * If @usize == @ksize, then it's copied verbatim.
+ * * If @usize < @ksize, then the userspace has passed an old struct to a
+ * newer kernel. The rest of the trailing bytes in @dst (@ksize - @usize)
+ * are to be zero-filled.
+ * * If @usize > @ksize, then the userspace has passed a new struct to an
+ * older kernel. The trailing bytes unknown to the kernel (@usize - @ksize)
+ * are checked to ensure they are zeroed, otherwise -E2BIG is returned.
+ *
+ * Returns (in all cases, some data may have been copied):
+ * * -E2BIG: (@usize > @ksize) and there are non-zero trailing bytes in @src.
+ * * -EFAULT: access to userspace failed.
+ */
+static __always_inline __must_check int
+copy_struct_from_user(void *dst, size_t ksize, const void __user *src,
+ size_t usize)
+{
+ size_t size = min(ksize, usize);
+ size_t rest = max(ksize, usize) - size;
+
+ /* Deal with trailing bytes. */
+ if (usize < ksize) {
+ memset(dst + size, 0, rest);
+ } else if (usize > ksize) {
+ int ret = check_zeroed_user(src + size, rest);
+ if (ret <= 0)
+ return ret ?: -E2BIG;
+ }
+ /* Copy the interoperable parts of the struct. */
+ if (copy_from_user(dst, src, size))
+ return -EFAULT;
+ return 0;
+}
+
/*
* probe_kernel_read(): safely attempt to read from a location
* @dst: pointer to the buffer that shall take the data
diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h
index c99b4f2..4fe35d6 100644
--- a/include/uapi/drm/amdgpu_drm.h
+++ b/include/uapi/drm/amdgpu_drm.h
@@ -1003,6 +1003,8 @@ struct drm_amdgpu_info_device {
__u64 high_va_max;
/* gfx10 pa_sc_tile_steering_override */
__u32 pa_sc_tile_steering_override;
+ /* disabled TCCs */
+ __u64 tcc_disabled_mask;
};
struct drm_amdgpu_info_hw_ip {
diff --git a/include/uapi/linux/nvme_ioctl.h b/include/uapi/linux/nvme_ioctl.h
index 1c215ea..e168dc5 100644
--- a/include/uapi/linux/nvme_ioctl.h
+++ b/include/uapi/linux/nvme_ioctl.h
@@ -45,6 +45,27 @@ struct nvme_passthru_cmd {
__u32 result;
};
+struct nvme_passthru_cmd64 {
+ __u8 opcode;
+ __u8 flags;
+ __u16 rsvd1;
+ __u32 nsid;
+ __u32 cdw2;
+ __u32 cdw3;
+ __u64 metadata;
+ __u64 addr;
+ __u32 metadata_len;
+ __u32 data_len;
+ __u32 cdw10;
+ __u32 cdw11;
+ __u32 cdw12;
+ __u32 cdw13;
+ __u32 cdw14;
+ __u32 cdw15;
+ __u32 timeout_ms;
+ __u64 result;
+};
+
#define nvme_admin_cmd nvme_passthru_cmd
#define NVME_IOCTL_ID _IO('N', 0x40)
@@ -54,5 +75,7 @@ struct nvme_passthru_cmd {
#define NVME_IOCTL_RESET _IO('N', 0x44)
#define NVME_IOCTL_SUBSYS_RESET _IO('N', 0x45)
#define NVME_IOCTL_RESCAN _IO('N', 0x46)
+#define NVME_IOCTL_ADMIN64_CMD _IOWR('N', 0x47, struct nvme_passthru_cmd64)
+#define NVME_IOCTL_IO64_CMD _IOWR('N', 0x48, struct nvme_passthru_cmd64)
#endif /* _UAPI_LINUX_NVME_IOCTL_H */
diff --git a/include/uapi/linux/pg.h b/include/uapi/linux/pg.h
index 364c350..62b6f69 100644
--- a/include/uapi/linux/pg.h
+++ b/include/uapi/linux/pg.h
@@ -35,6 +35,9 @@
*/
+#ifndef _UAPI_LINUX_PG_H
+#define _UAPI_LINUX_PG_H
+
#define PG_MAGIC 'P'
#define PG_RESET 'Z'
#define PG_COMMAND 'C'
@@ -61,4 +64,4 @@ struct pg_read_hdr {
};
-/* end of pg.h */
+#endif /* _UAPI_LINUX_PG_H */
diff --git a/include/uapi/linux/sched.h b/include/uapi/linux/sched.h
index b3105ac..99335e1 100644
--- a/include/uapi/linux/sched.h
+++ b/include/uapi/linux/sched.h
@@ -33,8 +33,31 @@
#define CLONE_NEWNET 0x40000000 /* New network namespace */
#define CLONE_IO 0x80000000 /* Clone io context */
-/*
- * Arguments for the clone3 syscall
+#ifndef __ASSEMBLY__
+/**
+ * struct clone_args - arguments for the clone3 syscall
+ * @flags: Flags for the new process as listed above.
+ * All flags are valid except for CSIGNAL and
+ * CLONE_DETACHED.
+ * @pidfd: If CLONE_PIDFD is set, a pidfd will be
+ * returned in this argument.
+ * @child_tid: If CLONE_CHILD_SETTID is set, the TID of the
+ * child process will be returned in the child's
+ * memory.
+ * @parent_tid: If CLONE_PARENT_SETTID is set, the TID of
+ * the child process will be returned in the
+ * parent's memory.
+ * @exit_signal: The exit_signal the parent process will be
+ * sent when the child exits.
+ * @stack: Specify the location of the stack for the
+ * child process.
+ * @stack_size: The size of the stack for the child process.
+ * @tls: If CLONE_SETTLS is set, the tls descriptor
+ * is set to tls.
+ *
+ * The structure is versioned by size and thus extensible.
+ * New struct members must go at the end of the struct and
+ * must be properly 64bit aligned.
*/
struct clone_args {
__aligned_u64 flags;
@@ -46,6 +69,9 @@ struct clone_args {
__aligned_u64 stack_size;
__aligned_u64 tls;
};
+#endif
+
+#define CLONE_ARGS_SIZE_VER0 64 /* sizeof first published struct */
/*
* Scheduling policies
diff --git a/include/xen/xen-ops.h b/include/xen/xen-ops.h
index 98b30c1..d89969a 100644
--- a/include/xen/xen-ops.h
+++ b/include/xen/xen-ops.h
@@ -212,30 +212,7 @@ int xen_xlate_map_ballooned_pages(xen_pfn_t **pfns, void **vaddr,
bool xen_running_on_version_or_later(unsigned int major, unsigned int minor);
-efi_status_t xen_efi_get_time(efi_time_t *tm, efi_time_cap_t *tc);
-efi_status_t xen_efi_set_time(efi_time_t *tm);
-efi_status_t xen_efi_get_wakeup_time(efi_bool_t *enabled, efi_bool_t *pending,
- efi_time_t *tm);
-efi_status_t xen_efi_set_wakeup_time(efi_bool_t enabled, efi_time_t *tm);
-efi_status_t xen_efi_get_variable(efi_char16_t *name, efi_guid_t *vendor,
- u32 *attr, unsigned long *data_size,
- void *data);
-efi_status_t xen_efi_get_next_variable(unsigned long *name_size,
- efi_char16_t *name, efi_guid_t *vendor);
-efi_status_t xen_efi_set_variable(efi_char16_t *name, efi_guid_t *vendor,
- u32 attr, unsigned long data_size,
- void *data);
-efi_status_t xen_efi_query_variable_info(u32 attr, u64 *storage_space,
- u64 *remaining_space,
- u64 *max_variable_size);
-efi_status_t xen_efi_get_next_high_mono_count(u32 *count);
-efi_status_t xen_efi_update_capsule(efi_capsule_header_t **capsules,
- unsigned long count, unsigned long sg_list);
-efi_status_t xen_efi_query_capsule_caps(efi_capsule_header_t **capsules,
- unsigned long count, u64 *max_size,
- int *reset_type);
-void xen_efi_reset_system(int reset_type, efi_status_t status,
- unsigned long data_size, efi_char16_t *data);
+void xen_efi_runtime_setup(void);
#ifdef CONFIG_PREEMPT
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 4655adb..3f0cb82 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -10586,55 +10586,26 @@ static int perf_copy_attr(struct perf_event_attr __user *uattr,
u32 size;
int ret;
- if (!access_ok(uattr, PERF_ATTR_SIZE_VER0))
- return -EFAULT;
-
- /*
- * zero the full structure, so that a short copy will be nice.
- */
+ /* Zero the full structure, so that a short copy will be nice. */
memset(attr, 0, sizeof(*attr));
ret = get_user(size, &uattr->size);
if (ret)
return ret;
- if (size > PAGE_SIZE) /* silly large */
- goto err_size;
-
- if (!size) /* abi compat */
+ /* ABI compatibility quirk: */
+ if (!size)
size = PERF_ATTR_SIZE_VER0;
-
- if (size < PERF_ATTR_SIZE_VER0)
+ if (size < PERF_ATTR_SIZE_VER0 || size > PAGE_SIZE)
goto err_size;
- /*
- * If we're handed a bigger struct than we know of,
- * ensure all the unknown bits are 0 - i.e. new
- * user-space does not rely on any kernel feature
- * extensions we dont know about yet.
- */
- if (size > sizeof(*attr)) {
- unsigned char __user *addr;
- unsigned char __user *end;
- unsigned char val;
-
- addr = (void __user *)uattr + sizeof(*attr);
- end = (void __user *)uattr + size;
-
- for (; addr < end; addr++) {
- ret = get_user(val, addr);
- if (ret)
- return ret;
- if (val)
- goto err_size;
- }
- size = sizeof(*attr);
+ ret = copy_struct_from_user(attr, sizeof(*attr), uattr, size);
+ if (ret) {
+ if (ret == -E2BIG)
+ goto err_size;
+ return ret;
}
- ret = copy_from_user(attr, uattr, size);
- if (ret)
- return -EFAULT;
-
attr->size = size;
if (attr->__reserved_1)
diff --git a/kernel/fork.c b/kernel/fork.c
index f9572f4..1f6c45f 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -2525,39 +2525,19 @@ SYSCALL_DEFINE5(clone, unsigned long, clone_flags, unsigned long, newsp,
#ifdef __ARCH_WANT_SYS_CLONE3
noinline static int copy_clone_args_from_user(struct kernel_clone_args *kargs,
struct clone_args __user *uargs,
- size_t size)
+ size_t usize)
{
+ int err;
struct clone_args args;
- if (unlikely(size > PAGE_SIZE))
+ if (unlikely(usize > PAGE_SIZE))
return -E2BIG;
-
- if (unlikely(size < sizeof(struct clone_args)))
+ if (unlikely(usize < CLONE_ARGS_SIZE_VER0))
return -EINVAL;
- if (unlikely(!access_ok(uargs, size)))
- return -EFAULT;
-
- if (size > sizeof(struct clone_args)) {
- unsigned char __user *addr;
- unsigned char __user *end;
- unsigned char val;
-
- addr = (void __user *)uargs + sizeof(struct clone_args);
- end = (void __user *)uargs + size;
-
- for (; addr < end; addr++) {
- if (get_user(val, addr))
- return -EFAULT;
- if (val)
- return -E2BIG;
- }
-
- size = sizeof(struct clone_args);
- }
-
- if (copy_from_user(&args, uargs, size))
- return -EFAULT;
+ err = copy_struct_from_user(&args, sizeof(args), uargs, usize);
+ if (err)
+ return err;
/*
* Verify that higher 32bits of exit_signal are unset and that
@@ -2604,6 +2584,17 @@ static bool clone3_args_valid(const struct kernel_clone_args *kargs)
return true;
}
+/**
+ * clone3 - create a new process with specific properties
+ * @uargs: argument structure
+ * @size: size of @uargs
+ *
+ * clone3() is the extensible successor to clone()/clone2().
+ * It takes a struct as argument that is versioned by its size.
+ *
+ * Return: On success, a positive PID for the child process.
+ * On error, a negative errno number.
+ */
SYSCALL_DEFINE2(clone3, struct clone_args __user *, uargs, size_t, size)
{
int err;
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 7880f4f..dd05a37 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -5106,9 +5106,6 @@ static int sched_copy_attr(struct sched_attr __user *uattr, struct sched_attr *a
u32 size;
int ret;
- if (!access_ok(uattr, SCHED_ATTR_SIZE_VER0))
- return -EFAULT;
-
/* Zero the full structure, so that a short copy will be nice: */
memset(attr, 0, sizeof(*attr));
@@ -5116,45 +5113,19 @@ static int sched_copy_attr(struct sched_attr __user *uattr, struct sched_attr *a
if (ret)
return ret;
- /* Bail out on silly large: */
- if (size > PAGE_SIZE)
- goto err_size;
-
/* ABI compatibility quirk: */
if (!size)
size = SCHED_ATTR_SIZE_VER0;
-
- if (size < SCHED_ATTR_SIZE_VER0)
+ if (size < SCHED_ATTR_SIZE_VER0 || size > PAGE_SIZE)
goto err_size;
- /*
- * If we're handed a bigger struct than we know of,
- * ensure all the unknown bits are 0 - i.e. new
- * user-space does not rely on any kernel feature
- * extensions we dont know about yet.
- */
- if (size > sizeof(*attr)) {
- unsigned char __user *addr;
- unsigned char __user *end;
- unsigned char val;
-
- addr = (void __user *)uattr + sizeof(*attr);
- end = (void __user *)uattr + size;
-
- for (; addr < end; addr++) {
- ret = get_user(val, addr);
- if (ret)
- return ret;
- if (val)
- goto err_size;
- }
- size = sizeof(*attr);
+ ret = copy_struct_from_user(attr, sizeof(*attr), uattr, size);
+ if (ret) {
+ if (ret == -E2BIG)
+ goto err_size;
+ return ret;
}
- ret = copy_from_user(attr, uattr, size);
- if (ret)
- return -EFAULT;
-
if ((attr->sched_flags & SCHED_FLAG_UTIL_CLAMP) &&
size < SCHED_ATTR_SIZE_VER1)
return -EINVAL;
@@ -5354,7 +5325,7 @@ sched_attr_copy_to_user(struct sched_attr __user *uattr,
* sys_sched_getattr - similar to sched_getparam, but with sched_attr
* @pid: the pid in question.
* @uattr: structure containing the extended parameters.
- * @usize: sizeof(attr) that user-space knows about, for forwards and backwards compatibility.
+ * @usize: sizeof(attr) for fwd/bwd comp.
* @flags: for future extension.
*/
SYSCALL_DEFINE4(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr,
diff --git a/kernel/sched/membarrier.c b/kernel/sched/membarrier.c
index a39bed2..168479a 100644
--- a/kernel/sched/membarrier.c
+++ b/kernel/sched/membarrier.c
@@ -174,7 +174,6 @@ static int membarrier_private_expedited(int flags)
*/
if (cpu == raw_smp_processor_id())
continue;
- rcu_read_lock();
p = rcu_dereference(cpu_rq(cpu)->curr);
if (p && p->mm == mm)
__cpumask_set_cpu(cpu, tmpmask);
diff --git a/kernel/time/tick-broadcast-hrtimer.c b/kernel/time/tick-broadcast-hrtimer.c
index c1f5bb5..b5a65e2 100644
--- a/kernel/time/tick-broadcast-hrtimer.c
+++ b/kernel/time/tick-broadcast-hrtimer.c
@@ -42,39 +42,39 @@ static int bc_shutdown(struct clock_event_device *evt)
*/
static int bc_set_next(ktime_t expires, struct clock_event_device *bc)
{
- int bc_moved;
/*
- * We try to cancel the timer first. If the callback is on
- * flight on some other cpu then we let it handle it. If we
- * were able to cancel the timer nothing can rearm it as we
- * own broadcast_lock.
+ * This is called either from enter/exit idle code or from the
+ * broadcast handler. In all cases tick_broadcast_lock is held.
*
- * However we can also be called from the event handler of
- * ce_broadcast_hrtimer itself when it expires. We cannot
- * restart the timer because we are in the callback, but we
- * can set the expiry time and let the callback return
- * HRTIMER_RESTART.
+ * hrtimer_cancel() cannot be called here neither from the
+ * broadcast handler nor from the enter/exit idle code. The idle
+ * code can run into the problem described in bc_shutdown() and the
+ * broadcast handler cannot wait for itself to complete for obvious
+ * reasons.
*
- * Since we are in the idle loop at this point and because
- * hrtimer_{start/cancel} functions call into tracing,
- * calls to these functions must be bound within RCU_NONIDLE.
+ * Each caller tries to arm the hrtimer on its own CPU, but if the
+ * hrtimer callbback function is currently running, then
+ * hrtimer_start() cannot move it and the timer stays on the CPU on
+ * which it is assigned at the moment.
+ *
+ * As this can be called from idle code, the hrtimer_start()
+ * invocation has to be wrapped with RCU_NONIDLE() as
+ * hrtimer_start() can call into tracing.
*/
- RCU_NONIDLE(
- {
- bc_moved = hrtimer_try_to_cancel(&bctimer) >= 0;
- if (bc_moved) {
- hrtimer_start(&bctimer, expires,
- HRTIMER_MODE_ABS_PINNED_HARD);
- }
- }
- );
-
- if (bc_moved) {
- /* Bind the "device" to the cpu */
- bc->bound_on = smp_processor_id();
- } else if (bc->bound_on == smp_processor_id()) {
- hrtimer_set_expires(&bctimer, expires);
- }
+ RCU_NONIDLE( {
+ hrtimer_start(&bctimer, expires, HRTIMER_MODE_ABS_PINNED_HARD);
+ /*
+ * The core tick broadcast mode expects bc->bound_on to be set
+ * correctly to prevent a CPU which has the broadcast hrtimer
+ * armed from going deep idle.
+ *
+ * As tick_broadcast_lock is held, nothing can change the cpu
+ * base which was just established in hrtimer_start() above. So
+ * the below access is safe even without holding the hrtimer
+ * base lock.
+ */
+ bc->bound_on = bctimer.base->cpu_base->cpu;
+ } );
return 0;
}
@@ -100,10 +100,6 @@ static enum hrtimer_restart bc_handler(struct hrtimer *t)
{
ce_broadcast_hrtimer.event_handler(&ce_broadcast_hrtimer);
- if (clockevent_state_oneshot(&ce_broadcast_hrtimer))
- if (ce_broadcast_hrtimer.next_event != KTIME_MAX)
- return HRTIMER_RESTART;
-
return HRTIMER_NORESTART;
}
diff --git a/lib/strnlen_user.c b/lib/strnlen_user.c
index 28ff554..6c0005d 100644
--- a/lib/strnlen_user.c
+++ b/lib/strnlen_user.c
@@ -3,16 +3,10 @@
#include <linux/export.h>
#include <linux/uaccess.h>
#include <linux/mm.h>
+#include <linux/bitops.h>
#include <asm/word-at-a-time.h>
-/* Set bits in the first 'n' bytes when loaded from memory */
-#ifdef __LITTLE_ENDIAN
-# define aligned_byte_mask(n) ((1ul << 8*(n))-1)
-#else
-# define aligned_byte_mask(n) (~0xfful << (BITS_PER_LONG - 8 - 8*(n)))
-#endif
-
/*
* Do a strnlen, return length of string *with* final '\0'.
* 'count' is the user-supplied count, while 'max' is the
diff --git a/lib/test_user_copy.c b/lib/test_user_copy.c
index 67bcd5d..e365ace06 100644
--- a/lib/test_user_copy.c
+++ b/lib/test_user_copy.c
@@ -31,14 +31,133 @@
# define TEST_U64
#endif
-#define test(condition, msg) \
-({ \
- int cond = (condition); \
- if (cond) \
- pr_warn("%s\n", msg); \
- cond; \
+#define test(condition, msg, ...) \
+({ \
+ int cond = (condition); \
+ if (cond) \
+ pr_warn("[%d] " msg "\n", __LINE__, ##__VA_ARGS__); \
+ cond; \
})
+static bool is_zeroed(void *from, size_t size)
+{
+ return memchr_inv(from, 0x0, size) == NULL;
+}
+
+static int test_check_nonzero_user(char *kmem, char __user *umem, size_t size)
+{
+ int ret = 0;
+ size_t start, end, i;
+ size_t zero_start = size / 4;
+ size_t zero_end = size - zero_start;
+
+ /*
+ * We conduct a series of check_nonzero_user() tests on a block of memory
+ * with the following byte-pattern (trying every possible [start,end]
+ * pair):
+ *
+ * [ 00 ff 00 ff ... 00 00 00 00 ... ff 00 ff 00 ]
+ *
+ * And we verify that check_nonzero_user() acts identically to memchr_inv().
+ */
+
+ memset(kmem, 0x0, size);
+ for (i = 1; i < zero_start; i += 2)
+ kmem[i] = 0xff;
+ for (i = zero_end; i < size; i += 2)
+ kmem[i] = 0xff;
+
+ ret |= test(copy_to_user(umem, kmem, size),
+ "legitimate copy_to_user failed");
+
+ for (start = 0; start <= size; start++) {
+ for (end = start; end <= size; end++) {
+ size_t len = end - start;
+ int retval = check_zeroed_user(umem + start, len);
+ int expected = is_zeroed(kmem + start, len);
+
+ ret |= test(retval != expected,
+ "check_nonzero_user(=%d) != memchr_inv(=%d) mismatch (start=%zu, end=%zu)",
+ retval, expected, start, end);
+ }
+ }
+
+ return ret;
+}
+
+static int test_copy_struct_from_user(char *kmem, char __user *umem,
+ size_t size)
+{
+ int ret = 0;
+ char *umem_src = NULL, *expected = NULL;
+ size_t ksize, usize;
+
+ umem_src = kmalloc(size, GFP_KERNEL);
+ if ((ret |= test(umem_src == NULL, "kmalloc failed")))
+ goto out_free;
+
+ expected = kmalloc(size, GFP_KERNEL);
+ if ((ret |= test(expected == NULL, "kmalloc failed")))
+ goto out_free;
+
+ /* Fill umem with a fixed byte pattern. */
+ memset(umem_src, 0x3e, size);
+ ret |= test(copy_to_user(umem, umem_src, size),
+ "legitimate copy_to_user failed");
+
+ /* Check basic case -- (usize == ksize). */
+ ksize = size;
+ usize = size;
+
+ memcpy(expected, umem_src, ksize);
+
+ memset(kmem, 0x0, size);
+ ret |= test(copy_struct_from_user(kmem, ksize, umem, usize),
+ "copy_struct_from_user(usize == ksize) failed");
+ ret |= test(memcmp(kmem, expected, ksize),
+ "copy_struct_from_user(usize == ksize) gives unexpected copy");
+
+ /* Old userspace case -- (usize < ksize). */
+ ksize = size;
+ usize = size / 2;
+
+ memcpy(expected, umem_src, usize);
+ memset(expected + usize, 0x0, ksize - usize);
+
+ memset(kmem, 0x0, size);
+ ret |= test(copy_struct_from_user(kmem, ksize, umem, usize),
+ "copy_struct_from_user(usize < ksize) failed");
+ ret |= test(memcmp(kmem, expected, ksize),
+ "copy_struct_from_user(usize < ksize) gives unexpected copy");
+
+ /* New userspace (-E2BIG) case -- (usize > ksize). */
+ ksize = size / 2;
+ usize = size;
+
+ memset(kmem, 0x0, size);
+ ret |= test(copy_struct_from_user(kmem, ksize, umem, usize) != -E2BIG,
+ "copy_struct_from_user(usize > ksize) didn't give E2BIG");
+
+ /* New userspace (success) case -- (usize > ksize). */
+ ksize = size / 2;
+ usize = size;
+
+ memcpy(expected, umem_src, ksize);
+ ret |= test(clear_user(umem + ksize, usize - ksize),
+ "legitimate clear_user failed");
+
+ memset(kmem, 0x0, size);
+ ret |= test(copy_struct_from_user(kmem, ksize, umem, usize),
+ "copy_struct_from_user(usize > ksize) failed");
+ ret |= test(memcmp(kmem, expected, ksize),
+ "copy_struct_from_user(usize > ksize) gives unexpected copy");
+
+out_free:
+ kfree(expected);
+ kfree(umem_src);
+ return ret;
+}
+
static int __init test_user_copy_init(void)
{
int ret = 0;
@@ -106,6 +225,11 @@ static int __init test_user_copy_init(void)
#endif
#undef test_legit
+ /* Test usage of check_nonzero_user(). */
+ ret |= test_check_nonzero_user(kmem, usermem, 2 * PAGE_SIZE);
+ /* Test usage of copy_struct_from_user(). */
+ ret |= test_copy_struct_from_user(kmem, usermem, 2 * PAGE_SIZE);
+
/*
* Invalid usage: none of these copies should succeed.
*/
diff --git a/lib/usercopy.c b/lib/usercopy.c
index c2bfbca..cbb4d9e 100644
--- a/lib/usercopy.c
+++ b/lib/usercopy.c
@@ -1,5 +1,6 @@
// SPDX-License-Identifier: GPL-2.0
#include <linux/uaccess.h>
+#include <linux/bitops.h>
/* out-of-line parts */
@@ -31,3 +32,57 @@ unsigned long _copy_to_user(void __user *to, const void *from, unsigned long n)
}
EXPORT_SYMBOL(_copy_to_user);
#endif
+
+/**
+ * check_zeroed_user: check if a userspace buffer only contains zero bytes
+ * @from: Source address, in userspace.
+ * @size: Size of buffer.
+ *
+ * This is effectively shorthand for "memchr_inv(from, 0, size) == NULL" for
+ * userspace addresses (and is more efficient because we don't care where the
+ * first non-zero byte is).
+ *
+ * Returns:
+ * * 0: There were non-zero bytes present in the buffer.
+ * * 1: The buffer was full of zero bytes.
+ * * -EFAULT: access to userspace failed.
+ */
+int check_zeroed_user(const void __user *from, size_t size)
+{
+ unsigned long val;
+ uintptr_t align = (uintptr_t) from % sizeof(unsigned long);
+
+ if (unlikely(size == 0))
+ return 1;
+
+ from -= align;
+ size += align;
+
+ if (!user_access_begin(from, size))
+ return -EFAULT;
+
+ unsafe_get_user(val, (unsigned long __user *) from, err_fault);
+ if (align)
+ val &= ~aligned_byte_mask(align);
+
+ while (size > sizeof(unsigned long)) {
+ if (unlikely(val))
+ goto done;
+
+ from += sizeof(unsigned long);
+ size -= sizeof(unsigned long);
+
+ unsafe_get_user(val, (unsigned long __user *) from, err_fault);
+ }
+
+ if (size < sizeof(unsigned long))
+ val &= aligned_byte_mask(size);
+
+done:
+ user_access_end();
+ return (val == 0);
+err_fault:
+ user_access_end();
+ return -EFAULT;
+}
+EXPORT_SYMBOL(check_zeroed_user);
diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index 62c591f..c5ec868 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -22,6 +22,7 @@
TEST_GEN_PROGS_x86_64 += x86_64/state_test
TEST_GEN_PROGS_x86_64 += x86_64/sync_regs_test
TEST_GEN_PROGS_x86_64 += x86_64/vmx_close_while_nested_test
+TEST_GEN_PROGS_x86_64 += x86_64/vmx_dirty_log_test
TEST_GEN_PROGS_x86_64 += x86_64/vmx_set_nested_state_test
TEST_GEN_PROGS_x86_64 += x86_64/vmx_tsc_adjust_test
TEST_GEN_PROGS_x86_64 += clear_dirty_log_test
@@ -48,7 +49,7 @@
-I$(LINUX_HDR_PATH) -Iinclude -I$(<D) -Iinclude/$(UNAME_M) -I..
no-pie-option := $(call try-run, echo 'int main() { return 0; }' | \
- $(CC) -Werror $(KBUILD_CPPFLAGS) $(CC_OPTION_CFLAGS) -no-pie -x c - -o "$$TMP", -no-pie)
+ $(CC) -Werror -no-pie -x c - -o "$$TMP", -no-pie)
# On s390, build the testcases KVM-enabled
pgste-option = $(call try-run, echo 'int main() { return 0; }' | \
diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h
index 0c17f2e..ff23401 100644
--- a/tools/testing/selftests/kvm/include/x86_64/processor.h
+++ b/tools/testing/selftests/kvm/include/x86_64/processor.h
@@ -1083,6 +1083,9 @@ void kvm_get_cpu_address_width(unsigned int *pa_bits, unsigned int *va_bits);
#define VMX_BASIC_MEM_TYPE_WB 6LLU
#define VMX_BASIC_INOUT 0x0040000000000000LLU
+/* VMX_EPT_VPID_CAP bits */
+#define VMX_EPT_VPID_CAP_AD_BITS (1ULL << 21)
+
/* MSR_IA32_VMX_MISC bits */
#define MSR_IA32_VMX_MISC_VMWRITE_SHADOW_RO_FIELDS (1ULL << 29)
#define MSR_IA32_VMX_MISC_PREEMPTION_TIMER_SCALE 0x1F
diff --git a/tools/testing/selftests/kvm/include/x86_64/vmx.h b/tools/testing/selftests/kvm/include/x86_64/vmx.h
index 69b1705..6ae5a47 100644
--- a/tools/testing/selftests/kvm/include/x86_64/vmx.h
+++ b/tools/testing/selftests/kvm/include/x86_64/vmx.h
@@ -569,6 +569,10 @@ struct vmx_pages {
void *enlightened_vmcs_hva;
uint64_t enlightened_vmcs_gpa;
void *enlightened_vmcs;
+
+ void *eptp_hva;
+ uint64_t eptp_gpa;
+ void *eptp;
};
struct vmx_pages *vcpu_alloc_vmx(struct kvm_vm *vm, vm_vaddr_t *p_vmx_gva);
@@ -576,4 +580,14 @@ bool prepare_for_vmx_operation(struct vmx_pages *vmx);
void prepare_vmcs(struct vmx_pages *vmx, void *guest_rip, void *guest_rsp);
bool load_vmcs(struct vmx_pages *vmx);
+void nested_pg_map(struct vmx_pages *vmx, struct kvm_vm *vm,
+ uint64_t nested_paddr, uint64_t paddr, uint32_t eptp_memslot);
+void nested_map(struct vmx_pages *vmx, struct kvm_vm *vm,
+ uint64_t nested_paddr, uint64_t paddr, uint64_t size,
+ uint32_t eptp_memslot);
+void nested_map_memslot(struct vmx_pages *vmx, struct kvm_vm *vm,
+ uint32_t memslot, uint32_t eptp_memslot);
+void prepare_eptp(struct vmx_pages *vmx, struct kvm_vm *vm,
+ uint32_t eptp_memslot);
+
#endif /* SELFTEST_KVM_VMX_H */
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index 80a338b..41cf454 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -705,7 +705,7 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm,
* on error (e.g. currently no memory region using memslot as a KVM
* memory slot ID).
*/
-static struct userspace_mem_region *
+struct userspace_mem_region *
memslot2region(struct kvm_vm *vm, uint32_t memslot)
{
struct userspace_mem_region *region;
diff --git a/tools/testing/selftests/kvm/lib/kvm_util_internal.h b/tools/testing/selftests/kvm/lib/kvm_util_internal.h
index f36262e..ac50c42 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util_internal.h
+++ b/tools/testing/selftests/kvm/lib/kvm_util_internal.h
@@ -68,4 +68,7 @@ void virt_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent);
void regs_dump(FILE *stream, struct kvm_regs *regs, uint8_t indent);
void sregs_dump(FILE *stream, struct kvm_sregs *sregs, uint8_t indent);
+struct userspace_mem_region *
+memslot2region(struct kvm_vm *vm, uint32_t memslot);
+
#endif /* SELFTEST_KVM_UTIL_INTERNAL_H */
diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c
index c53dbc6..6698cb7 100644
--- a/tools/testing/selftests/kvm/lib/x86_64/processor.c
+++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c
@@ -1085,7 +1085,7 @@ struct kvm_x86_state *vcpu_save_state(struct kvm_vm *vm, uint32_t vcpuid)
for (i = 0; i < nmsrs; i++)
state->msrs.entries[i].index = list->indices[i];
r = ioctl(vcpu->fd, KVM_GET_MSRS, &state->msrs);
- TEST_ASSERT(r == nmsrs, "Unexpected result from KVM_GET_MSRS, r: %i (failed at %x)",
+ TEST_ASSERT(r == nmsrs, "Unexpected result from KVM_GET_MSRS, r: %i (failed MSR was 0x%x)",
r, r == nmsrs ? -1 : list->indices[r]);
r = ioctl(vcpu->fd, KVM_GET_DEBUGREGS, &state->debugregs);
diff --git a/tools/testing/selftests/kvm/lib/x86_64/vmx.c b/tools/testing/selftests/kvm/lib/x86_64/vmx.c
index 9cef045..fab8f6b 100644
--- a/tools/testing/selftests/kvm/lib/x86_64/vmx.c
+++ b/tools/testing/selftests/kvm/lib/x86_64/vmx.c
@@ -7,11 +7,39 @@
#include "test_util.h"
#include "kvm_util.h"
+#include "../kvm_util_internal.h"
#include "processor.h"
#include "vmx.h"
+#define PAGE_SHIFT_4K 12
+
+#define KVM_EPT_PAGE_TABLE_MIN_PADDR 0x1c0000
+
bool enable_evmcs;
+struct eptPageTableEntry {
+ uint64_t readable:1;
+ uint64_t writable:1;
+ uint64_t executable:1;
+ uint64_t memory_type:3;
+ uint64_t ignore_pat:1;
+ uint64_t page_size:1;
+ uint64_t accessed:1;
+ uint64_t dirty:1;
+ uint64_t ignored_11_10:2;
+ uint64_t address:40;
+ uint64_t ignored_62_52:11;
+ uint64_t suppress_ve:1;
+};
+
+struct eptPageTablePointer {
+ uint64_t memory_type:3;
+ uint64_t page_walk_length:3;
+ uint64_t ad_enabled:1;
+ uint64_t reserved_11_07:5;
+ uint64_t address:40;
+ uint64_t reserved_63_52:12;
+};
int vcpu_enable_evmcs(struct kvm_vm *vm, int vcpu_id)
{
uint16_t evmcs_ver;
@@ -174,15 +202,35 @@ bool load_vmcs(struct vmx_pages *vmx)
*/
static inline void init_vmcs_control_fields(struct vmx_pages *vmx)
{
+ uint32_t sec_exec_ctl = 0;
+
vmwrite(VIRTUAL_PROCESSOR_ID, 0);
vmwrite(POSTED_INTR_NV, 0);
vmwrite(PIN_BASED_VM_EXEC_CONTROL, rdmsr(MSR_IA32_VMX_TRUE_PINBASED_CTLS));
- if (!vmwrite(SECONDARY_VM_EXEC_CONTROL, 0))
+
+ if (vmx->eptp_gpa) {
+ uint64_t ept_paddr;
+ struct eptPageTablePointer eptp = {
+ .memory_type = VMX_BASIC_MEM_TYPE_WB,
+ .page_walk_length = 3, /* + 1 */
+ .ad_enabled = !!(rdmsr(MSR_IA32_VMX_EPT_VPID_CAP) & VMX_EPT_VPID_CAP_AD_BITS),
+ .address = vmx->eptp_gpa >> PAGE_SHIFT_4K,
+ };
+
+ memcpy(&ept_paddr, &eptp, sizeof(ept_paddr));
+ vmwrite(EPT_POINTER, ept_paddr);
+ sec_exec_ctl |= SECONDARY_EXEC_ENABLE_EPT;
+ }
+
+ if (!vmwrite(SECONDARY_VM_EXEC_CONTROL, sec_exec_ctl))
vmwrite(CPU_BASED_VM_EXEC_CONTROL,
rdmsr(MSR_IA32_VMX_TRUE_PROCBASED_CTLS) | CPU_BASED_ACTIVATE_SECONDARY_CONTROLS);
- else
+ else {
vmwrite(CPU_BASED_VM_EXEC_CONTROL, rdmsr(MSR_IA32_VMX_TRUE_PROCBASED_CTLS));
+ GUEST_ASSERT(!sec_exec_ctl);
+ }
+
vmwrite(EXCEPTION_BITMAP, 0);
vmwrite(PAGE_FAULT_ERROR_CODE_MASK, 0);
vmwrite(PAGE_FAULT_ERROR_CODE_MATCH, -1); /* Never match */
@@ -327,3 +375,152 @@ void prepare_vmcs(struct vmx_pages *vmx, void *guest_rip, void *guest_rsp)
init_vmcs_host_state();
init_vmcs_guest_state(guest_rip, guest_rsp);
}
+
+void nested_pg_map(struct vmx_pages *vmx, struct kvm_vm *vm,
+ uint64_t nested_paddr, uint64_t paddr, uint32_t eptp_memslot)
+{
+ uint16_t index[4];
+ struct eptPageTableEntry *pml4e;
+
+ TEST_ASSERT(vm->mode == VM_MODE_PXXV48_4K, "Attempt to use "
+ "unknown or unsupported guest mode, mode: 0x%x", vm->mode);
+
+ TEST_ASSERT((nested_paddr % vm->page_size) == 0,
+ "Nested physical address not on page boundary,\n"
+ " nested_paddr: 0x%lx vm->page_size: 0x%x",
+ nested_paddr, vm->page_size);
+ TEST_ASSERT((nested_paddr >> vm->page_shift) <= vm->max_gfn,
+ "Physical address beyond beyond maximum supported,\n"
+ " nested_paddr: 0x%lx vm->max_gfn: 0x%lx vm->page_size: 0x%x",
+ paddr, vm->max_gfn, vm->page_size);
+ TEST_ASSERT((paddr % vm->page_size) == 0,
+ "Physical address not on page boundary,\n"
+ " paddr: 0x%lx vm->page_size: 0x%x",
+ paddr, vm->page_size);
+ TEST_ASSERT((paddr >> vm->page_shift) <= vm->max_gfn,
+ "Physical address beyond beyond maximum supported,\n"
+ " paddr: 0x%lx vm->max_gfn: 0x%lx vm->page_size: 0x%x",
+ paddr, vm->max_gfn, vm->page_size);
+
+ index[0] = (nested_paddr >> 12) & 0x1ffu;
+ index[1] = (nested_paddr >> 21) & 0x1ffu;
+ index[2] = (nested_paddr >> 30) & 0x1ffu;
+ index[3] = (nested_paddr >> 39) & 0x1ffu;
+
+ /* Allocate page directory pointer table if not present. */
+ pml4e = vmx->eptp_hva;
+ if (!pml4e[index[3]].readable) {
+ pml4e[index[3]].address = vm_phy_page_alloc(vm,
+ KVM_EPT_PAGE_TABLE_MIN_PADDR, eptp_memslot)
+ >> vm->page_shift;
+ pml4e[index[3]].writable = true;
+ pml4e[index[3]].readable = true;
+ pml4e[index[3]].executable = true;
+ }
+
+ /* Allocate page directory table if not present. */
+ struct eptPageTableEntry *pdpe;
+ pdpe = addr_gpa2hva(vm, pml4e[index[3]].address * vm->page_size);
+ if (!pdpe[index[2]].readable) {
+ pdpe[index[2]].address = vm_phy_page_alloc(vm,
+ KVM_EPT_PAGE_TABLE_MIN_PADDR, eptp_memslot)
+ >> vm->page_shift;
+ pdpe[index[2]].writable = true;
+ pdpe[index[2]].readable = true;
+ pdpe[index[2]].executable = true;
+ }
+
+ /* Allocate page table if not present. */
+ struct eptPageTableEntry *pde;
+ pde = addr_gpa2hva(vm, pdpe[index[2]].address * vm->page_size);
+ if (!pde[index[1]].readable) {
+ pde[index[1]].address = vm_phy_page_alloc(vm,
+ KVM_EPT_PAGE_TABLE_MIN_PADDR, eptp_memslot)
+ >> vm->page_shift;
+ pde[index[1]].writable = true;
+ pde[index[1]].readable = true;
+ pde[index[1]].executable = true;
+ }
+
+ /* Fill in page table entry. */
+ struct eptPageTableEntry *pte;
+ pte = addr_gpa2hva(vm, pde[index[1]].address * vm->page_size);
+ pte[index[0]].address = paddr >> vm->page_shift;
+ pte[index[0]].writable = true;
+ pte[index[0]].readable = true;
+ pte[index[0]].executable = true;
+
+ /*
+ * For now mark these as accessed and dirty because the only
+ * testcase we have needs that. Can be reconsidered later.
+ */
+ pte[index[0]].accessed = true;
+ pte[index[0]].dirty = true;
+}
+
+/*
+ * Map a range of EPT guest physical addresses to the VM's physical address
+ *
+ * Input Args:
+ * vm - Virtual Machine
+ * nested_paddr - Nested guest physical address to map
+ * paddr - VM Physical Address
+ * size - The size of the range to map
+ * eptp_memslot - Memory region slot for new virtual translation tables
+ *
+ * Output Args: None
+ *
+ * Return: None
+ *
+ * Within the VM given by vm, creates a nested guest translation for the
+ * page range starting at nested_paddr to the page range starting at paddr.
+ */
+void nested_map(struct vmx_pages *vmx, struct kvm_vm *vm,
+ uint64_t nested_paddr, uint64_t paddr, uint64_t size,
+ uint32_t eptp_memslot)
+{
+ size_t page_size = vm->page_size;
+ size_t npages = size / page_size;
+
+ TEST_ASSERT(nested_paddr + size > nested_paddr, "Vaddr overflow");
+ TEST_ASSERT(paddr + size > paddr, "Paddr overflow");
+
+ while (npages--) {
+ nested_pg_map(vmx, vm, nested_paddr, paddr, eptp_memslot);
+ nested_paddr += page_size;
+ paddr += page_size;
+ }
+}
+
+/* Prepare an identity extended page table that maps all the
+ * physical pages in VM.
+ */
+void nested_map_memslot(struct vmx_pages *vmx, struct kvm_vm *vm,
+ uint32_t memslot, uint32_t eptp_memslot)
+{
+ sparsebit_idx_t i, last;
+ struct userspace_mem_region *region =
+ memslot2region(vm, memslot);
+
+ i = (region->region.guest_phys_addr >> vm->page_shift) - 1;
+ last = i + (region->region.memory_size >> vm->page_shift);
+ for (;;) {
+ i = sparsebit_next_clear(region->unused_phy_pages, i);
+ if (i > last)
+ break;
+
+ nested_map(vmx, vm,
+ (uint64_t)i << vm->page_shift,
+ (uint64_t)i << vm->page_shift,
+ 1 << vm->page_shift,
+ eptp_memslot);
+ }
+}
+
+void prepare_eptp(struct vmx_pages *vmx, struct kvm_vm *vm,
+ uint32_t eptp_memslot)
+{
+ vmx->eptp = (void *)vm_vaddr_alloc(vm, getpagesize(), 0x10000, 0, 0);
+ vmx->eptp_hva = addr_gva2hva(vm, (uintptr_t)vmx->eptp);
+ vmx->eptp_gpa = addr_gva2gpa(vm, (uintptr_t)vmx->eptp);
+}
diff --git a/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c b/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c
new file mode 100644
index 0000000..0bca1cf
--- /dev/null
+++ b/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c
@@ -0,0 +1,156 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * KVM dirty page logging test
+ *
+ * Copyright (C) 2018, Red Hat, Inc.
+ */
+
+#define _GNU_SOURCE /* for program_invocation_name */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <linux/bitmap.h>
+#include <linux/bitops.h>
+
+#include "test_util.h"
+#include "kvm_util.h"
+#include "processor.h"
+#include "vmx.h"
+
+#define VCPU_ID 1
+
+/* The memory slot index to track dirty pages */
+#define TEST_MEM_SLOT_INDEX 1
+#define TEST_MEM_SIZE 3
+
+/* L1 guest test virtual memory offset */
+#define GUEST_TEST_MEM 0xc0000000
+
+/* L2 guest test virtual memory offset */
+#define NESTED_TEST_MEM1 0xc0001000
+#define NESTED_TEST_MEM2 0xc0002000
+
+static void l2_guest_code(void)
+{
+ *(volatile uint64_t *)NESTED_TEST_MEM1;
+ *(volatile uint64_t *)NESTED_TEST_MEM1 = 1;
+ GUEST_SYNC(true);
+ GUEST_SYNC(false);
+
+ *(volatile uint64_t *)NESTED_TEST_MEM2 = 1;
+ GUEST_SYNC(true);
+ *(volatile uint64_t *)NESTED_TEST_MEM2 = 1;
+ GUEST_SYNC(true);
+ GUEST_SYNC(false);
+
+ /* Exit to L1 and never come back. */
+ vmcall();
+}
+
+void l1_guest_code(struct vmx_pages *vmx)
+{
+#define L2_GUEST_STACK_SIZE 64
+ unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE];
+
+ GUEST_ASSERT(vmx->vmcs_gpa);
+ GUEST_ASSERT(prepare_for_vmx_operation(vmx));
+ GUEST_ASSERT(load_vmcs(vmx));
+
+ prepare_vmcs(vmx, l2_guest_code,
+ &l2_guest_stack[L2_GUEST_STACK_SIZE]);
+
+ GUEST_SYNC(false);
+ GUEST_ASSERT(!vmlaunch());
+ GUEST_SYNC(false);
+ GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_VMCALL);
+ GUEST_DONE();
+}
+
+int main(int argc, char *argv[])
+{
+ vm_vaddr_t vmx_pages_gva = 0;
+ struct vmx_pages *vmx;
+ unsigned long *bmap;
+ uint64_t *host_test_mem;
+
+ struct kvm_vm *vm;
+ struct kvm_run *run;
+ struct ucall uc;
+ bool done = false;
+
+ /* Create VM */
+ vm = vm_create_default(VCPU_ID, 0, l1_guest_code);
+ vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
+ vmx = vcpu_alloc_vmx(vm, &vmx_pages_gva);
+ vcpu_args_set(vm, VCPU_ID, 1, vmx_pages_gva);
+ run = vcpu_state(vm, VCPU_ID);
+
+ /* Add an extra memory slot for testing dirty logging */
+ vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS,
+ GUEST_TEST_MEM,
+ TEST_MEM_SLOT_INDEX,
+ TEST_MEM_SIZE,
+ KVM_MEM_LOG_DIRTY_PAGES);
+
+ /*
+ * Add an identity map for GVA range [0xc0000000, 0xc0002000). This
+ * affects both L1 and L2. However...
+ */
+ virt_map(vm, GUEST_TEST_MEM, GUEST_TEST_MEM,
+ TEST_MEM_SIZE * 4096, 0);
+
+ /*
+ * ... pages in the L2 GPA range [0xc0001000, 0xc0003000) will map to
+ * 0xc0000000.
+ *
+ * Note that prepare_eptp should be called only L1's GPA map is done,
+ * meaning after the last call to virt_map.
+ */
+ prepare_eptp(vmx, vm, 0);
+ nested_map_memslot(vmx, vm, 0, 0);
+ nested_map(vmx, vm, NESTED_TEST_MEM1, GUEST_TEST_MEM, 4096, 0);
+ nested_map(vmx, vm, NESTED_TEST_MEM2, GUEST_TEST_MEM, 4096, 0);
+
+ bmap = bitmap_alloc(TEST_MEM_SIZE);
+ host_test_mem = addr_gpa2hva(vm, GUEST_TEST_MEM);
+
+ while (!done) {
+ memset(host_test_mem, 0xaa, TEST_MEM_SIZE * 4096);
+ _vcpu_run(vm, VCPU_ID);
+ TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
+ "Unexpected exit reason: %u (%s),\n",
+ run->exit_reason,
+ exit_reason_str(run->exit_reason));
+
+ switch (get_ucall(vm, VCPU_ID, &uc)) {
+ case UCALL_ABORT:
+ TEST_ASSERT(false, "%s at %s:%d", (const char *)uc.args[0],
+ __FILE__, uc.args[1]);
+ /* NOT REACHED */
+ case UCALL_SYNC:
+ /*
+ * The nested guest wrote at offset 0x1000 in the memslot, but the
+ * dirty bitmap must be filled in according to L1 GPA, not L2.
+ */
+ kvm_vm_get_dirty_log(vm, TEST_MEM_SLOT_INDEX, bmap);
+ if (uc.args[1]) {
+ TEST_ASSERT(test_bit(0, bmap), "Page 0 incorrectly reported clean\n");
+ TEST_ASSERT(host_test_mem[0] == 1, "Page 0 not written by guest\n");
+ } else {
+ TEST_ASSERT(!test_bit(0, bmap), "Page 0 incorrectly reported dirty\n");
+ TEST_ASSERT(host_test_mem[0] == 0xaaaaaaaaaaaaaaaaULL, "Page 0 written by guest\n");
+ }
+
+ TEST_ASSERT(!test_bit(1, bmap), "Page 1 incorrectly reported dirty\n");
+ TEST_ASSERT(host_test_mem[4096 / 8] == 0xaaaaaaaaaaaaaaaaULL, "Page 1 written by guest\n");
+ TEST_ASSERT(!test_bit(2, bmap), "Page 2 incorrectly reported dirty\n");
+ TEST_ASSERT(host_test_mem[8192 / 8] == 0xaaaaaaaaaaaaaaaaULL, "Page 2 written by guest\n");
+ break;
+ case UCALL_DONE:
+ done = true;
+ break;
+ default:
+ TEST_ASSERT(false, "Unknown ucall 0x%x.", uc.cmd);
+ }
+ }
+}
diff --git a/tools/testing/selftests/pidfd/Makefile b/tools/testing/selftests/pidfd/Makefile
index 464c9b7..7550f08 100644
--- a/tools/testing/selftests/pidfd/Makefile
+++ b/tools/testing/selftests/pidfd/Makefile
@@ -1,5 +1,5 @@
# SPDX-License-Identifier: GPL-2.0-only
-CFLAGS += -g -I../../../../usr/include/ -lpthread
+CFLAGS += -g -I../../../../usr/include/ -pthread
TEST_GEN_PROGS := pidfd_test pidfd_open_test pidfd_poll_test pidfd_wait
diff --git a/virt/kvm/arm/vgic/trace.h b/virt/kvm/arm/vgic/trace.h
index 55fed77..4fd4f6d 100644
--- a/virt/kvm/arm/vgic/trace.h
+++ b/virt/kvm/arm/vgic/trace.h
@@ -30,7 +30,7 @@ TRACE_EVENT(vgic_update_irq_pending,
#endif /* _TRACE_VGIC_H */
#undef TRACE_INCLUDE_PATH
-#define TRACE_INCLUDE_PATH ../../../virt/kvm/arm/vgic
+#define TRACE_INCLUDE_PATH ../../virt/kvm/arm/vgic
#undef TRACE_INCLUDE_FILE
#define TRACE_INCLUDE_FILE trace
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index e6de315..fd68fbe 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -617,8 +617,9 @@ static int kvm_create_vm_debugfs(struct kvm *kvm, int fd)
stat_data->kvm = kvm;
stat_data->offset = p->offset;
+ stat_data->mode = p->mode ? p->mode : 0644;
kvm->debugfs_stat_data[p - debugfs_entries] = stat_data;
- debugfs_create_file(p->name, 0644, kvm->debugfs_dentry,
+ debugfs_create_file(p->name, stat_data->mode, kvm->debugfs_dentry,
stat_data, stat_fops_per_vm[p->kind]);
}
return 0;
@@ -3929,7 +3930,9 @@ static int kvm_debugfs_open(struct inode *inode, struct file *file,
if (!refcount_inc_not_zero(&stat_data->kvm->users_count))
return -ENOENT;
- if (simple_attr_open(inode, file, get, set, fmt)) {
+ if (simple_attr_open(inode, file, get,
+ stat_data->mode & S_IWUGO ? set : NULL,
+ fmt)) {
kvm_put_kvm(stat_data->kvm);
return -ENOMEM;
}
@@ -4177,7 +4180,8 @@ static void kvm_init_debug(void)
kvm_debugfs_num_entries = 0;
for (p = debugfs_entries; p->name; ++p, kvm_debugfs_num_entries++) {
- debugfs_create_file(p->name, 0644, kvm_debugfs_dir,
+ int mode = p->mode ? p->mode : 0644;
+ debugfs_create_file(p->name, mode, kvm_debugfs_dir,
(void *)(long)p->offset,
stat_fops[p->kind]);
}