* [PATCH v3 07/15] x86/paravirt: remove clobbers from struct paravirt_patch_site
From: Juergen Gross @ 2018-08-28 7:40 UTC (permalink / raw)
To: linux-kernel, xen-devel, x86, virtualization
Cc: Juergen Gross, boris.ostrovsky, rusty, mingo, hpa, akataria, tglx
In-Reply-To: <20180828074026.820-1-jgross@suse.com>
There is no need any longer to store the clobbers in struct
paravirt_patch_site. Remove clobbers from the struct and from the
related macros.
While at it fix some lines longer than 80 characters.
Signed-off-by: Juergen Gross <jgross@suse.com>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
---
arch/x86/include/asm/paravirt.h | 33 +++++++++++++++------------------
arch/x86/include/asm/paravirt_types.h | 1 -
2 files changed, 15 insertions(+), 19 deletions(-)
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index e375d4266b53..e1364cb40ce5 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -827,7 +827,7 @@ extern void default_banner(void);
#else /* __ASSEMBLY__ */
-#define _PVSITE(ptype, clobbers, ops, word, algn) \
+#define _PVSITE(ptype, ops, word, algn) \
771:; \
ops; \
772:; \
@@ -836,7 +836,6 @@ extern void default_banner(void);
word 771b; \
.byte ptype; \
.byte 772b-771b; \
- .short clobbers; \
.popsection
@@ -869,7 +868,7 @@ extern void default_banner(void);
COND_POP(set, CLBR_RAX, rax)
#define PARA_PATCH(struct, off) ((PARAVIRT_PATCH_##struct + (off)) / 8)
-#define PARA_SITE(ptype, clobbers, ops) _PVSITE(ptype, clobbers, ops, .quad, 8)
+#define PARA_SITE(ptype, ops) _PVSITE(ptype, ops, .quad, 8)
#define PARA_INDIRECT(addr) *addr(%rip)
#else
#define PV_SAVE_REGS(set) \
@@ -884,26 +883,26 @@ extern void default_banner(void);
COND_POP(set, CLBR_EAX, eax)
#define PARA_PATCH(struct, off) ((PARAVIRT_PATCH_##struct + (off)) / 4)
-#define PARA_SITE(ptype, clobbers, ops) _PVSITE(ptype, clobbers, ops, .long, 4)
+#define PARA_SITE(ptype, ops) _PVSITE(ptype, ops, .long, 4)
#define PARA_INDIRECT(addr) *%cs:addr
#endif
#define INTERRUPT_RETURN \
- PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_iret), CLBR_NONE, \
- ANNOTATE_RETPOLINE_SAFE; \
+ PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_iret), \
+ ANNOTATE_RETPOLINE_SAFE; \
jmp PARA_INDIRECT(pv_cpu_ops+PV_CPU_iret);)
#define DISABLE_INTERRUPTS(clobbers) \
- PARA_SITE(PARA_PATCH(pv_irq_ops, PV_IRQ_irq_disable), clobbers, \
+ PARA_SITE(PARA_PATCH(pv_irq_ops, PV_IRQ_irq_disable), \
PV_SAVE_REGS(clobbers | CLBR_CALLEE_SAVE); \
- ANNOTATE_RETPOLINE_SAFE; \
+ ANNOTATE_RETPOLINE_SAFE; \
call PARA_INDIRECT(pv_irq_ops+PV_IRQ_irq_disable); \
PV_RESTORE_REGS(clobbers | CLBR_CALLEE_SAVE);)
#define ENABLE_INTERRUPTS(clobbers) \
- PARA_SITE(PARA_PATCH(pv_irq_ops, PV_IRQ_irq_enable), clobbers, \
+ PARA_SITE(PARA_PATCH(pv_irq_ops, PV_IRQ_irq_enable), \
PV_SAVE_REGS(clobbers | CLBR_CALLEE_SAVE); \
- ANNOTATE_RETPOLINE_SAFE; \
+ ANNOTATE_RETPOLINE_SAFE; \
call PARA_INDIRECT(pv_irq_ops+PV_IRQ_irq_enable); \
PV_RESTORE_REGS(clobbers | CLBR_CALLEE_SAVE);)
@@ -921,8 +920,7 @@ extern void default_banner(void);
* inlined, or the swapgs instruction must be trapped and emulated.
*/
#define SWAPGS_UNSAFE_STACK \
- PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_swapgs), CLBR_NONE, \
- swapgs)
+ PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_swapgs), swapgs)
/*
* Note: swapgs is very special, and in practise is either going to be
@@ -931,8 +929,8 @@ extern void default_banner(void);
* it.
*/
#define SWAPGS \
- PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_swapgs), CLBR_NONE, \
- ANNOTATE_RETPOLINE_SAFE; \
+ PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_swapgs), \
+ ANNOTATE_RETPOLINE_SAFE; \
call PARA_INDIRECT(pv_cpu_ops+PV_CPU_swapgs); \
)
@@ -942,15 +940,14 @@ extern void default_banner(void);
#define USERGS_SYSRET64 \
PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_usergs_sysret64), \
- CLBR_NONE, \
- ANNOTATE_RETPOLINE_SAFE; \
+ ANNOTATE_RETPOLINE_SAFE; \
jmp PARA_INDIRECT(pv_cpu_ops+PV_CPU_usergs_sysret64);)
#ifdef CONFIG_DEBUG_ENTRY
#define SAVE_FLAGS(clobbers) \
- PARA_SITE(PARA_PATCH(pv_irq_ops, PV_IRQ_save_fl), clobbers, \
+ PARA_SITE(PARA_PATCH(pv_irq_ops, PV_IRQ_save_fl), \
PV_SAVE_REGS(clobbers | CLBR_CALLEE_SAVE); \
- ANNOTATE_RETPOLINE_SAFE; \
+ ANNOTATE_RETPOLINE_SAFE; \
call PARA_INDIRECT(pv_irq_ops+PV_IRQ_save_fl); \
PV_RESTORE_REGS(clobbers | CLBR_CALLEE_SAVE);)
#endif
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index 225d871373ed..b2220536a7d4 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -681,7 +681,6 @@ struct paravirt_patch_site {
u8 *instr; /* original instructions */
u8 instrtype; /* type of this instruction */
u8 len; /* length of original instruction */
- u16 clobbers; /* what registers you may clobber */
};
extern struct paravirt_patch_site __parainstructions[],
--
2.16.4
^ permalink raw reply related
* [PATCH v3 08/15] x86/paravirt: use a single ops structure
From: Juergen Gross @ 2018-08-28 7:40 UTC (permalink / raw)
To: linux-kernel, xen-devel, x86, virtualization
Cc: Juergen Gross, boris.ostrovsky, rusty, mingo, hpa, akataria, tglx
In-Reply-To: <20180828074026.820-1-jgross@suse.com>
Instead of using six globally visible paravirt ops structures combine
them in a single structure, keeping the original structures as
sub-structures.
This avoids the need to assemble struct paravirt_patch_template at
runtime on the stack each time apply_paravirt() is being called (i.e.
when loading a module).
Signed-off-by: Juergen Gross <jgross@suse.com>
---
V2:
- shorten pv_ops sub-structure names (Jan Beulich)
V3:
- rebase to master
- fix build failure on ARM
---
arch/arm/include/asm/paravirt.h | 9 +-
arch/arm/kernel/paravirt.c | 4 +-
arch/arm64/include/asm/paravirt.h | 9 +-
arch/arm64/kernel/paravirt.c | 4 +-
arch/x86/hyperv/mmu.c | 4 +-
arch/x86/include/asm/paravirt.h | 275 +++++++++++++++------------------
arch/x86/include/asm/paravirt_types.h | 25 ++-
arch/x86/kernel/alternative.c | 2 +-
arch/x86/kernel/asm-offsets.c | 12 +-
arch/x86/kernel/asm-offsets_64.c | 7 +-
arch/x86/kernel/cpu/common.c | 2 +-
arch/x86/kernel/cpu/vmware.c | 4 +-
arch/x86/kernel/kvm.c | 19 +--
arch/x86/kernel/kvmclock.c | 4 +-
arch/x86/kernel/paravirt-spinlocks.c | 15 +-
arch/x86/kernel/paravirt.c | 283 ++++++++++++++++------------------
arch/x86/kernel/paravirt_patch_32.c | 48 +++---
arch/x86/kernel/paravirt_patch_64.c | 56 +++----
arch/x86/kernel/tsc.c | 2 +-
arch/x86/kernel/vsmp_64.c | 18 +--
arch/x86/xen/enlighten_pv.c | 31 ++--
arch/x86/xen/irq.c | 2 +-
arch/x86/xen/mmu_hvm.c | 2 +-
arch/x86/xen/mmu_pv.c | 28 ++--
arch/x86/xen/spinlock.c | 11 +-
arch/x86/xen/time.c | 4 +-
drivers/xen/time.c | 2 +-
27 files changed, 427 insertions(+), 455 deletions(-)
diff --git a/arch/arm/include/asm/paravirt.h b/arch/arm/include/asm/paravirt.h
index d51e5cd31d01..cdbf02d9c1d4 100644
--- a/arch/arm/include/asm/paravirt.h
+++ b/arch/arm/include/asm/paravirt.h
@@ -10,11 +10,16 @@ extern struct static_key paravirt_steal_rq_enabled;
struct pv_time_ops {
unsigned long long (*steal_clock)(int cpu);
};
-extern struct pv_time_ops pv_time_ops;
+
+struct paravirt_patch_template {
+ struct pv_time_ops time;
+};
+
+extern struct paravirt_patch_template pv_ops;
static inline u64 paravirt_steal_clock(int cpu)
{
- return pv_time_ops.steal_clock(cpu);
+ return pv_ops.time.steal_clock(cpu);
}
#endif
diff --git a/arch/arm/kernel/paravirt.c b/arch/arm/kernel/paravirt.c
index 53f371ed4568..75c158b0353f 100644
--- a/arch/arm/kernel/paravirt.c
+++ b/arch/arm/kernel/paravirt.c
@@ -21,5 +21,5 @@
struct static_key paravirt_steal_enabled;
struct static_key paravirt_steal_rq_enabled;
-struct pv_time_ops pv_time_ops;
-EXPORT_SYMBOL_GPL(pv_time_ops);
+struct paravirt_patch_template pv_ops;
+EXPORT_SYMBOL_GPL(pv_ops);
diff --git a/arch/arm64/include/asm/paravirt.h b/arch/arm64/include/asm/paravirt.h
index bb5dcea42003..799d9dd6f7cc 100644
--- a/arch/arm64/include/asm/paravirt.h
+++ b/arch/arm64/include/asm/paravirt.h
@@ -10,11 +10,16 @@ extern struct static_key paravirt_steal_rq_enabled;
struct pv_time_ops {
unsigned long long (*steal_clock)(int cpu);
};
-extern struct pv_time_ops pv_time_ops;
+
+struct paravirt_patch_template {
+ struct pv_time_ops time;
+};
+
+extern struct paravirt_patch_template pv_ops;
static inline u64 paravirt_steal_clock(int cpu)
{
- return pv_time_ops.steal_clock(cpu);
+ return pv_ops.time.steal_clock(cpu);
}
#endif
diff --git a/arch/arm64/kernel/paravirt.c b/arch/arm64/kernel/paravirt.c
index 53f371ed4568..75c158b0353f 100644
--- a/arch/arm64/kernel/paravirt.c
+++ b/arch/arm64/kernel/paravirt.c
@@ -21,5 +21,5 @@
struct static_key paravirt_steal_enabled;
struct static_key paravirt_steal_rq_enabled;
-struct pv_time_ops pv_time_ops;
-EXPORT_SYMBOL_GPL(pv_time_ops);
+struct paravirt_patch_template pv_ops;
+EXPORT_SYMBOL_GPL(pv_ops);
diff --git a/arch/x86/hyperv/mmu.c b/arch/x86/hyperv/mmu.c
index ef5f29f913d7..e65d7fe6489f 100644
--- a/arch/x86/hyperv/mmu.c
+++ b/arch/x86/hyperv/mmu.c
@@ -231,6 +231,6 @@ void hyperv_setup_mmu_ops(void)
return;
pr_info("Using hypercall for remote TLB flush\n");
- pv_mmu_ops.flush_tlb_others = hyperv_flush_tlb_others;
- pv_mmu_ops.tlb_remove_table = tlb_remove_table;
+ pv_ops.mmu.flush_tlb_others = hyperv_flush_tlb_others;
+ pv_ops.mmu.tlb_remove_table = tlb_remove_table;
}
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index e1364cb40ce5..a9189b81c7dd 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -19,14 +19,14 @@
static inline void load_sp0(unsigned long sp0)
{
- PVOP_VCALL1(pv_cpu_ops.load_sp0, sp0);
+ PVOP_VCALL1(cpu.load_sp0, sp0);
}
/* The paravirtualized CPUID instruction. */
static inline void __cpuid(unsigned int *eax, unsigned int *ebx,
unsigned int *ecx, unsigned int *edx)
{
- PVOP_VCALL4(pv_cpu_ops.cpuid, eax, ebx, ecx, edx);
+ PVOP_VCALL4(cpu.cpuid, eax, ebx, ecx, edx);
}
/*
@@ -34,98 +34,98 @@ static inline void __cpuid(unsigned int *eax, unsigned int *ebx,
*/
static inline unsigned long paravirt_get_debugreg(int reg)
{
- return PVOP_CALL1(unsigned long, pv_cpu_ops.get_debugreg, reg);
+ return PVOP_CALL1(unsigned long, cpu.get_debugreg, reg);
}
#define get_debugreg(var, reg) var = paravirt_get_debugreg(reg)
static inline void set_debugreg(unsigned long val, int reg)
{
- PVOP_VCALL2(pv_cpu_ops.set_debugreg, reg, val);
+ PVOP_VCALL2(cpu.set_debugreg, reg, val);
}
static inline unsigned long read_cr0(void)
{
- return PVOP_CALL0(unsigned long, pv_cpu_ops.read_cr0);
+ return PVOP_CALL0(unsigned long, cpu.read_cr0);
}
static inline void write_cr0(unsigned long x)
{
- PVOP_VCALL1(pv_cpu_ops.write_cr0, x);
+ PVOP_VCALL1(cpu.write_cr0, x);
}
static inline unsigned long read_cr2(void)
{
- return PVOP_CALL0(unsigned long, pv_mmu_ops.read_cr2);
+ return PVOP_CALL0(unsigned long, mmu.read_cr2);
}
static inline void write_cr2(unsigned long x)
{
- PVOP_VCALL1(pv_mmu_ops.write_cr2, x);
+ PVOP_VCALL1(mmu.write_cr2, x);
}
static inline unsigned long __read_cr3(void)
{
- return PVOP_CALL0(unsigned long, pv_mmu_ops.read_cr3);
+ return PVOP_CALL0(unsigned long, mmu.read_cr3);
}
static inline void write_cr3(unsigned long x)
{
- PVOP_VCALL1(pv_mmu_ops.write_cr3, x);
+ PVOP_VCALL1(mmu.write_cr3, x);
}
static inline void __write_cr4(unsigned long x)
{
- PVOP_VCALL1(pv_cpu_ops.write_cr4, x);
+ PVOP_VCALL1(cpu.write_cr4, x);
}
#ifdef CONFIG_X86_64
static inline unsigned long read_cr8(void)
{
- return PVOP_CALL0(unsigned long, pv_cpu_ops.read_cr8);
+ return PVOP_CALL0(unsigned long, cpu.read_cr8);
}
static inline void write_cr8(unsigned long x)
{
- PVOP_VCALL1(pv_cpu_ops.write_cr8, x);
+ PVOP_VCALL1(cpu.write_cr8, x);
}
#endif
static inline void arch_safe_halt(void)
{
- PVOP_VCALL0(pv_irq_ops.safe_halt);
+ PVOP_VCALL0(irq.safe_halt);
}
static inline void halt(void)
{
- PVOP_VCALL0(pv_irq_ops.halt);
+ PVOP_VCALL0(irq.halt);
}
static inline void wbinvd(void)
{
- PVOP_VCALL0(pv_cpu_ops.wbinvd);
+ PVOP_VCALL0(cpu.wbinvd);
}
#define get_kernel_rpl() (pv_info.kernel_rpl)
static inline u64 paravirt_read_msr(unsigned msr)
{
- return PVOP_CALL1(u64, pv_cpu_ops.read_msr, msr);
+ return PVOP_CALL1(u64, cpu.read_msr, msr);
}
static inline void paravirt_write_msr(unsigned msr,
unsigned low, unsigned high)
{
- PVOP_VCALL3(pv_cpu_ops.write_msr, msr, low, high);
+ PVOP_VCALL3(cpu.write_msr, msr, low, high);
}
static inline u64 paravirt_read_msr_safe(unsigned msr, int *err)
{
- return PVOP_CALL2(u64, pv_cpu_ops.read_msr_safe, msr, err);
+ return PVOP_CALL2(u64, cpu.read_msr_safe, msr, err);
}
static inline int paravirt_write_msr_safe(unsigned msr,
unsigned low, unsigned high)
{
- return PVOP_CALL3(int, pv_cpu_ops.write_msr_safe, msr, low, high);
+ return PVOP_CALL3(int, cpu.write_msr_safe, msr, low, high);
}
#define rdmsr(msr, val1, val2) \
@@ -172,7 +172,7 @@ static inline int rdmsrl_safe(unsigned msr, unsigned long long *p)
static inline unsigned long long paravirt_sched_clock(void)
{
- return PVOP_CALL0(unsigned long long, pv_time_ops.sched_clock);
+ return PVOP_CALL0(unsigned long long, time.sched_clock);
}
struct static_key;
@@ -181,12 +181,12 @@ extern struct static_key paravirt_steal_rq_enabled;
static inline u64 paravirt_steal_clock(int cpu)
{
- return PVOP_CALL1(u64, pv_time_ops.steal_clock, cpu);
+ return PVOP_CALL1(u64, time.steal_clock, cpu);
}
static inline unsigned long long paravirt_read_pmc(int counter)
{
- return PVOP_CALL1(u64, pv_cpu_ops.read_pmc, counter);
+ return PVOP_CALL1(u64, cpu.read_pmc, counter);
}
#define rdpmc(counter, low, high) \
@@ -200,166 +200,166 @@ do { \
static inline void paravirt_alloc_ldt(struct desc_struct *ldt, unsigned entries)
{
- PVOP_VCALL2(pv_cpu_ops.alloc_ldt, ldt, entries);
+ PVOP_VCALL2(cpu.alloc_ldt, ldt, entries);
}
static inline void paravirt_free_ldt(struct desc_struct *ldt, unsigned entries)
{
- PVOP_VCALL2(pv_cpu_ops.free_ldt, ldt, entries);
+ PVOP_VCALL2(cpu.free_ldt, ldt, entries);
}
static inline void load_TR_desc(void)
{
- PVOP_VCALL0(pv_cpu_ops.load_tr_desc);
+ PVOP_VCALL0(cpu.load_tr_desc);
}
static inline void load_gdt(const struct desc_ptr *dtr)
{
- PVOP_VCALL1(pv_cpu_ops.load_gdt, dtr);
+ PVOP_VCALL1(cpu.load_gdt, dtr);
}
static inline void load_idt(const struct desc_ptr *dtr)
{
- PVOP_VCALL1(pv_cpu_ops.load_idt, dtr);
+ PVOP_VCALL1(cpu.load_idt, dtr);
}
static inline void set_ldt(const void *addr, unsigned entries)
{
- PVOP_VCALL2(pv_cpu_ops.set_ldt, addr, entries);
+ PVOP_VCALL2(cpu.set_ldt, addr, entries);
}
static inline unsigned long paravirt_store_tr(void)
{
- return PVOP_CALL0(unsigned long, pv_cpu_ops.store_tr);
+ return PVOP_CALL0(unsigned long, cpu.store_tr);
}
#define store_tr(tr) ((tr) = paravirt_store_tr())
static inline void load_TLS(struct thread_struct *t, unsigned cpu)
{
- PVOP_VCALL2(pv_cpu_ops.load_tls, t, cpu);
+ PVOP_VCALL2(cpu.load_tls, t, cpu);
}
#ifdef CONFIG_X86_64
static inline void load_gs_index(unsigned int gs)
{
- PVOP_VCALL1(pv_cpu_ops.load_gs_index, gs);
+ PVOP_VCALL1(cpu.load_gs_index, gs);
}
#endif
static inline void write_ldt_entry(struct desc_struct *dt, int entry,
const void *desc)
{
- PVOP_VCALL3(pv_cpu_ops.write_ldt_entry, dt, entry, desc);
+ PVOP_VCALL3(cpu.write_ldt_entry, dt, entry, desc);
}
static inline void write_gdt_entry(struct desc_struct *dt, int entry,
void *desc, int type)
{
- PVOP_VCALL4(pv_cpu_ops.write_gdt_entry, dt, entry, desc, type);
+ PVOP_VCALL4(cpu.write_gdt_entry, dt, entry, desc, type);
}
static inline void write_idt_entry(gate_desc *dt, int entry, const gate_desc *g)
{
- PVOP_VCALL3(pv_cpu_ops.write_idt_entry, dt, entry, g);
+ PVOP_VCALL3(cpu.write_idt_entry, dt, entry, g);
}
static inline void set_iopl_mask(unsigned mask)
{
- PVOP_VCALL1(pv_cpu_ops.set_iopl_mask, mask);
+ PVOP_VCALL1(cpu.set_iopl_mask, mask);
}
/* The paravirtualized I/O functions */
static inline void slow_down_io(void)
{
- pv_cpu_ops.io_delay();
+ pv_ops.cpu.io_delay();
#ifdef REALLY_SLOW_IO
- pv_cpu_ops.io_delay();
- pv_cpu_ops.io_delay();
- pv_cpu_ops.io_delay();
+ pv_ops.cpu.io_delay();
+ pv_ops.cpu.io_delay();
+ pv_ops.cpu.io_delay();
#endif
}
static inline void paravirt_activate_mm(struct mm_struct *prev,
struct mm_struct *next)
{
- PVOP_VCALL2(pv_mmu_ops.activate_mm, prev, next);
+ PVOP_VCALL2(mmu.activate_mm, prev, next);
}
static inline void paravirt_arch_dup_mmap(struct mm_struct *oldmm,
struct mm_struct *mm)
{
- PVOP_VCALL2(pv_mmu_ops.dup_mmap, oldmm, mm);
+ PVOP_VCALL2(mmu.dup_mmap, oldmm, mm);
}
static inline void paravirt_arch_exit_mmap(struct mm_struct *mm)
{
- PVOP_VCALL1(pv_mmu_ops.exit_mmap, mm);
+ PVOP_VCALL1(mmu.exit_mmap, mm);
}
static inline void __flush_tlb(void)
{
- PVOP_VCALL0(pv_mmu_ops.flush_tlb_user);
+ PVOP_VCALL0(mmu.flush_tlb_user);
}
static inline void __flush_tlb_global(void)
{
- PVOP_VCALL0(pv_mmu_ops.flush_tlb_kernel);
+ PVOP_VCALL0(mmu.flush_tlb_kernel);
}
static inline void __flush_tlb_one_user(unsigned long addr)
{
- PVOP_VCALL1(pv_mmu_ops.flush_tlb_one_user, addr);
+ PVOP_VCALL1(mmu.flush_tlb_one_user, addr);
}
static inline void flush_tlb_others(const struct cpumask *cpumask,
const struct flush_tlb_info *info)
{
- PVOP_VCALL2(pv_mmu_ops.flush_tlb_others, cpumask, info);
+ PVOP_VCALL2(mmu.flush_tlb_others, cpumask, info);
}
static inline void paravirt_tlb_remove_table(struct mmu_gather *tlb, void *table)
{
- PVOP_VCALL2(pv_mmu_ops.tlb_remove_table, tlb, table);
+ PVOP_VCALL2(mmu.tlb_remove_table, tlb, table);
}
static inline int paravirt_pgd_alloc(struct mm_struct *mm)
{
- return PVOP_CALL1(int, pv_mmu_ops.pgd_alloc, mm);
+ return PVOP_CALL1(int, mmu.pgd_alloc, mm);
}
static inline void paravirt_pgd_free(struct mm_struct *mm, pgd_t *pgd)
{
- PVOP_VCALL2(pv_mmu_ops.pgd_free, mm, pgd);
+ PVOP_VCALL2(mmu.pgd_free, mm, pgd);
}
static inline void paravirt_alloc_pte(struct mm_struct *mm, unsigned long pfn)
{
- PVOP_VCALL2(pv_mmu_ops.alloc_pte, mm, pfn);
+ PVOP_VCALL2(mmu.alloc_pte, mm, pfn);
}
static inline void paravirt_release_pte(unsigned long pfn)
{
- PVOP_VCALL1(pv_mmu_ops.release_pte, pfn);
+ PVOP_VCALL1(mmu.release_pte, pfn);
}
static inline void paravirt_alloc_pmd(struct mm_struct *mm, unsigned long pfn)
{
- PVOP_VCALL2(pv_mmu_ops.alloc_pmd, mm, pfn);
+ PVOP_VCALL2(mmu.alloc_pmd, mm, pfn);
}
static inline void paravirt_release_pmd(unsigned long pfn)
{
- PVOP_VCALL1(pv_mmu_ops.release_pmd, pfn);
+ PVOP_VCALL1(mmu.release_pmd, pfn);
}
static inline void paravirt_alloc_pud(struct mm_struct *mm, unsigned long pfn)
{
- PVOP_VCALL2(pv_mmu_ops.alloc_pud, mm, pfn);
+ PVOP_VCALL2(mmu.alloc_pud, mm, pfn);
}
static inline void paravirt_release_pud(unsigned long pfn)
{
- PVOP_VCALL1(pv_mmu_ops.release_pud, pfn);
+ PVOP_VCALL1(mmu.release_pud, pfn);
}
static inline void paravirt_alloc_p4d(struct mm_struct *mm, unsigned long pfn)
{
- PVOP_VCALL2(pv_mmu_ops.alloc_p4d, mm, pfn);
+ PVOP_VCALL2(mmu.alloc_p4d, mm, pfn);
}
static inline void paravirt_release_p4d(unsigned long pfn)
{
- PVOP_VCALL1(pv_mmu_ops.release_p4d, pfn);
+ PVOP_VCALL1(mmu.release_p4d, pfn);
}
static inline pte_t __pte(pteval_t val)
@@ -367,13 +367,9 @@ static inline pte_t __pte(pteval_t val)
pteval_t ret;
if (sizeof(pteval_t) > sizeof(long))
- ret = PVOP_CALLEE2(pteval_t,
- pv_mmu_ops.make_pte,
- val, (u64)val >> 32);
+ ret = PVOP_CALLEE2(pteval_t, mmu.make_pte, val, (u64)val >> 32);
else
- ret = PVOP_CALLEE1(pteval_t,
- pv_mmu_ops.make_pte,
- val);
+ ret = PVOP_CALLEE1(pteval_t, mmu.make_pte, val);
return (pte_t) { .pte = ret };
}
@@ -383,11 +379,10 @@ static inline pteval_t pte_val(pte_t pte)
pteval_t ret;
if (sizeof(pteval_t) > sizeof(long))
- ret = PVOP_CALLEE2(pteval_t, pv_mmu_ops.pte_val,
+ ret = PVOP_CALLEE2(pteval_t, mmu.pte_val,
pte.pte, (u64)pte.pte >> 32);
else
- ret = PVOP_CALLEE1(pteval_t, pv_mmu_ops.pte_val,
- pte.pte);
+ ret = PVOP_CALLEE1(pteval_t, mmu.pte_val, pte.pte);
return ret;
}
@@ -397,11 +392,9 @@ static inline pgd_t __pgd(pgdval_t val)
pgdval_t ret;
if (sizeof(pgdval_t) > sizeof(long))
- ret = PVOP_CALLEE2(pgdval_t, pv_mmu_ops.make_pgd,
- val, (u64)val >> 32);
+ ret = PVOP_CALLEE2(pgdval_t, mmu.make_pgd, val, (u64)val >> 32);
else
- ret = PVOP_CALLEE1(pgdval_t, pv_mmu_ops.make_pgd,
- val);
+ ret = PVOP_CALLEE1(pgdval_t, mmu.make_pgd, val);
return (pgd_t) { ret };
}
@@ -411,11 +404,10 @@ static inline pgdval_t pgd_val(pgd_t pgd)
pgdval_t ret;
if (sizeof(pgdval_t) > sizeof(long))
- ret = PVOP_CALLEE2(pgdval_t, pv_mmu_ops.pgd_val,
+ ret = PVOP_CALLEE2(pgdval_t, mmu.pgd_val,
pgd.pgd, (u64)pgd.pgd >> 32);
else
- ret = PVOP_CALLEE1(pgdval_t, pv_mmu_ops.pgd_val,
- pgd.pgd);
+ ret = PVOP_CALLEE1(pgdval_t, mmu.pgd_val, pgd.pgd);
return ret;
}
@@ -426,8 +418,7 @@ static inline pte_t ptep_modify_prot_start(struct mm_struct *mm, unsigned long a
{
pteval_t ret;
- ret = PVOP_CALL3(pteval_t, pv_mmu_ops.ptep_modify_prot_start,
- mm, addr, ptep);
+ ret = PVOP_CALL3(pteval_t, mmu.ptep_modify_prot_start, mm, addr, ptep);
return (pte_t) { .pte = ret };
}
@@ -437,20 +428,18 @@ static inline void ptep_modify_prot_commit(struct mm_struct *mm, unsigned long a
{
if (sizeof(pteval_t) > sizeof(long))
/* 5 arg words */
- pv_mmu_ops.ptep_modify_prot_commit(mm, addr, ptep, pte);
+ pv_ops.mmu.ptep_modify_prot_commit(mm, addr, ptep, pte);
else
- PVOP_VCALL4(pv_mmu_ops.ptep_modify_prot_commit,
+ PVOP_VCALL4(mmu.ptep_modify_prot_commit,
mm, addr, ptep, pte.pte);
}
static inline void set_pte(pte_t *ptep, pte_t pte)
{
if (sizeof(pteval_t) > sizeof(long))
- PVOP_VCALL3(pv_mmu_ops.set_pte, ptep,
- pte.pte, (u64)pte.pte >> 32);
+ PVOP_VCALL3(mmu.set_pte, ptep, pte.pte, (u64)pte.pte >> 32);
else
- PVOP_VCALL2(pv_mmu_ops.set_pte, ptep,
- pte.pte);
+ PVOP_VCALL2(mmu.set_pte, ptep, pte.pte);
}
static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
@@ -458,9 +447,9 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
{
if (sizeof(pteval_t) > sizeof(long))
/* 5 arg words */
- pv_mmu_ops.set_pte_at(mm, addr, ptep, pte);
+ pv_ops.mmu.set_pte_at(mm, addr, ptep, pte);
else
- PVOP_VCALL4(pv_mmu_ops.set_pte_at, mm, addr, ptep, pte.pte);
+ PVOP_VCALL4(mmu.set_pte_at, mm, addr, ptep, pte.pte);
}
static inline void set_pmd(pmd_t *pmdp, pmd_t pmd)
@@ -468,9 +457,9 @@ static inline void set_pmd(pmd_t *pmdp, pmd_t pmd)
pmdval_t val = native_pmd_val(pmd);
if (sizeof(pmdval_t) > sizeof(long))
- PVOP_VCALL3(pv_mmu_ops.set_pmd, pmdp, val, (u64)val >> 32);
+ PVOP_VCALL3(mmu.set_pmd, pmdp, val, (u64)val >> 32);
else
- PVOP_VCALL2(pv_mmu_ops.set_pmd, pmdp, val);
+ PVOP_VCALL2(mmu.set_pmd, pmdp, val);
}
#if CONFIG_PGTABLE_LEVELS >= 3
@@ -479,11 +468,9 @@ static inline pmd_t __pmd(pmdval_t val)
pmdval_t ret;
if (sizeof(pmdval_t) > sizeof(long))
- ret = PVOP_CALLEE2(pmdval_t, pv_mmu_ops.make_pmd,
- val, (u64)val >> 32);
+ ret = PVOP_CALLEE2(pmdval_t, mmu.make_pmd, val, (u64)val >> 32);
else
- ret = PVOP_CALLEE1(pmdval_t, pv_mmu_ops.make_pmd,
- val);
+ ret = PVOP_CALLEE1(pmdval_t, mmu.make_pmd, val);
return (pmd_t) { ret };
}
@@ -493,11 +480,10 @@ static inline pmdval_t pmd_val(pmd_t pmd)
pmdval_t ret;
if (sizeof(pmdval_t) > sizeof(long))
- ret = PVOP_CALLEE2(pmdval_t, pv_mmu_ops.pmd_val,
+ ret = PVOP_CALLEE2(pmdval_t, mmu.pmd_val,
pmd.pmd, (u64)pmd.pmd >> 32);
else
- ret = PVOP_CALLEE1(pmdval_t, pv_mmu_ops.pmd_val,
- pmd.pmd);
+ ret = PVOP_CALLEE1(pmdval_t, mmu.pmd_val, pmd.pmd);
return ret;
}
@@ -507,11 +493,9 @@ static inline void set_pud(pud_t *pudp, pud_t pud)
pudval_t val = native_pud_val(pud);
if (sizeof(pudval_t) > sizeof(long))
- PVOP_VCALL3(pv_mmu_ops.set_pud, pudp,
- val, (u64)val >> 32);
+ PVOP_VCALL3(mmu.set_pud, pudp, val, (u64)val >> 32);
else
- PVOP_VCALL2(pv_mmu_ops.set_pud, pudp,
- val);
+ PVOP_VCALL2(mmu.set_pud, pudp, val);
}
#if CONFIG_PGTABLE_LEVELS >= 4
static inline pud_t __pud(pudval_t val)
@@ -519,11 +503,9 @@ static inline pud_t __pud(pudval_t val)
pudval_t ret;
if (sizeof(pudval_t) > sizeof(long))
- ret = PVOP_CALLEE2(pudval_t, pv_mmu_ops.make_pud,
- val, (u64)val >> 32);
+ ret = PVOP_CALLEE2(pudval_t, mmu.make_pud, val, (u64)val >> 32);
else
- ret = PVOP_CALLEE1(pudval_t, pv_mmu_ops.make_pud,
- val);
+ ret = PVOP_CALLEE1(pudval_t, mmu.make_pud, val);
return (pud_t) { ret };
}
@@ -533,11 +515,10 @@ static inline pudval_t pud_val(pud_t pud)
pudval_t ret;
if (sizeof(pudval_t) > sizeof(long))
- ret = PVOP_CALLEE2(pudval_t, pv_mmu_ops.pud_val,
+ ret = PVOP_CALLEE2(pudval_t, mmu.pud_val,
pud.pud, (u64)pud.pud >> 32);
else
- ret = PVOP_CALLEE1(pudval_t, pv_mmu_ops.pud_val,
- pud.pud);
+ ret = PVOP_CALLEE1(pudval_t, mmu.pud_val, pud.pud);
return ret;
}
@@ -552,30 +533,28 @@ static inline void set_p4d(p4d_t *p4dp, p4d_t p4d)
p4dval_t val = native_p4d_val(p4d);
if (sizeof(p4dval_t) > sizeof(long))
- PVOP_VCALL3(pv_mmu_ops.set_p4d, p4dp,
- val, (u64)val >> 32);
+ PVOP_VCALL3(mmu.set_p4d, p4dp, val, (u64)val >> 32);
else
- PVOP_VCALL2(pv_mmu_ops.set_p4d, p4dp,
- val);
+ PVOP_VCALL2(mmu.set_p4d, p4dp, val);
}
#if CONFIG_PGTABLE_LEVELS >= 5
static inline p4d_t __p4d(p4dval_t val)
{
- p4dval_t ret = PVOP_CALLEE1(p4dval_t, pv_mmu_ops.make_p4d, val);
+ p4dval_t ret = PVOP_CALLEE1(p4dval_t, mmu.make_p4d, val);
return (p4d_t) { ret };
}
static inline p4dval_t p4d_val(p4d_t p4d)
{
- return PVOP_CALLEE1(p4dval_t, pv_mmu_ops.p4d_val, p4d.p4d);
+ return PVOP_CALLEE1(p4dval_t, mmu.p4d_val, p4d.p4d);
}
static inline void __set_pgd(pgd_t *pgdp, pgd_t pgd)
{
- PVOP_VCALL2(pv_mmu_ops.set_pgd, pgdp, native_pgd_val(pgd));
+ PVOP_VCALL2(mmu.set_pgd, pgdp, native_pgd_val(pgd));
}
#define set_pgd(pgdp, pgdval) do { \
@@ -606,19 +585,18 @@ static inline void p4d_clear(p4d_t *p4dp)
64-bit pte atomically */
static inline void set_pte_atomic(pte_t *ptep, pte_t pte)
{
- PVOP_VCALL3(pv_mmu_ops.set_pte_atomic, ptep,
- pte.pte, pte.pte >> 32);
+ PVOP_VCALL3(mmu.set_pte_atomic, ptep, pte.pte, pte.pte >> 32);
}
static inline void pte_clear(struct mm_struct *mm, unsigned long addr,
pte_t *ptep)
{
- PVOP_VCALL3(pv_mmu_ops.pte_clear, mm, addr, ptep);
+ PVOP_VCALL3(mmu.pte_clear, mm, addr, ptep);
}
static inline void pmd_clear(pmd_t *pmdp)
{
- PVOP_VCALL1(pv_mmu_ops.pmd_clear, pmdp);
+ PVOP_VCALL1(mmu.pmd_clear, pmdp);
}
#else /* !CONFIG_X86_PAE */
static inline void set_pte_atomic(pte_t *ptep, pte_t pte)
@@ -641,34 +619,34 @@ static inline void pmd_clear(pmd_t *pmdp)
#define __HAVE_ARCH_START_CONTEXT_SWITCH
static inline void arch_start_context_switch(struct task_struct *prev)
{
- PVOP_VCALL1(pv_cpu_ops.start_context_switch, prev);
+ PVOP_VCALL1(cpu.start_context_switch, prev);
}
static inline void arch_end_context_switch(struct task_struct *next)
{
- PVOP_VCALL1(pv_cpu_ops.end_context_switch, next);
+ PVOP_VCALL1(cpu.end_context_switch, next);
}
#define __HAVE_ARCH_ENTER_LAZY_MMU_MODE
static inline void arch_enter_lazy_mmu_mode(void)
{
- PVOP_VCALL0(pv_mmu_ops.lazy_mode.enter);
+ PVOP_VCALL0(mmu.lazy_mode.enter);
}
static inline void arch_leave_lazy_mmu_mode(void)
{
- PVOP_VCALL0(pv_mmu_ops.lazy_mode.leave);
+ PVOP_VCALL0(mmu.lazy_mode.leave);
}
static inline void arch_flush_lazy_mmu_mode(void)
{
- PVOP_VCALL0(pv_mmu_ops.lazy_mode.flush);
+ PVOP_VCALL0(mmu.lazy_mode.flush);
}
static inline void __set_fixmap(unsigned /* enum fixed_addresses */ idx,
phys_addr_t phys, pgprot_t flags)
{
- pv_mmu_ops.set_fixmap(idx, phys, flags);
+ pv_ops.mmu.set_fixmap(idx, phys, flags);
}
#if defined(CONFIG_SMP) && defined(CONFIG_PARAVIRT_SPINLOCKS)
@@ -676,29 +654,32 @@ static inline void __set_fixmap(unsigned /* enum fixed_addresses */ idx,
static __always_inline void pv_queued_spin_lock_slowpath(struct qspinlock *lock,
u32 val)
{
- PVOP_VCALL2(pv_lock_ops.queued_spin_lock_slowpath, lock, val);
+ PVOP_VCALL2(lock.queued_spin_lock_slowpath, lock, val);
}
static __always_inline void pv_queued_spin_unlock(struct qspinlock *lock)
{
- PVOP_VCALLEE1(pv_lock_ops.queued_spin_unlock, lock);
+ PVOP_VCALLEE1(lock.queued_spin_unlock, lock);
}
static __always_inline void pv_wait(u8 *ptr, u8 val)
{
- PVOP_VCALL2(pv_lock_ops.wait, ptr, val);
+ PVOP_VCALL2(lock.wait, ptr, val);
}
static __always_inline void pv_kick(int cpu)
{
- PVOP_VCALL1(pv_lock_ops.kick, cpu);
+ PVOP_VCALL1(lock.kick, cpu);
}
static __always_inline bool pv_vcpu_is_preempted(long cpu)
{
- return PVOP_CALLEE1(bool, pv_lock_ops.vcpu_is_preempted, cpu);
+ return PVOP_CALLEE1(bool, lock.vcpu_is_preempted, cpu);
}
+void __raw_callee_save___native_queued_spin_unlock(struct qspinlock *lock);
+bool __raw_callee_save___native_vcpu_is_preempted(long cpu);
+
#endif /* SMP && PARAVIRT_SPINLOCKS */
#ifdef CONFIG_X86_32
@@ -780,22 +761,22 @@ static __always_inline bool pv_vcpu_is_preempted(long cpu)
static inline notrace unsigned long arch_local_save_flags(void)
{
- return PVOP_CALLEE0(unsigned long, pv_irq_ops.save_fl);
+ return PVOP_CALLEE0(unsigned long, irq.save_fl);
}
static inline notrace void arch_local_irq_restore(unsigned long f)
{
- PVOP_VCALLEE1(pv_irq_ops.restore_fl, f);
+ PVOP_VCALLEE1(irq.restore_fl, f);
}
static inline notrace void arch_local_irq_disable(void)
{
- PVOP_VCALLEE0(pv_irq_ops.irq_disable);
+ PVOP_VCALLEE0(irq.irq_disable);
}
static inline notrace void arch_local_irq_enable(void)
{
- PVOP_VCALLEE0(pv_irq_ops.irq_enable);
+ PVOP_VCALLEE0(irq.irq_enable);
}
static inline notrace unsigned long arch_local_irq_save(void)
@@ -867,7 +848,7 @@ extern void default_banner(void);
COND_POP(set, CLBR_RCX, rcx); \
COND_POP(set, CLBR_RAX, rax)
-#define PARA_PATCH(struct, off) ((PARAVIRT_PATCH_##struct + (off)) / 8)
+#define PARA_PATCH(off) ((off) / 8)
#define PARA_SITE(ptype, ops) _PVSITE(ptype, ops, .quad, 8)
#define PARA_INDIRECT(addr) *addr(%rip)
#else
@@ -882,35 +863,35 @@ extern void default_banner(void);
COND_POP(set, CLBR_EDI, edi); \
COND_POP(set, CLBR_EAX, eax)
-#define PARA_PATCH(struct, off) ((PARAVIRT_PATCH_##struct + (off)) / 4)
+#define PARA_PATCH(off) ((off) / 4)
#define PARA_SITE(ptype, ops) _PVSITE(ptype, ops, .long, 4)
#define PARA_INDIRECT(addr) *%cs:addr
#endif
#define INTERRUPT_RETURN \
- PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_iret), \
+ PARA_SITE(PARA_PATCH(PV_CPU_iret), \
ANNOTATE_RETPOLINE_SAFE; \
- jmp PARA_INDIRECT(pv_cpu_ops+PV_CPU_iret);)
+ jmp PARA_INDIRECT(pv_ops+PV_CPU_iret);)
#define DISABLE_INTERRUPTS(clobbers) \
- PARA_SITE(PARA_PATCH(pv_irq_ops, PV_IRQ_irq_disable), \
+ PARA_SITE(PARA_PATCH(PV_IRQ_irq_disable), \
PV_SAVE_REGS(clobbers | CLBR_CALLEE_SAVE); \
ANNOTATE_RETPOLINE_SAFE; \
- call PARA_INDIRECT(pv_irq_ops+PV_IRQ_irq_disable); \
+ call PARA_INDIRECT(pv_ops+PV_IRQ_irq_disable); \
PV_RESTORE_REGS(clobbers | CLBR_CALLEE_SAVE);)
#define ENABLE_INTERRUPTS(clobbers) \
- PARA_SITE(PARA_PATCH(pv_irq_ops, PV_IRQ_irq_enable), \
+ PARA_SITE(PARA_PATCH(PV_IRQ_irq_enable), \
PV_SAVE_REGS(clobbers | CLBR_CALLEE_SAVE); \
ANNOTATE_RETPOLINE_SAFE; \
- call PARA_INDIRECT(pv_irq_ops+PV_IRQ_irq_enable); \
+ call PARA_INDIRECT(pv_ops+PV_IRQ_irq_enable); \
PV_RESTORE_REGS(clobbers | CLBR_CALLEE_SAVE);)
#ifdef CONFIG_X86_32
#define GET_CR0_INTO_EAX \
push %ecx; push %edx; \
ANNOTATE_RETPOLINE_SAFE; \
- call PARA_INDIRECT(pv_cpu_ops+PV_CPU_read_cr0); \
+ call PARA_INDIRECT(pv_ops+PV_CPU_read_cr0); \
pop %edx; pop %ecx
#else /* !CONFIG_X86_32 */
@@ -920,7 +901,7 @@ extern void default_banner(void);
* inlined, or the swapgs instruction must be trapped and emulated.
*/
#define SWAPGS_UNSAFE_STACK \
- PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_swapgs), swapgs)
+ PARA_SITE(PARA_PATCH(PV_CPU_swapgs), swapgs)
/*
* Note: swapgs is very special, and in practise is either going to be
@@ -929,26 +910,26 @@ extern void default_banner(void);
* it.
*/
#define SWAPGS \
- PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_swapgs), \
+ PARA_SITE(PARA_PATCH(PV_CPU_swapgs), \
ANNOTATE_RETPOLINE_SAFE; \
- call PARA_INDIRECT(pv_cpu_ops+PV_CPU_swapgs); \
+ call PARA_INDIRECT(pv_ops+PV_CPU_swapgs); \
)
#define GET_CR2_INTO_RAX \
ANNOTATE_RETPOLINE_SAFE; \
- call PARA_INDIRECT(pv_mmu_ops+PV_MMU_read_cr2);
+ call PARA_INDIRECT(pv_ops+PV_MMU_read_cr2);
#define USERGS_SYSRET64 \
- PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_usergs_sysret64), \
+ PARA_SITE(PARA_PATCH(PV_CPU_usergs_sysret64), \
ANNOTATE_RETPOLINE_SAFE; \
- jmp PARA_INDIRECT(pv_cpu_ops+PV_CPU_usergs_sysret64);)
+ jmp PARA_INDIRECT(pv_ops+PV_CPU_usergs_sysret64);)
#ifdef CONFIG_DEBUG_ENTRY
#define SAVE_FLAGS(clobbers) \
- PARA_SITE(PARA_PATCH(pv_irq_ops, PV_IRQ_save_fl), \
+ PARA_SITE(PARA_PATCH(PV_IRQ_save_fl), \
PV_SAVE_REGS(clobbers | CLBR_CALLEE_SAVE); \
ANNOTATE_RETPOLINE_SAFE; \
- call PARA_INDIRECT(pv_irq_ops+PV_IRQ_save_fl); \
+ call PARA_INDIRECT(pv_ops+PV_IRQ_save_fl); \
PV_RESTORE_REGS(clobbers | CLBR_CALLEE_SAVE);)
#endif
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index b2220536a7d4..462a54b2bb53 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -321,28 +321,23 @@ struct pv_lock_ops {
* number for each function using the offset which we use to indicate
* what to patch. */
struct paravirt_patch_template {
- struct pv_init_ops pv_init_ops;
- struct pv_time_ops pv_time_ops;
- struct pv_cpu_ops pv_cpu_ops;
- struct pv_irq_ops pv_irq_ops;
- struct pv_mmu_ops pv_mmu_ops;
- struct pv_lock_ops pv_lock_ops;
+ struct pv_init_ops init;
+ struct pv_time_ops time;
+ struct pv_cpu_ops cpu;
+ struct pv_irq_ops irq;
+ struct pv_mmu_ops mmu;
+ struct pv_lock_ops lock;
} __no_randomize_layout;
extern struct pv_info pv_info;
-extern struct pv_init_ops pv_init_ops;
-extern struct pv_time_ops pv_time_ops;
-extern struct pv_cpu_ops pv_cpu_ops;
-extern struct pv_irq_ops pv_irq_ops;
-extern struct pv_mmu_ops pv_mmu_ops;
-extern struct pv_lock_ops pv_lock_ops;
+extern struct paravirt_patch_template pv_ops;
#define PARAVIRT_PATCH(x) \
(offsetof(struct paravirt_patch_template, x) / sizeof(void *))
#define paravirt_type(op) \
[paravirt_typenum] "i" (PARAVIRT_PATCH(op)), \
- [paravirt_opptr] "i" (&(op))
+ [paravirt_opptr] "i" (&(pv_ops.op))
#define paravirt_clobber(clobber) \
[paravirt_clobber] "i" (clobber)
@@ -503,9 +498,9 @@ int paravirt_disable_iospace(void);
#endif /* CONFIG_X86_32 */
#ifdef CONFIG_PARAVIRT_DEBUG
-#define PVOP_TEST_NULL(op) BUG_ON(op == NULL)
+#define PVOP_TEST_NULL(op) BUG_ON(pv_ops.op == NULL)
#else
-#define PVOP_TEST_NULL(op) ((void)op)
+#define PVOP_TEST_NULL(op) ((void)pv_ops.op)
#endif
#define PVOP_RETMASK(rettype) \
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 7985c20601b4..85dc63b97d07 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -594,7 +594,7 @@ void __init_or_module apply_paravirt(struct paravirt_patch_site *start,
BUG_ON(p->len > MAX_PATCH_LEN);
/* prep the buffer with the original instructions */
memcpy(insnbuf, p->instr, p->len);
- used = pv_init_ops.patch(p->instrtype, insnbuf,
+ used = pv_ops.init.patch(p->instrtype, insnbuf,
(unsigned long)p->instr, p->len);
BUG_ON(used > p->len);
diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c
index 01de31db300d..46d14498e214 100644
--- a/arch/x86/kernel/asm-offsets.c
+++ b/arch/x86/kernel/asm-offsets.c
@@ -66,13 +66,11 @@ void common(void) {
#ifdef CONFIG_PARAVIRT
BLANK();
- OFFSET(PARAVIRT_PATCH_pv_cpu_ops, paravirt_patch_template, pv_cpu_ops);
- OFFSET(PARAVIRT_PATCH_pv_irq_ops, paravirt_patch_template, pv_irq_ops);
- OFFSET(PV_IRQ_irq_disable, pv_irq_ops, irq_disable);
- OFFSET(PV_IRQ_irq_enable, pv_irq_ops, irq_enable);
- OFFSET(PV_CPU_iret, pv_cpu_ops, iret);
- OFFSET(PV_CPU_read_cr0, pv_cpu_ops, read_cr0);
- OFFSET(PV_MMU_read_cr2, pv_mmu_ops, read_cr2);
+ OFFSET(PV_IRQ_irq_disable, paravirt_patch_template, irq.irq_disable);
+ OFFSET(PV_IRQ_irq_enable, paravirt_patch_template, irq.irq_enable);
+ OFFSET(PV_CPU_iret, paravirt_patch_template, cpu.iret);
+ OFFSET(PV_CPU_read_cr0, paravirt_patch_template, cpu.read_cr0);
+ OFFSET(PV_MMU_read_cr2, paravirt_patch_template, mmu.read_cr2);
#endif
#ifdef CONFIG_XEN
diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c
index 3b9405e7ba2b..3384b03e717f 100644
--- a/arch/x86/kernel/asm-offsets_64.c
+++ b/arch/x86/kernel/asm-offsets_64.c
@@ -21,10 +21,11 @@ static char syscalls_ia32[] = {
int main(void)
{
#ifdef CONFIG_PARAVIRT
- OFFSET(PV_CPU_usergs_sysret64, pv_cpu_ops, usergs_sysret64);
- OFFSET(PV_CPU_swapgs, pv_cpu_ops, swapgs);
+ OFFSET(PV_CPU_usergs_sysret64, paravirt_patch_template,
+ cpu.usergs_sysret64);
+ OFFSET(PV_CPU_swapgs, paravirt_patch_template, cpu.swapgs);
#ifdef CONFIG_DEBUG_ENTRY
- OFFSET(PV_IRQ_save_fl, pv_irq_ops, save_fl);
+ OFFSET(PV_IRQ_save_fl, paravirt_patch_template, irq.save_fl);
#endif
BLANK();
#endif
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 84dee5ab745a..1f089e1c79d3 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1242,7 +1242,7 @@ static void generic_identify(struct cpuinfo_x86 *c)
# ifdef CONFIG_PARAVIRT
do {
extern void native_iret(void);
- if (pv_cpu_ops.iret == native_iret)
+ if (pv_ops.cpu.iret == native_iret)
set_cpu_bug(c, X86_BUG_ESPFIX);
} while (0);
# else
diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c
index 8e005329648b..d9ab49bed8af 100644
--- a/arch/x86/kernel/cpu/vmware.c
+++ b/arch/x86/kernel/cpu/vmware.c
@@ -97,14 +97,14 @@ static void __init vmware_sched_clock_setup(void)
d->cyc2ns_offset = mul_u64_u32_shr(tsc_now, d->cyc2ns_mul,
d->cyc2ns_shift);
- pv_time_ops.sched_clock = vmware_sched_clock;
+ pv_ops.time.sched_clock = vmware_sched_clock;
pr_info("using sched offset of %llu ns\n", d->cyc2ns_offset);
}
static void __init vmware_paravirt_ops_setup(void)
{
pv_info.name = "VMware hypervisor";
- pv_cpu_ops.io_delay = paravirt_nop;
+ pv_ops.cpu.io_delay = paravirt_nop;
if (vmware_tsc_khz && vmw_sched_clock)
vmware_sched_clock_setup();
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index d9b71924c23c..ba4bfb7f6a36 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -283,7 +283,7 @@ static void __init paravirt_ops_setup(void)
pv_info.name = "KVM";
if (kvm_para_has_feature(KVM_FEATURE_NOP_IO_DELAY))
- pv_cpu_ops.io_delay = kvm_io_delay;
+ pv_ops.cpu.io_delay = kvm_io_delay;
#ifdef CONFIG_X86_IO_APIC
no_timer_check = 1;
@@ -632,14 +632,14 @@ static void __init kvm_guest_init(void)
if (kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) {
has_steal_clock = 1;
- pv_time_ops.steal_clock = kvm_steal_clock;
+ pv_ops.time.steal_clock = kvm_steal_clock;
}
if (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH) &&
!kvm_para_has_hint(KVM_HINTS_REALTIME) &&
kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) {
- pv_mmu_ops.flush_tlb_others = kvm_flush_tlb_others;
- pv_mmu_ops.tlb_remove_table = tlb_remove_table;
+ pv_ops.mmu.flush_tlb_others = kvm_flush_tlb_others;
+ pv_ops.mmu.tlb_remove_table = tlb_remove_table;
}
if (kvm_para_has_feature(KVM_FEATURE_PV_EOI))
@@ -850,13 +850,14 @@ void __init kvm_spinlock_init(void)
return;
__pv_init_lock_hash();
- pv_lock_ops.queued_spin_lock_slowpath = __pv_queued_spin_lock_slowpath;
- pv_lock_ops.queued_spin_unlock = PV_CALLEE_SAVE(__pv_queued_spin_unlock);
- pv_lock_ops.wait = kvm_wait;
- pv_lock_ops.kick = kvm_kick_cpu;
+ pv_ops.lock.queued_spin_lock_slowpath = __pv_queued_spin_lock_slowpath;
+ pv_ops.lock.queued_spin_unlock =
+ PV_CALLEE_SAVE(__pv_queued_spin_unlock);
+ pv_ops.lock.wait = kvm_wait;
+ pv_ops.lock.kick = kvm_kick_cpu;
if (kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) {
- pv_lock_ops.vcpu_is_preempted =
+ pv_ops.lock.vcpu_is_preempted =
PV_CALLEE_SAVE(__kvm_vcpu_is_preempted);
}
}
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index 1e6764648af3..a36b93a722a2 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -116,13 +116,13 @@ static u64 kvm_sched_clock_read(void)
static inline void kvm_sched_clock_init(bool stable)
{
if (!stable) {
- pv_time_ops.sched_clock = kvm_clock_read;
+ pv_ops.time.sched_clock = kvm_clock_read;
clear_sched_clock_stable();
return;
}
kvm_sched_clock_offset = kvm_clock_read();
- pv_time_ops.sched_clock = kvm_sched_clock_read;
+ pv_ops.time.sched_clock = kvm_sched_clock_read;
pr_info("kvm-clock: using sched offset of %llu cycles",
kvm_sched_clock_offset);
diff --git a/arch/x86/kernel/paravirt-spinlocks.c b/arch/x86/kernel/paravirt-spinlocks.c
index 71f2d1125ec0..4f75d0cf6305 100644
--- a/arch/x86/kernel/paravirt-spinlocks.c
+++ b/arch/x86/kernel/paravirt-spinlocks.c
@@ -17,7 +17,7 @@ PV_CALLEE_SAVE_REGS_THUNK(__native_queued_spin_unlock);
bool pv_is_native_spin_unlock(void)
{
- return pv_lock_ops.queued_spin_unlock.func ==
+ return pv_ops.lock.queued_spin_unlock.func ==
__raw_callee_save___native_queued_spin_unlock;
}
@@ -29,17 +29,6 @@ PV_CALLEE_SAVE_REGS_THUNK(__native_vcpu_is_preempted);
bool pv_is_native_vcpu_is_preempted(void)
{
- return pv_lock_ops.vcpu_is_preempted.func ==
+ return pv_ops.lock.vcpu_is_preempted.func ==
__raw_callee_save___native_vcpu_is_preempted;
}
-
-struct pv_lock_ops pv_lock_ops = {
-#ifdef CONFIG_SMP
- .queued_spin_lock_slowpath = native_queued_spin_lock_slowpath,
- .queued_spin_unlock = PV_CALLEE_SAVE(__native_queued_spin_unlock),
- .wait = paravirt_nop,
- .kick = paravirt_nop,
- .vcpu_is_preempted = PV_CALLEE_SAVE(__native_vcpu_is_preempted),
-#endif /* SMP */
-};
-EXPORT_SYMBOL(pv_lock_ops);
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index 287d34513f6a..5fc2b94e1591 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -128,29 +128,14 @@ void __init native_pv_lock_init(void)
static_branch_disable(&virt_spin_lock_key);
}
-/*
- * Neat trick to map patch type back to the call within the
- * corresponding structure.
- */
-static void *get_call_destination(u8 type)
-{
- struct paravirt_patch_template tmpl = {
- .pv_init_ops = pv_init_ops,
- .pv_time_ops = pv_time_ops,
- .pv_cpu_ops = pv_cpu_ops,
- .pv_irq_ops = pv_irq_ops,
- .pv_mmu_ops = pv_mmu_ops,
-#ifdef CONFIG_PARAVIRT_SPINLOCKS
- .pv_lock_ops = pv_lock_ops,
-#endif
- };
- return *((void **)&tmpl + type);
-}
-
unsigned paravirt_patch_default(u8 type, void *insnbuf,
unsigned long addr, unsigned len)
{
- void *opfunc = get_call_destination(type);
+ /*
+ * Neat trick to map patch type back to the call within the
+ * corresponding structure.
+ */
+ void *opfunc = *((void **)&pv_ops + type);
unsigned ret;
if (opfunc == NULL)
@@ -165,8 +150,8 @@ unsigned paravirt_patch_default(u8 type, void *insnbuf,
else if (opfunc == _paravirt_ident_64)
ret = paravirt_patch_ident_64(insnbuf, len);
- else if (type == PARAVIRT_PATCH(pv_cpu_ops.iret) ||
- type == PARAVIRT_PATCH(pv_cpu_ops.usergs_sysret64))
+ else if (type == PARAVIRT_PATCH(cpu.iret) ||
+ type == PARAVIRT_PATCH(cpu.usergs_sysret64))
/* If operation requires a jmp, then jmp */
ret = paravirt_patch_jmp(insnbuf, opfunc, addr, len);
else
@@ -316,77 +301,6 @@ struct pv_info pv_info = {
#endif
};
-struct pv_init_ops pv_init_ops = {
- .patch = native_patch,
-};
-
-struct pv_time_ops pv_time_ops = {
- .sched_clock = native_sched_clock,
- .steal_clock = native_steal_clock,
-};
-
-__visible struct pv_irq_ops pv_irq_ops = {
- .save_fl = __PV_IS_CALLEE_SAVE(native_save_fl),
- .restore_fl = __PV_IS_CALLEE_SAVE(native_restore_fl),
- .irq_disable = __PV_IS_CALLEE_SAVE(native_irq_disable),
- .irq_enable = __PV_IS_CALLEE_SAVE(native_irq_enable),
- .safe_halt = native_safe_halt,
- .halt = native_halt,
-};
-
-__visible struct pv_cpu_ops pv_cpu_ops = {
- .cpuid = native_cpuid,
- .get_debugreg = native_get_debugreg,
- .set_debugreg = native_set_debugreg,
- .read_cr0 = native_read_cr0,
- .write_cr0 = native_write_cr0,
- .write_cr4 = native_write_cr4,
-#ifdef CONFIG_X86_64
- .read_cr8 = native_read_cr8,
- .write_cr8 = native_write_cr8,
-#endif
- .wbinvd = native_wbinvd,
- .read_msr = native_read_msr,
- .write_msr = native_write_msr,
- .read_msr_safe = native_read_msr_safe,
- .write_msr_safe = native_write_msr_safe,
- .read_pmc = native_read_pmc,
- .load_tr_desc = native_load_tr_desc,
- .set_ldt = native_set_ldt,
- .load_gdt = native_load_gdt,
- .load_idt = native_load_idt,
- .store_tr = native_store_tr,
- .load_tls = native_load_tls,
-#ifdef CONFIG_X86_64
- .load_gs_index = native_load_gs_index,
-#endif
- .write_ldt_entry = native_write_ldt_entry,
- .write_gdt_entry = native_write_gdt_entry,
- .write_idt_entry = native_write_idt_entry,
-
- .alloc_ldt = paravirt_nop,
- .free_ldt = paravirt_nop,
-
- .load_sp0 = native_load_sp0,
-
-#ifdef CONFIG_X86_64
- .usergs_sysret64 = native_usergs_sysret64,
-#endif
- .iret = native_iret,
- .swapgs = native_swapgs,
-
- .set_iopl_mask = native_set_iopl_mask,
- .io_delay = native_io_delay,
-
- .start_context_switch = paravirt_nop,
- .end_context_switch = paravirt_nop,
-};
-
-/* At this point, native_get/set_debugreg has real function entries */
-NOKPROBE_SYMBOL(native_get_debugreg);
-NOKPROBE_SYMBOL(native_set_debugreg);
-NOKPROBE_SYMBOL(native_load_idt);
-
#if defined(CONFIG_X86_32) && !defined(CONFIG_X86_PAE)
/* 32-bit pagetable entries */
#define PTE_IDENT __PV_IS_CALLEE_SAVE(_paravirt_ident_32)
@@ -395,85 +309,162 @@ NOKPROBE_SYMBOL(native_load_idt);
#define PTE_IDENT __PV_IS_CALLEE_SAVE(_paravirt_ident_64)
#endif
-struct pv_mmu_ops pv_mmu_ops __ro_after_init = {
-
- .read_cr2 = native_read_cr2,
- .write_cr2 = native_write_cr2,
- .read_cr3 = __native_read_cr3,
- .write_cr3 = native_write_cr3,
-
- .flush_tlb_user = native_flush_tlb,
- .flush_tlb_kernel = native_flush_tlb_global,
- .flush_tlb_one_user = native_flush_tlb_one_user,
- .flush_tlb_others = native_flush_tlb_others,
- .tlb_remove_table = (void (*)(struct mmu_gather *, void *))tlb_remove_page,
-
- .pgd_alloc = __paravirt_pgd_alloc,
- .pgd_free = paravirt_nop,
+struct paravirt_patch_template pv_ops = {
+ /* Init ops. */
+ .init.patch = native_patch,
+
+ /* Time ops. */
+ .time.sched_clock = native_sched_clock,
+ .time.steal_clock = native_steal_clock,
+
+ /* Cpu ops. */
+ .cpu.cpuid = native_cpuid,
+ .cpu.get_debugreg = native_get_debugreg,
+ .cpu.set_debugreg = native_set_debugreg,
+ .cpu.read_cr0 = native_read_cr0,
+ .cpu.write_cr0 = native_write_cr0,
+ .cpu.write_cr4 = native_write_cr4,
+#ifdef CONFIG_X86_64
+ .cpu.read_cr8 = native_read_cr8,
+ .cpu.write_cr8 = native_write_cr8,
+#endif
+ .cpu.wbinvd = native_wbinvd,
+ .cpu.read_msr = native_read_msr,
+ .cpu.write_msr = native_write_msr,
+ .cpu.read_msr_safe = native_read_msr_safe,
+ .cpu.write_msr_safe = native_write_msr_safe,
+ .cpu.read_pmc = native_read_pmc,
+ .cpu.load_tr_desc = native_load_tr_desc,
+ .cpu.set_ldt = native_set_ldt,
+ .cpu.load_gdt = native_load_gdt,
+ .cpu.load_idt = native_load_idt,
+ .cpu.store_tr = native_store_tr,
+ .cpu.load_tls = native_load_tls,
+#ifdef CONFIG_X86_64
+ .cpu.load_gs_index = native_load_gs_index,
+#endif
+ .cpu.write_ldt_entry = native_write_ldt_entry,
+ .cpu.write_gdt_entry = native_write_gdt_entry,
+ .cpu.write_idt_entry = native_write_idt_entry,
- .alloc_pte = paravirt_nop,
- .alloc_pmd = paravirt_nop,
- .alloc_pud = paravirt_nop,
- .alloc_p4d = paravirt_nop,
- .release_pte = paravirt_nop,
- .release_pmd = paravirt_nop,
- .release_pud = paravirt_nop,
- .release_p4d = paravirt_nop,
+ .cpu.alloc_ldt = paravirt_nop,
+ .cpu.free_ldt = paravirt_nop,
- .set_pte = native_set_pte,
- .set_pte_at = native_set_pte_at,
- .set_pmd = native_set_pmd,
+ .cpu.load_sp0 = native_load_sp0,
- .ptep_modify_prot_start = __ptep_modify_prot_start,
- .ptep_modify_prot_commit = __ptep_modify_prot_commit,
+#ifdef CONFIG_X86_64
+ .cpu.usergs_sysret64 = native_usergs_sysret64,
+#endif
+ .cpu.iret = native_iret,
+ .cpu.swapgs = native_swapgs,
+
+ .cpu.set_iopl_mask = native_set_iopl_mask,
+ .cpu.io_delay = native_io_delay,
+
+ .cpu.start_context_switch = paravirt_nop,
+ .cpu.end_context_switch = paravirt_nop,
+
+ /* Irq ops. */
+ .irq.save_fl = __PV_IS_CALLEE_SAVE(native_save_fl),
+ .irq.restore_fl = __PV_IS_CALLEE_SAVE(native_restore_fl),
+ .irq.irq_disable = __PV_IS_CALLEE_SAVE(native_irq_disable),
+ .irq.irq_enable = __PV_IS_CALLEE_SAVE(native_irq_enable),
+ .irq.safe_halt = native_safe_halt,
+ .irq.halt = native_halt,
+
+ /* Mmu ops. */
+ .mmu.read_cr2 = native_read_cr2,
+ .mmu.write_cr2 = native_write_cr2,
+ .mmu.read_cr3 = __native_read_cr3,
+ .mmu.write_cr3 = native_write_cr3,
+
+ .mmu.flush_tlb_user = native_flush_tlb,
+ .mmu.flush_tlb_kernel = native_flush_tlb_global,
+ .mmu.flush_tlb_one_user = native_flush_tlb_one_user,
+ .mmu.flush_tlb_others = native_flush_tlb_others,
+ .mmu.tlb_remove_table =
+ (void (*)(struct mmu_gather *, void *))tlb_remove_page,
+
+ .mmu.pgd_alloc = __paravirt_pgd_alloc,
+ .mmu.pgd_free = paravirt_nop,
+
+ .mmu.alloc_pte = paravirt_nop,
+ .mmu.alloc_pmd = paravirt_nop,
+ .mmu.alloc_pud = paravirt_nop,
+ .mmu.alloc_p4d = paravirt_nop,
+ .mmu.release_pte = paravirt_nop,
+ .mmu.release_pmd = paravirt_nop,
+ .mmu.release_pud = paravirt_nop,
+ .mmu.release_p4d = paravirt_nop,
+
+ .mmu.set_pte = native_set_pte,
+ .mmu.set_pte_at = native_set_pte_at,
+ .mmu.set_pmd = native_set_pmd,
+
+ .mmu.ptep_modify_prot_start = __ptep_modify_prot_start,
+ .mmu.ptep_modify_prot_commit = __ptep_modify_prot_commit,
#if CONFIG_PGTABLE_LEVELS >= 3
#ifdef CONFIG_X86_PAE
- .set_pte_atomic = native_set_pte_atomic,
- .pte_clear = native_pte_clear,
- .pmd_clear = native_pmd_clear,
+ .mmu.set_pte_atomic = native_set_pte_atomic,
+ .mmu.pte_clear = native_pte_clear,
+ .mmu.pmd_clear = native_pmd_clear,
#endif
- .set_pud = native_set_pud,
+ .mmu.set_pud = native_set_pud,
- .pmd_val = PTE_IDENT,
- .make_pmd = PTE_IDENT,
+ .mmu.pmd_val = PTE_IDENT,
+ .mmu.make_pmd = PTE_IDENT,
#if CONFIG_PGTABLE_LEVELS >= 4
- .pud_val = PTE_IDENT,
- .make_pud = PTE_IDENT,
+ .mmu.pud_val = PTE_IDENT,
+ .mmu.make_pud = PTE_IDENT,
- .set_p4d = native_set_p4d,
+ .mmu.set_p4d = native_set_p4d,
#if CONFIG_PGTABLE_LEVELS >= 5
- .p4d_val = PTE_IDENT,
- .make_p4d = PTE_IDENT,
+ .mmu.p4d_val = PTE_IDENT,
+ .mmu.make_p4d = PTE_IDENT,
- .set_pgd = native_set_pgd,
+ .mmu.set_pgd = native_set_pgd,
#endif /* CONFIG_PGTABLE_LEVELS >= 5 */
#endif /* CONFIG_PGTABLE_LEVELS >= 4 */
#endif /* CONFIG_PGTABLE_LEVELS >= 3 */
- .pte_val = PTE_IDENT,
- .pgd_val = PTE_IDENT,
+ .mmu.pte_val = PTE_IDENT,
+ .mmu.pgd_val = PTE_IDENT,
- .make_pte = PTE_IDENT,
- .make_pgd = PTE_IDENT,
+ .mmu.make_pte = PTE_IDENT,
+ .mmu.make_pgd = PTE_IDENT,
- .dup_mmap = paravirt_nop,
- .exit_mmap = paravirt_nop,
- .activate_mm = paravirt_nop,
+ .mmu.dup_mmap = paravirt_nop,
+ .mmu.exit_mmap = paravirt_nop,
+ .mmu.activate_mm = paravirt_nop,
- .lazy_mode = {
+ .mmu.lazy_mode = {
.enter = paravirt_nop,
.leave = paravirt_nop,
.flush = paravirt_nop,
},
- .set_fixmap = native_set_fixmap,
+ .mmu.set_fixmap = native_set_fixmap,
+
+#if defined(CONFIG_PARAVIRT_SPINLOCKS)
+ /* Lock ops. */
+#ifdef CONFIG_SMP
+ .lock.queued_spin_lock_slowpath = native_queued_spin_lock_slowpath,
+ .lock.queued_spin_unlock = PV_CALLEE_SAVE(__native_queued_spin_unlock),
+ .lock.wait = paravirt_nop,
+ .lock.kick = paravirt_nop,
+ .lock.vcpu_is_preempted =
+ PV_CALLEE_SAVE(__native_vcpu_is_preempted),
+#endif /* SMP */
+#endif
};
-EXPORT_SYMBOL_GPL(pv_time_ops);
-EXPORT_SYMBOL (pv_cpu_ops);
-EXPORT_SYMBOL (pv_mmu_ops);
+/* At this point, native_get/set_debugreg has real function entries */
+NOKPROBE_SYMBOL(native_get_debugreg);
+NOKPROBE_SYMBOL(native_set_debugreg);
+NOKPROBE_SYMBOL(native_load_idt);
+
+EXPORT_SYMBOL_GPL(pv_ops);
EXPORT_SYMBOL_GPL(pv_info);
-EXPORT_SYMBOL (pv_irq_ops);
diff --git a/arch/x86/kernel/paravirt_patch_32.c b/arch/x86/kernel/paravirt_patch_32.c
index e5c3a438149e..026fa43e9261 100644
--- a/arch/x86/kernel/paravirt_patch_32.c
+++ b/arch/x86/kernel/paravirt_patch_32.c
@@ -1,18 +1,18 @@
// SPDX-License-Identifier: GPL-2.0
#include <asm/paravirt.h>
-DEF_NATIVE(pv_irq_ops, irq_disable, "cli");
-DEF_NATIVE(pv_irq_ops, irq_enable, "sti");
-DEF_NATIVE(pv_irq_ops, restore_fl, "push %eax; popf");
-DEF_NATIVE(pv_irq_ops, save_fl, "pushf; pop %eax");
-DEF_NATIVE(pv_cpu_ops, iret, "iret");
-DEF_NATIVE(pv_mmu_ops, read_cr2, "mov %cr2, %eax");
-DEF_NATIVE(pv_mmu_ops, write_cr3, "mov %eax, %cr3");
-DEF_NATIVE(pv_mmu_ops, read_cr3, "mov %cr3, %eax");
+DEF_NATIVE(irq, irq_disable, "cli");
+DEF_NATIVE(irq, irq_enable, "sti");
+DEF_NATIVE(irq, restore_fl, "push %eax; popf");
+DEF_NATIVE(irq, save_fl, "pushf; pop %eax");
+DEF_NATIVE(cpu, iret, "iret");
+DEF_NATIVE(mmu, read_cr2, "mov %cr2, %eax");
+DEF_NATIVE(mmu, write_cr3, "mov %eax, %cr3");
+DEF_NATIVE(mmu, read_cr3, "mov %cr3, %eax");
#if defined(CONFIG_PARAVIRT_SPINLOCKS)
-DEF_NATIVE(pv_lock_ops, queued_spin_unlock, "movb $0, (%eax)");
-DEF_NATIVE(pv_lock_ops, vcpu_is_preempted, "xor %eax, %eax");
+DEF_NATIVE(lock, queued_spin_unlock, "movb $0, (%eax)");
+DEF_NATIVE(lock, vcpu_is_preempted, "xor %eax, %eax");
#endif
unsigned paravirt_patch_ident_32(void *insnbuf, unsigned len)
@@ -41,27 +41,27 @@ unsigned native_patch(u8 type, void *ibuf, unsigned long addr, unsigned len)
end = end_##ops##_##x; \
goto patch_site
switch (type) {
- PATCH_SITE(pv_irq_ops, irq_disable);
- PATCH_SITE(pv_irq_ops, irq_enable);
- PATCH_SITE(pv_irq_ops, restore_fl);
- PATCH_SITE(pv_irq_ops, save_fl);
- PATCH_SITE(pv_cpu_ops, iret);
- PATCH_SITE(pv_mmu_ops, read_cr2);
- PATCH_SITE(pv_mmu_ops, read_cr3);
- PATCH_SITE(pv_mmu_ops, write_cr3);
+ PATCH_SITE(irq, irq_disable);
+ PATCH_SITE(irq, irq_enable);
+ PATCH_SITE(irq, restore_fl);
+ PATCH_SITE(irq, save_fl);
+ PATCH_SITE(cpu, iret);
+ PATCH_SITE(mmu, read_cr2);
+ PATCH_SITE(mmu, read_cr3);
+ PATCH_SITE(mmu, write_cr3);
#if defined(CONFIG_PARAVIRT_SPINLOCKS)
- case PARAVIRT_PATCH(pv_lock_ops.queued_spin_unlock):
+ case PARAVIRT_PATCH(lock.queued_spin_unlock):
if (pv_is_native_spin_unlock()) {
- start = start_pv_lock_ops_queued_spin_unlock;
- end = end_pv_lock_ops_queued_spin_unlock;
+ start = start_lock_queued_spin_unlock;
+ end = end_lock_queued_spin_unlock;
goto patch_site;
}
goto patch_default;
- case PARAVIRT_PATCH(pv_lock_ops.vcpu_is_preempted):
+ case PARAVIRT_PATCH(lock.vcpu_is_preempted):
if (pv_is_native_vcpu_is_preempted()) {
- start = start_pv_lock_ops_vcpu_is_preempted;
- end = end_pv_lock_ops_vcpu_is_preempted;
+ start = start_lock_vcpu_is_preempted;
+ end = end_lock_vcpu_is_preempted;
goto patch_site;
}
goto patch_default;
diff --git a/arch/x86/kernel/paravirt_patch_64.c b/arch/x86/kernel/paravirt_patch_64.c
index 835f1985a115..582e893728e8 100644
--- a/arch/x86/kernel/paravirt_patch_64.c
+++ b/arch/x86/kernel/paravirt_patch_64.c
@@ -3,24 +3,24 @@
#include <asm/asm-offsets.h>
#include <linux/stringify.h>
-DEF_NATIVE(pv_irq_ops, irq_disable, "cli");
-DEF_NATIVE(pv_irq_ops, irq_enable, "sti");
-DEF_NATIVE(pv_irq_ops, restore_fl, "pushq %rdi; popfq");
-DEF_NATIVE(pv_irq_ops, save_fl, "pushfq; popq %rax");
-DEF_NATIVE(pv_mmu_ops, read_cr2, "movq %cr2, %rax");
-DEF_NATIVE(pv_mmu_ops, read_cr3, "movq %cr3, %rax");
-DEF_NATIVE(pv_mmu_ops, write_cr3, "movq %rdi, %cr3");
-DEF_NATIVE(pv_cpu_ops, wbinvd, "wbinvd");
+DEF_NATIVE(irq, irq_disable, "cli");
+DEF_NATIVE(irq, irq_enable, "sti");
+DEF_NATIVE(irq, restore_fl, "pushq %rdi; popfq");
+DEF_NATIVE(irq, save_fl, "pushfq; popq %rax");
+DEF_NATIVE(mmu, read_cr2, "movq %cr2, %rax");
+DEF_NATIVE(mmu, read_cr3, "movq %cr3, %rax");
+DEF_NATIVE(mmu, write_cr3, "movq %rdi, %cr3");
+DEF_NATIVE(cpu, wbinvd, "wbinvd");
-DEF_NATIVE(pv_cpu_ops, usergs_sysret64, "swapgs; sysretq");
-DEF_NATIVE(pv_cpu_ops, swapgs, "swapgs");
+DEF_NATIVE(cpu, usergs_sysret64, "swapgs; sysretq");
+DEF_NATIVE(cpu, swapgs, "swapgs");
DEF_NATIVE(, mov32, "mov %edi, %eax");
DEF_NATIVE(, mov64, "mov %rdi, %rax");
#if defined(CONFIG_PARAVIRT_SPINLOCKS)
-DEF_NATIVE(pv_lock_ops, queued_spin_unlock, "movb $0, (%rdi)");
-DEF_NATIVE(pv_lock_ops, vcpu_is_preempted, "xor %eax, %eax");
+DEF_NATIVE(lock, queued_spin_unlock, "movb $0, (%rdi)");
+DEF_NATIVE(lock, vcpu_is_preempted, "xor %eax, %eax");
#endif
unsigned paravirt_patch_ident_32(void *insnbuf, unsigned len)
@@ -49,29 +49,29 @@ unsigned native_patch(u8 type, void *ibuf, unsigned long addr, unsigned len)
end = end_##ops##_##x; \
goto patch_site
switch(type) {
- PATCH_SITE(pv_irq_ops, restore_fl);
- PATCH_SITE(pv_irq_ops, save_fl);
- PATCH_SITE(pv_irq_ops, irq_enable);
- PATCH_SITE(pv_irq_ops, irq_disable);
- PATCH_SITE(pv_cpu_ops, usergs_sysret64);
- PATCH_SITE(pv_cpu_ops, swapgs);
- PATCH_SITE(pv_mmu_ops, read_cr2);
- PATCH_SITE(pv_mmu_ops, read_cr3);
- PATCH_SITE(pv_mmu_ops, write_cr3);
- PATCH_SITE(pv_cpu_ops, wbinvd);
+ PATCH_SITE(irq, restore_fl);
+ PATCH_SITE(irq, save_fl);
+ PATCH_SITE(irq, irq_enable);
+ PATCH_SITE(irq, irq_disable);
+ PATCH_SITE(cpu, usergs_sysret64);
+ PATCH_SITE(cpu, swapgs);
+ PATCH_SITE(mmu, read_cr2);
+ PATCH_SITE(mmu, read_cr3);
+ PATCH_SITE(mmu, write_cr3);
+ PATCH_SITE(cpu, wbinvd);
#if defined(CONFIG_PARAVIRT_SPINLOCKS)
- case PARAVIRT_PATCH(pv_lock_ops.queued_spin_unlock):
+ case PARAVIRT_PATCH(lock.queued_spin_unlock):
if (pv_is_native_spin_unlock()) {
- start = start_pv_lock_ops_queued_spin_unlock;
- end = end_pv_lock_ops_queued_spin_unlock;
+ start = start_lock_queued_spin_unlock;
+ end = end_lock_queued_spin_unlock;
goto patch_site;
}
goto patch_default;
- case PARAVIRT_PATCH(pv_lock_ops.vcpu_is_preempted):
+ case PARAVIRT_PATCH(lock.vcpu_is_preempted):
if (pv_is_native_vcpu_is_preempted()) {
- start = start_pv_lock_ops_vcpu_is_preempted;
- end = end_pv_lock_ops_vcpu_is_preempted;
+ start = start_lock_vcpu_is_preempted;
+ end = end_lock_vcpu_is_preempted;
goto patch_site;
}
goto patch_default;
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 1463468ba9a0..9044aa5e2389 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -246,7 +246,7 @@ unsigned long long sched_clock(void)
bool using_native_sched_clock(void)
{
- return pv_time_ops.sched_clock == native_sched_clock;
+ return pv_ops.time.sched_clock == native_sched_clock;
}
#else
unsigned long long
diff --git a/arch/x86/kernel/vsmp_64.c b/arch/x86/kernel/vsmp_64.c
index f194e5e1e95c..789918d78697 100644
--- a/arch/x86/kernel/vsmp_64.c
+++ b/arch/x86/kernel/vsmp_64.c
@@ -73,10 +73,10 @@ static unsigned __init vsmp_patch(u8 type, void *ibuf,
unsigned long addr, unsigned len)
{
switch (type) {
- case PARAVIRT_PATCH(pv_irq_ops.irq_enable):
- case PARAVIRT_PATCH(pv_irq_ops.irq_disable):
- case PARAVIRT_PATCH(pv_irq_ops.save_fl):
- case PARAVIRT_PATCH(pv_irq_ops.restore_fl):
+ case PARAVIRT_PATCH(irq.irq_enable):
+ case PARAVIRT_PATCH(irq.irq_disable):
+ case PARAVIRT_PATCH(irq.save_fl):
+ case PARAVIRT_PATCH(irq.restore_fl):
return paravirt_patch_default(type, ibuf, addr, len);
default:
return native_patch(type, ibuf, addr, len);
@@ -111,11 +111,11 @@ static void __init set_vsmp_pv_ops(void)
if (cap & ctl & (1 << 4)) {
/* Setup irq ops and turn on vSMP IRQ fastpath handling */
- pv_irq_ops.irq_disable = PV_CALLEE_SAVE(vsmp_irq_disable);
- pv_irq_ops.irq_enable = PV_CALLEE_SAVE(vsmp_irq_enable);
- pv_irq_ops.save_fl = PV_CALLEE_SAVE(vsmp_save_fl);
- pv_irq_ops.restore_fl = PV_CALLEE_SAVE(vsmp_restore_fl);
- pv_init_ops.patch = vsmp_patch;
+ pv_ops.irq.irq_disable = PV_CALLEE_SAVE(vsmp_irq_disable);
+ pv_ops.irq.irq_enable = PV_CALLEE_SAVE(vsmp_irq_enable);
+ pv_ops.irq.save_fl = PV_CALLEE_SAVE(vsmp_save_fl);
+ pv_ops.irq.restore_fl = PV_CALLEE_SAVE(vsmp_restore_fl);
+ pv_ops.init.patch = vsmp_patch;
ctl &= ~(1 << 4);
}
writel(ctl, address + 4);
diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c
index 52a7c3faee0c..ec7a4209f310 100644
--- a/arch/x86/xen/enlighten_pv.c
+++ b/arch/x86/xen/enlighten_pv.c
@@ -995,11 +995,14 @@ void __init xen_setup_vcpu_info_placement(void)
* percpu area for all cpus, so make use of it.
*/
if (xen_have_vcpu_info_placement) {
- pv_irq_ops.save_fl = __PV_IS_CALLEE_SAVE(xen_save_fl_direct);
- pv_irq_ops.restore_fl = __PV_IS_CALLEE_SAVE(xen_restore_fl_direct);
- pv_irq_ops.irq_disable = __PV_IS_CALLEE_SAVE(xen_irq_disable_direct);
- pv_irq_ops.irq_enable = __PV_IS_CALLEE_SAVE(xen_irq_enable_direct);
- pv_mmu_ops.read_cr2 = xen_read_cr2_direct;
+ pv_ops.irq.save_fl = __PV_IS_CALLEE_SAVE(xen_save_fl_direct);
+ pv_ops.irq.restore_fl =
+ __PV_IS_CALLEE_SAVE(xen_restore_fl_direct);
+ pv_ops.irq.irq_disable =
+ __PV_IS_CALLEE_SAVE(xen_irq_disable_direct);
+ pv_ops.irq.irq_enable =
+ __PV_IS_CALLEE_SAVE(xen_irq_enable_direct);
+ pv_ops.mmu.read_cr2 = xen_read_cr2_direct;
}
}
@@ -1174,14 +1177,14 @@ static void __init xen_boot_params_init_edd(void)
*/
static void __init xen_setup_gdt(int cpu)
{
- pv_cpu_ops.write_gdt_entry = xen_write_gdt_entry_boot;
- pv_cpu_ops.load_gdt = xen_load_gdt_boot;
+ pv_ops.cpu.write_gdt_entry = xen_write_gdt_entry_boot;
+ pv_ops.cpu.load_gdt = xen_load_gdt_boot;
setup_stack_canary_segment(cpu);
switch_to_new_gdt(cpu);
- pv_cpu_ops.write_gdt_entry = xen_write_gdt_entry;
- pv_cpu_ops.load_gdt = xen_load_gdt;
+ pv_ops.cpu.write_gdt_entry = xen_write_gdt_entry;
+ pv_ops.cpu.load_gdt = xen_load_gdt;
}
static void __init xen_dom0_set_legacy_features(void)
@@ -1206,8 +1209,8 @@ asmlinkage __visible void __init xen_start_kernel(void)
/* Install Xen paravirt ops */
pv_info = xen_info;
- pv_init_ops.patch = paravirt_patch_default;
- pv_cpu_ops = xen_cpu_ops;
+ pv_ops.init.patch = paravirt_patch_default;
+ pv_ops.cpu = xen_cpu_ops;
xen_init_irq_ops();
/*
@@ -1276,8 +1279,10 @@ asmlinkage __visible void __init xen_start_kernel(void)
#endif
if (xen_feature(XENFEAT_mmu_pt_update_preserve_ad)) {
- pv_mmu_ops.ptep_modify_prot_start = xen_ptep_modify_prot_start;
- pv_mmu_ops.ptep_modify_prot_commit = xen_ptep_modify_prot_commit;
+ pv_ops.mmu.ptep_modify_prot_start =
+ xen_ptep_modify_prot_start;
+ pv_ops.mmu.ptep_modify_prot_commit =
+ xen_ptep_modify_prot_commit;
}
machine_ops = xen_machine_ops;
diff --git a/arch/x86/xen/irq.c b/arch/x86/xen/irq.c
index 7515a19fd324..850c93f346c7 100644
--- a/arch/x86/xen/irq.c
+++ b/arch/x86/xen/irq.c
@@ -128,6 +128,6 @@ static const struct pv_irq_ops xen_irq_ops __initconst = {
void __init xen_init_irq_ops(void)
{
- pv_irq_ops = xen_irq_ops;
+ pv_ops.irq = xen_irq_ops;
x86_init.irqs.intr_init = xen_init_IRQ;
}
diff --git a/arch/x86/xen/mmu_hvm.c b/arch/x86/xen/mmu_hvm.c
index dd2ad82eee80..57409373750f 100644
--- a/arch/x86/xen/mmu_hvm.c
+++ b/arch/x86/xen/mmu_hvm.c
@@ -73,7 +73,7 @@ static int is_pagetable_dying_supported(void)
void __init xen_hvm_init_mmu_ops(void)
{
if (is_pagetable_dying_supported())
- pv_mmu_ops.exit_mmap = xen_hvm_exit_mmap;
+ pv_ops.mmu.exit_mmap = xen_hvm_exit_mmap;
#ifdef CONFIG_PROC_VMCORE
WARN_ON(register_oldmem_pfn_is_ram(&xen_oldmem_pfn_is_ram));
#endif
diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c
index 1e9098f53967..12180e7283b7 100644
--- a/arch/x86/xen/mmu_pv.c
+++ b/arch/x86/xen/mmu_pv.c
@@ -2216,7 +2216,7 @@ static void __init xen_write_cr3_init(unsigned long cr3)
set_page_prot(initial_page_table, PAGE_KERNEL);
set_page_prot(initial_kernel_pmd, PAGE_KERNEL);
- pv_mmu_ops.write_cr3 = &xen_write_cr3;
+ pv_ops.mmu.write_cr3 = &xen_write_cr3;
}
/*
@@ -2365,27 +2365,27 @@ static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot)
static void __init xen_post_allocator_init(void)
{
- pv_mmu_ops.set_pte = xen_set_pte;
- pv_mmu_ops.set_pmd = xen_set_pmd;
- pv_mmu_ops.set_pud = xen_set_pud;
+ pv_ops.mmu.set_pte = xen_set_pte;
+ pv_ops.mmu.set_pmd = xen_set_pmd;
+ pv_ops.mmu.set_pud = xen_set_pud;
#ifdef CONFIG_X86_64
- pv_mmu_ops.set_p4d = xen_set_p4d;
+ pv_ops.mmu.set_p4d = xen_set_p4d;
#endif
/* This will work as long as patching hasn't happened yet
(which it hasn't) */
- pv_mmu_ops.alloc_pte = xen_alloc_pte;
- pv_mmu_ops.alloc_pmd = xen_alloc_pmd;
- pv_mmu_ops.release_pte = xen_release_pte;
- pv_mmu_ops.release_pmd = xen_release_pmd;
+ pv_ops.mmu.alloc_pte = xen_alloc_pte;
+ pv_ops.mmu.alloc_pmd = xen_alloc_pmd;
+ pv_ops.mmu.release_pte = xen_release_pte;
+ pv_ops.mmu.release_pmd = xen_release_pmd;
#ifdef CONFIG_X86_64
- pv_mmu_ops.alloc_pud = xen_alloc_pud;
- pv_mmu_ops.release_pud = xen_release_pud;
+ pv_ops.mmu.alloc_pud = xen_alloc_pud;
+ pv_ops.mmu.release_pud = xen_release_pud;
#endif
- pv_mmu_ops.make_pte = PV_CALLEE_SAVE(xen_make_pte);
+ pv_ops.mmu.make_pte = PV_CALLEE_SAVE(xen_make_pte);
#ifdef CONFIG_X86_64
- pv_mmu_ops.write_cr3 = &xen_write_cr3;
+ pv_ops.mmu.write_cr3 = &xen_write_cr3;
#endif
}
@@ -2473,7 +2473,7 @@ void __init xen_init_mmu_ops(void)
x86_init.paging.pagetable_init = xen_pagetable_init;
x86_init.hyper.init_after_bootmem = xen_after_bootmem;
- pv_mmu_ops = xen_mmu_ops;
+ pv_ops.mmu = xen_mmu_ops;
memset(dummy_mapping, 0xff, PAGE_SIZE);
}
diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c
index 973f10e05211..23f6793af88a 100644
--- a/arch/x86/xen/spinlock.c
+++ b/arch/x86/xen/spinlock.c
@@ -141,11 +141,12 @@ void __init xen_init_spinlocks(void)
printk(KERN_DEBUG "xen: PV spinlocks enabled\n");
__pv_init_lock_hash();
- pv_lock_ops.queued_spin_lock_slowpath = __pv_queued_spin_lock_slowpath;
- pv_lock_ops.queued_spin_unlock = PV_CALLEE_SAVE(__pv_queued_spin_unlock);
- pv_lock_ops.wait = xen_qlock_wait;
- pv_lock_ops.kick = xen_qlock_kick;
- pv_lock_ops.vcpu_is_preempted = PV_CALLEE_SAVE(xen_vcpu_stolen);
+ pv_ops.lock.queued_spin_lock_slowpath = __pv_queued_spin_lock_slowpath;
+ pv_ops.lock.queued_spin_unlock =
+ PV_CALLEE_SAVE(__pv_queued_spin_unlock);
+ pv_ops.lock.wait = xen_qlock_wait;
+ pv_ops.lock.kick = xen_qlock_kick;
+ pv_ops.lock.vcpu_is_preempted = PV_CALLEE_SAVE(xen_vcpu_stolen);
}
static __init int xen_parse_nopvspin(char *arg)
diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c
index c84f1e039d84..72bf446c3fee 100644
--- a/arch/x86/xen/time.c
+++ b/arch/x86/xen/time.c
@@ -513,7 +513,7 @@ static void __init xen_time_init(void)
void __init xen_init_time_ops(void)
{
xen_sched_clock_offset = xen_clocksource_read();
- pv_time_ops = xen_time_ops;
+ pv_ops.time = xen_time_ops;
x86_init.timers.timer_init = xen_time_init;
x86_init.timers.setup_percpu_clockev = x86_init_noop;
@@ -555,7 +555,7 @@ void __init xen_hvm_init_time_ops(void)
}
xen_sched_clock_offset = xen_clocksource_read();
- pv_time_ops = xen_time_ops;
+ pv_ops.time = xen_time_ops;
x86_init.timers.setup_percpu_clockev = xen_time_init;
x86_cpuinit.setup_percpu_clockev = xen_hvm_setup_cpu_clockevents;
diff --git a/drivers/xen/time.c b/drivers/xen/time.c
index 3e741cd1409c..0968859c29d0 100644
--- a/drivers/xen/time.c
+++ b/drivers/xen/time.c
@@ -175,7 +175,7 @@ void __init xen_time_setup_guest(void)
xen_runstate_remote = !HYPERVISOR_vm_assist(VMASST_CMD_enable,
VMASST_TYPE_runstate_update_flag);
- pv_time_ops.steal_clock = xen_steal_clock;
+ pv_ops.time.steal_clock = xen_steal_clock;
static_key_slow_inc(¶virt_steal_enabled);
if (xen_runstate_remote)
--
2.16.4
^ permalink raw reply related
* [PATCH v3 09/15] x86/paravirt: remove unused paravirt bits
From: Juergen Gross @ 2018-08-28 7:40 UTC (permalink / raw)
To: linux-kernel, xen-devel, x86, virtualization
Cc: Juergen Gross, boris.ostrovsky, rusty, mingo, hpa, akataria, tglx
In-Reply-To: <20180828074026.820-1-jgross@suse.com>
The macros ENABLE_INTERRUPTS_SYSEXIT, GET_CR0_INTO_EAX and
PARAVIRT_ADJUST_EXCEPTION_FRAME are used nowhere. Remove their
definitions.
Signed-off-by: Juergen Gross <jgross@suse.com>
---
arch/x86/include/asm/irqflags.h | 4 ----
arch/x86/include/asm/paravirt.h | 9 +--------
arch/x86/kernel/asm-offsets.c | 1 -
3 files changed, 1 insertion(+), 13 deletions(-)
diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h
index c14f2a74b2be..250bcd40d769 100644
--- a/arch/x86/include/asm/irqflags.h
+++ b/arch/x86/include/asm/irqflags.h
@@ -134,8 +134,6 @@ static inline notrace unsigned long arch_local_irq_save(void)
*/
#define SWAPGS_UNSAFE_STACK swapgs
-#define PARAVIRT_ADJUST_EXCEPTION_FRAME /* */
-
#define INTERRUPT_RETURN jmp native_iret
#define USERGS_SYSRET64 \
swapgs; \
@@ -149,8 +147,6 @@ static inline notrace unsigned long arch_local_irq_save(void)
#endif
#else
#define INTERRUPT_RETURN iret
-#define ENABLE_INTERRUPTS_SYSEXIT sti; sysexit
-#define GET_CR0_INTO_EAX movl %cr0, %eax
#endif
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index a9189b81c7dd..2ba23e98c5cd 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -887,14 +887,7 @@ extern void default_banner(void);
call PARA_INDIRECT(pv_ops+PV_IRQ_irq_enable); \
PV_RESTORE_REGS(clobbers | CLBR_CALLEE_SAVE);)
-#ifdef CONFIG_X86_32
-#define GET_CR0_INTO_EAX \
- push %ecx; push %edx; \
- ANNOTATE_RETPOLINE_SAFE; \
- call PARA_INDIRECT(pv_ops+PV_CPU_read_cr0); \
- pop %edx; pop %ecx
-#else /* !CONFIG_X86_32 */
-
+#ifdef CONFIG_X86_64
/*
* If swapgs is used while the userspace stack is still current,
* there's no way to call a pvop. The PV replacement *must* be
diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c
index 46d14498e214..37e323f3d8c9 100644
--- a/arch/x86/kernel/asm-offsets.c
+++ b/arch/x86/kernel/asm-offsets.c
@@ -69,7 +69,6 @@ void common(void) {
OFFSET(PV_IRQ_irq_disable, paravirt_patch_template, irq.irq_disable);
OFFSET(PV_IRQ_irq_enable, paravirt_patch_template, irq.irq_enable);
OFFSET(PV_CPU_iret, paravirt_patch_template, cpu.iret);
- OFFSET(PV_CPU_read_cr0, paravirt_patch_template, cpu.read_cr0);
OFFSET(PV_MMU_read_cr2, paravirt_patch_template, mmu.read_cr2);
#endif
--
2.16.4
^ permalink raw reply related
* [PATCH v3 10/15] x86/paravirt: introduce new config option PARAVIRT_XXL
From: Juergen Gross @ 2018-08-28 7:40 UTC (permalink / raw)
To: linux-kernel, xen-devel, x86, virtualization
Cc: Juergen Gross, boris.ostrovsky, rusty, mingo, hpa, akataria, tglx
In-Reply-To: <20180828074026.820-1-jgross@suse.com>
A large amount of paravirt ops is used by Xen PV guests only. Add a new
config option PARAVIRT_XXL which is selected by XEN_PV. Later we can
put the Xen PV only paravirt ops under the PARAVIRT_XXL umbrella.
Since irq related paravirt ops are used only by VSMP and Xen PV, let
VSMP select PARAVIRT_XXL, too, in order to enable moving the irq ops
under PARAVIRT_XXL.
Signed-off-by: Juergen Gross <jgross@suse.com>
---
V3:
- let VSMP select PARAVIRT_XXL (Peter Zijlstra)
---
arch/x86/Kconfig | 4 ++++
arch/x86/boot/compressed/misc.h | 1 +
arch/x86/mm/mem_encrypt_identity.c | 1 +
arch/x86/xen/Kconfig | 1 +
4 files changed, 7 insertions(+)
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index c5ff296bc5d1..61dfdb694483 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -523,6 +523,7 @@ config X86_VSMP
bool "ScaleMP vSMP"
select HYPERVISOR_GUEST
select PARAVIRT
+ select PARAVIRT_XXL
depends on X86_64 && PCI
depends on X86_EXTENDED_PLATFORM
depends on SMP
@@ -754,6 +755,9 @@ config PARAVIRT
over full virtualization. However, when run without a hypervisor
the kernel is theoretically slower and slightly larger.
+config PARAVIRT_XXL
+ bool
+
config PARAVIRT_DEBUG
bool "paravirt-ops debugging"
depends on PARAVIRT && DEBUG_KERNEL
diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h
index a423bdb42686..a1d5918765f3 100644
--- a/arch/x86/boot/compressed/misc.h
+++ b/arch/x86/boot/compressed/misc.h
@@ -9,6 +9,7 @@
* paravirt and debugging variants are added.)
*/
#undef CONFIG_PARAVIRT
+#undef CONFIG_PARAVIRT_XXL
#undef CONFIG_PARAVIRT_SPINLOCKS
#undef CONFIG_KASAN
diff --git a/arch/x86/mm/mem_encrypt_identity.c b/arch/x86/mm/mem_encrypt_identity.c
index 7ae36868aed2..a19ef1a416ff 100644
--- a/arch/x86/mm/mem_encrypt_identity.c
+++ b/arch/x86/mm/mem_encrypt_identity.c
@@ -27,6 +27,7 @@
* be extended when new paravirt and debugging variants are added.)
*/
#undef CONFIG_PARAVIRT
+#undef CONFIG_PARAVIRT_XXL
#undef CONFIG_PARAVIRT_SPINLOCKS
#include <linux/kernel.h>
diff --git a/arch/x86/xen/Kconfig b/arch/x86/xen/Kconfig
index c1f98f32c45f..dd92d7bd3613 100644
--- a/arch/x86/xen/Kconfig
+++ b/arch/x86/xen/Kconfig
@@ -18,6 +18,7 @@ config XEN_PV
bool "Xen PV guest support"
default y
depends on XEN
+ select PARAVIRT_XXL
select XEN_HAVE_PVMMU
select XEN_HAVE_VPMU
help
--
2.16.4
^ permalink raw reply related
* [PATCH v3 11/15] x86/paravirt: move items in pv_info under PARAVIRT_XXL umbrella
From: Juergen Gross @ 2018-08-28 7:40 UTC (permalink / raw)
To: linux-kernel, xen-devel, x86, virtualization
Cc: Juergen Gross, boris.ostrovsky, rusty, mingo, hpa, akataria, tglx
In-Reply-To: <20180828074026.820-1-jgross@suse.com>
All items but name in pv_info are needed by Xen PV only. Define them
with CONFIG_PARAVIRT_XXL set only.
Signed-off-by: Juergen Gross <jgross@suse.com>
---
arch/x86/include/asm/paravirt.h | 2 ++
arch/x86/include/asm/paravirt_types.h | 2 ++
arch/x86/include/asm/pgtable-3level_types.h | 2 +-
arch/x86/include/asm/ptrace.h | 2 +-
arch/x86/include/asm/segment.h | 2 +-
arch/x86/kernel/paravirt.c | 2 ++
6 files changed, 9 insertions(+), 3 deletions(-)
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index 2ba23e98c5cd..dbaedf1ed622 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -104,7 +104,9 @@ static inline void wbinvd(void)
PVOP_VCALL0(cpu.wbinvd);
}
+#ifdef CONFIG_PARAVIRT_XXL
#define get_kernel_rpl() (pv_info.kernel_rpl)
+#endif
static inline u64 paravirt_read_msr(unsigned msr)
{
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index 462a54b2bb53..98e1110354b8 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -66,11 +66,13 @@ struct paravirt_callee_save {
/* general info */
struct pv_info {
+#ifdef CONFIG_PARAVIRT_XXL
unsigned int kernel_rpl;
int shared_kernel_pmd;
#ifdef CONFIG_X86_64
u16 extra_user_64bit_cs; /* __USER_CS if none */
+#endif
#endif
const char *name;
diff --git a/arch/x86/include/asm/pgtable-3level_types.h b/arch/x86/include/asm/pgtable-3level_types.h
index 858358a82b14..33845d36897c 100644
--- a/arch/x86/include/asm/pgtable-3level_types.h
+++ b/arch/x86/include/asm/pgtable-3level_types.h
@@ -20,7 +20,7 @@ typedef union {
} pte_t;
#endif /* !__ASSEMBLY__ */
-#ifdef CONFIG_PARAVIRT
+#ifdef CONFIG_PARAVIRT_XXL
#define SHARED_KERNEL_PMD ((!static_cpu_has(X86_FEATURE_PTI) && \
(pv_info.shared_kernel_pmd)))
#else
diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h
index 6de1fd3d0097..250be50aa257 100644
--- a/arch/x86/include/asm/ptrace.h
+++ b/arch/x86/include/asm/ptrace.h
@@ -144,7 +144,7 @@ static inline int v8086_mode(struct pt_regs *regs)
static inline bool user_64bit_mode(struct pt_regs *regs)
{
#ifdef CONFIG_X86_64
-#ifndef CONFIG_PARAVIRT
+#ifndef CONFIG_PARAVIRT_XXL
/*
* On non-paravirt systems, this is the only long mode CPL 3
* selector. We do not allow long mode selectors in the LDT.
diff --git a/arch/x86/include/asm/segment.h b/arch/x86/include/asm/segment.h
index e293c122d0d5..0ffbe9519e68 100644
--- a/arch/x86/include/asm/segment.h
+++ b/arch/x86/include/asm/segment.h
@@ -211,7 +211,7 @@
#endif
-#ifndef CONFIG_PARAVIRT
+#ifndef CONFIG_PARAVIRT_XXL
# define get_kernel_rpl() 0
#endif
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index 5fc2b94e1591..ee7da9ec3ea2 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -293,12 +293,14 @@ enum paravirt_lazy_mode paravirt_get_lazy_mode(void)
struct pv_info pv_info = {
.name = "bare hardware",
+#ifdef CONFIG_PARAVIRT_XXL
.kernel_rpl = 0,
.shared_kernel_pmd = 1, /* Only used when CONFIG_X86_PAE is set */
#ifdef CONFIG_X86_64
.extra_user_64bit_cs = __USER_CS,
#endif
+#endif
};
#if defined(CONFIG_X86_32) && !defined(CONFIG_X86_PAE)
--
2.16.4
^ permalink raw reply related
* [PATCH v3 12/15] x86/paravirt: move the Xen-only pv_cpu_ops under the PARAVIRT_XXL umbrella
From: Juergen Gross @ 2018-08-28 7:40 UTC (permalink / raw)
To: linux-kernel, xen-devel, x86, virtualization
Cc: Juergen Gross, boris.ostrovsky, rusty, mingo, hpa, akataria, tglx
In-Reply-To: <20180828074026.820-1-jgross@suse.com>
Most of the paravirt ops defined in pv_cpu_ops are for Xen PV guests
only. Define them only if CONFIG_PARAVIRT_XXL is set.
Signed-off-by: Juergen Gross <jgross@suse.com>
---
arch/x86/include/asm/debugreg.h | 2 +-
arch/x86/include/asm/desc.h | 4 ++--
arch/x86/include/asm/irqflags.h | 16 +++++++++++-----
arch/x86/include/asm/msr.h | 4 ++--
arch/x86/include/asm/paravirt.h | 19 +++++++++++++++++--
arch/x86/include/asm/paravirt_types.h | 5 ++++-
arch/x86/include/asm/pgtable.h | 6 ++++--
arch/x86/include/asm/processor.h | 4 ++--
arch/x86/include/asm/special_insns.h | 9 +++++++--
arch/x86/kernel/asm-offsets.c | 2 ++
arch/x86/kernel/asm-offsets_64.c | 2 ++
arch/x86/kernel/cpu/common.c | 2 +-
arch/x86/kernel/head_64.S | 2 ++
arch/x86/kernel/paravirt.c | 13 ++++++++++++-
arch/x86/kernel/paravirt_patch_32.c | 4 ++++
arch/x86/kernel/paravirt_patch_64.c | 6 +++++-
16 files changed, 78 insertions(+), 22 deletions(-)
diff --git a/arch/x86/include/asm/debugreg.h b/arch/x86/include/asm/debugreg.h
index 4505ac2735ad..9e5ca30738e5 100644
--- a/arch/x86/include/asm/debugreg.h
+++ b/arch/x86/include/asm/debugreg.h
@@ -8,7 +8,7 @@
DECLARE_PER_CPU(unsigned long, cpu_dr7);
-#ifndef CONFIG_PARAVIRT
+#ifndef CONFIG_PARAVIRT_XXL
/*
* These special macros can be used to get or set a debugging register
*/
diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h
index 13c5ee878a47..68a99d2a5f33 100644
--- a/arch/x86/include/asm/desc.h
+++ b/arch/x86/include/asm/desc.h
@@ -108,7 +108,7 @@ static inline int desc_empty(const void *ptr)
return !(desc[0] | desc[1]);
}
-#ifdef CONFIG_PARAVIRT
+#ifdef CONFIG_PARAVIRT_XXL
#include <asm/paravirt.h>
#else
#define load_TR_desc() native_load_tr_desc()
@@ -134,7 +134,7 @@ static inline void paravirt_alloc_ldt(struct desc_struct *ldt, unsigned entries)
static inline void paravirt_free_ldt(struct desc_struct *ldt, unsigned entries)
{
}
-#endif /* CONFIG_PARAVIRT */
+#endif /* CONFIG_PARAVIRT_XXL */
#define store_ldt(ldt) asm("sldt %0" : "=m"(ldt))
diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h
index 250bcd40d769..c5e74ba2c95e 100644
--- a/arch/x86/include/asm/irqflags.h
+++ b/arch/x86/include/asm/irqflags.h
@@ -121,6 +121,16 @@ static inline notrace unsigned long arch_local_irq_save(void)
#define ENABLE_INTERRUPTS(x) sti
#define DISABLE_INTERRUPTS(x) cli
+#ifdef CONFIG_X86_64
+#ifdef CONFIG_DEBUG_ENTRY
+#define SAVE_FLAGS(x) pushfq; popq %rax
+#endif
+#endif
+#endif /* __ASSEMBLY__ */
+#endif /* CONFIG_PARAVIRT */
+
+#ifndef CONFIG_PARAVIRT_XXL
+#ifdef __ASSEMBLY__
#ifdef CONFIG_X86_64
#define SWAPGS swapgs
/*
@@ -142,16 +152,12 @@ static inline notrace unsigned long arch_local_irq_save(void)
swapgs; \
sysretl
-#ifdef CONFIG_DEBUG_ENTRY
-#define SAVE_FLAGS(x) pushfq; popq %rax
-#endif
#else
#define INTERRUPT_RETURN iret
#endif
-
#endif /* __ASSEMBLY__ */
-#endif /* CONFIG_PARAVIRT */
+#endif /* CONFIG_PARAVIRT_XXL */
#ifndef __ASSEMBLY__
static inline int arch_irqs_disabled_flags(unsigned long flags)
diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h
index 04addd6e0a4a..91e4cf189914 100644
--- a/arch/x86/include/asm/msr.h
+++ b/arch/x86/include/asm/msr.h
@@ -242,7 +242,7 @@ static inline unsigned long long native_read_pmc(int counter)
return EAX_EDX_VAL(val, low, high);
}
-#ifdef CONFIG_PARAVIRT
+#ifdef CONFIG_PARAVIRT_XXL
#include <asm/paravirt.h>
#else
#include <linux/errno.h>
@@ -305,7 +305,7 @@ do { \
#define rdpmcl(counter, val) ((val) = native_read_pmc(counter))
-#endif /* !CONFIG_PARAVIRT */
+#endif /* !CONFIG_PARAVIRT_XXL */
/*
* 64-bit version of wrmsr_safe():
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index dbaedf1ed622..686a68004b5f 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -17,6 +17,7 @@
#include <linux/cpumask.h>
#include <asm/frame.h>
+#ifdef CONFIG_PARAVIRT_XXL
static inline void load_sp0(unsigned long sp0)
{
PVOP_VCALL1(cpu.load_sp0, sp0);
@@ -51,6 +52,7 @@ static inline void write_cr0(unsigned long x)
{
PVOP_VCALL1(cpu.write_cr0, x);
}
+#endif
static inline unsigned long read_cr2(void)
{
@@ -72,6 +74,7 @@ static inline void write_cr3(unsigned long x)
PVOP_VCALL1(mmu.write_cr3, x);
}
+#ifdef CONFIG_PARAVIRT_XXL
static inline void __write_cr4(unsigned long x)
{
PVOP_VCALL1(cpu.write_cr4, x);
@@ -88,6 +91,7 @@ static inline void write_cr8(unsigned long x)
PVOP_VCALL1(cpu.write_cr8, x);
}
#endif
+#endif
static inline void arch_safe_halt(void)
{
@@ -99,14 +103,13 @@ static inline void halt(void)
PVOP_VCALL0(irq.halt);
}
+#ifdef CONFIG_PARAVIRT_XXL
static inline void wbinvd(void)
{
PVOP_VCALL0(cpu.wbinvd);
}
-#ifdef CONFIG_PARAVIRT_XXL
#define get_kernel_rpl() (pv_info.kernel_rpl)
-#endif
static inline u64 paravirt_read_msr(unsigned msr)
{
@@ -171,6 +174,7 @@ static inline int rdmsrl_safe(unsigned msr, unsigned long long *p)
*p = paravirt_read_msr_safe(msr, &err);
return err;
}
+#endif
static inline unsigned long long paravirt_sched_clock(void)
{
@@ -186,6 +190,7 @@ static inline u64 paravirt_steal_clock(int cpu)
return PVOP_CALL1(u64, time.steal_clock, cpu);
}
+#ifdef CONFIG_PARAVIRT_XXL
static inline unsigned long long paravirt_read_pmc(int counter)
{
return PVOP_CALL1(u64, cpu.read_pmc, counter);
@@ -230,6 +235,7 @@ static inline unsigned long paravirt_store_tr(void)
{
return PVOP_CALL0(unsigned long, cpu.store_tr);
}
+
#define store_tr(tr) ((tr) = paravirt_store_tr())
static inline void load_TLS(struct thread_struct *t, unsigned cpu)
{
@@ -263,6 +269,7 @@ static inline void set_iopl_mask(unsigned mask)
{
PVOP_VCALL1(cpu.set_iopl_mask, mask);
}
+#endif
/* The paravirtualized I/O functions */
static inline void slow_down_io(void)
@@ -618,6 +625,7 @@ static inline void pmd_clear(pmd_t *pmdp)
}
#endif /* CONFIG_X86_PAE */
+#ifdef CONFIG_PARAVIRT_XXL
#define __HAVE_ARCH_START_CONTEXT_SWITCH
static inline void arch_start_context_switch(struct task_struct *prev)
{
@@ -628,6 +636,7 @@ static inline void arch_end_context_switch(struct task_struct *next)
{
PVOP_VCALL1(cpu.end_context_switch, next);
}
+#endif
#define __HAVE_ARCH_ENTER_LAZY_MMU_MODE
static inline void arch_enter_lazy_mmu_mode(void)
@@ -870,10 +879,12 @@ extern void default_banner(void);
#define PARA_INDIRECT(addr) *%cs:addr
#endif
+#ifdef CONFIG_PARAVIRT_XXL
#define INTERRUPT_RETURN \
PARA_SITE(PARA_PATCH(PV_CPU_iret), \
ANNOTATE_RETPOLINE_SAFE; \
jmp PARA_INDIRECT(pv_ops+PV_CPU_iret);)
+#endif
#define DISABLE_INTERRUPTS(clobbers) \
PARA_SITE(PARA_PATCH(PV_IRQ_irq_disable), \
@@ -890,6 +901,7 @@ extern void default_banner(void);
PV_RESTORE_REGS(clobbers | CLBR_CALLEE_SAVE);)
#ifdef CONFIG_X86_64
+#ifdef CONFIG_PARAVIRT_XXL
/*
* If swapgs is used while the userspace stack is still current,
* there's no way to call a pvop. The PV replacement *must* be
@@ -909,15 +921,18 @@ extern void default_banner(void);
ANNOTATE_RETPOLINE_SAFE; \
call PARA_INDIRECT(pv_ops+PV_CPU_swapgs); \
)
+#endif
#define GET_CR2_INTO_RAX \
ANNOTATE_RETPOLINE_SAFE; \
call PARA_INDIRECT(pv_ops+PV_MMU_read_cr2);
+#ifdef CONFIG_PARAVIRT_XXL
#define USERGS_SYSRET64 \
PARA_SITE(PARA_PATCH(PV_CPU_usergs_sysret64), \
ANNOTATE_RETPOLINE_SAFE; \
jmp PARA_INDIRECT(pv_ops+PV_CPU_usergs_sysret64);)
+#endif
#ifdef CONFIG_DEBUG_ENTRY
#define SAVE_FLAGS(clobbers) \
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index 98e1110354b8..30ee6538442c 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -106,6 +106,9 @@ struct pv_time_ops {
struct pv_cpu_ops {
/* hooks for various privileged instructions */
+ void (*io_delay)(void);
+
+#ifdef CONFIG_PARAVIRT_XXL
unsigned long (*get_debugreg)(int regno);
void (*set_debugreg)(int regno, unsigned long value);
@@ -143,7 +146,6 @@ struct pv_cpu_ops {
void (*set_iopl_mask)(unsigned mask);
void (*wbinvd)(void);
- void (*io_delay)(void);
/* cpuid emulation, mostly so that caps bits can be disabled */
void (*cpuid)(unsigned int *eax, unsigned int *ebx,
@@ -178,6 +180,7 @@ struct pv_cpu_ops {
void (*start_context_switch)(struct task_struct *prev);
void (*end_context_switch)(struct task_struct *next);
+#endif
} __no_randomize_layout;
struct pv_irq_ops {
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index e4ffa565a69f..5bb0fe3b7e00 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -111,10 +111,12 @@ extern pmdval_t early_pmd_flags;
#define pte_val(x) native_pte_val(x)
#define __pte(x) native_make_pte(x)
-#define arch_end_context_switch(prev) do {} while(0)
-
#endif /* CONFIG_PARAVIRT */
+#ifndef CONFIG_PARAVIRT_XXL
+#define arch_end_context_switch(prev) do {} while(0)
+#endif /* CONFIG_PARAVIRT_XXL */
+
/*
* The following only work if pte_present() is true.
* Undefined behaviour if not..
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index c24297268ebc..a6220620dcf8 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -576,7 +576,7 @@ static inline bool on_thread_stack(void)
current_stack_pointer) < THREAD_SIZE;
}
-#ifdef CONFIG_PARAVIRT
+#ifdef CONFIG_PARAVIRT_XXL
#include <asm/paravirt.h>
#else
#define __cpuid native_cpuid
@@ -587,7 +587,7 @@ static inline void load_sp0(unsigned long sp0)
}
#define set_iopl_mask native_set_iopl_mask
-#endif /* CONFIG_PARAVIRT */
+#endif /* CONFIG_PARAVIRT_XXL */
/* Free all resources held by a thread. */
extern void release_thread(struct task_struct *);
diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h
index 317fc59b512c..2aa6ce4bf159 100644
--- a/arch/x86/include/asm/special_insns.h
+++ b/arch/x86/include/asm/special_insns.h
@@ -143,8 +143,9 @@ static inline unsigned long __read_cr4(void)
#ifdef CONFIG_PARAVIRT
#include <asm/paravirt.h>
-#else
+#endif
+#ifndef CONFIG_PARAVIRT_XXL
static inline unsigned long read_cr0(void)
{
return native_read_cr0();
@@ -154,7 +155,9 @@ static inline void write_cr0(unsigned long x)
{
native_write_cr0(x);
}
+#endif
+#ifndef CONFIG_PARAVIRT
static inline unsigned long read_cr2(void)
{
return native_read_cr2();
@@ -178,7 +181,9 @@ static inline void write_cr3(unsigned long x)
{
native_write_cr3(x);
}
+#endif
+#ifndef CONFIG_PARAVIRT_XXL
static inline void __write_cr4(unsigned long x)
{
native_write_cr4(x);
@@ -208,7 +213,7 @@ static inline void load_gs_index(unsigned selector)
#endif
-#endif/* CONFIG_PARAVIRT */
+#endif/* CONFIG_PARAVIRT_XXL */
static inline void clflush(volatile void *__p)
{
diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c
index 37e323f3d8c9..0fe233d98d17 100644
--- a/arch/x86/kernel/asm-offsets.c
+++ b/arch/x86/kernel/asm-offsets.c
@@ -68,7 +68,9 @@ void common(void) {
BLANK();
OFFSET(PV_IRQ_irq_disable, paravirt_patch_template, irq.irq_disable);
OFFSET(PV_IRQ_irq_enable, paravirt_patch_template, irq.irq_enable);
+#ifdef CONFIG_PARAVIRT_XXL
OFFSET(PV_CPU_iret, paravirt_patch_template, cpu.iret);
+#endif
OFFSET(PV_MMU_read_cr2, paravirt_patch_template, mmu.read_cr2);
#endif
diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c
index 3384b03e717f..2a15d420a84d 100644
--- a/arch/x86/kernel/asm-offsets_64.c
+++ b/arch/x86/kernel/asm-offsets_64.c
@@ -21,9 +21,11 @@ static char syscalls_ia32[] = {
int main(void)
{
#ifdef CONFIG_PARAVIRT
+#ifdef CONFIG_PARAVIRT_XXL
OFFSET(PV_CPU_usergs_sysret64, paravirt_patch_template,
cpu.usergs_sysret64);
OFFSET(PV_CPU_swapgs, paravirt_patch_template, cpu.swapgs);
+#endif
#ifdef CONFIG_DEBUG_ENTRY
OFFSET(PV_IRQ_save_fl, paravirt_patch_template, irq.save_fl);
#endif
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 1f089e1c79d3..ffe6904eca1c 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1239,7 +1239,7 @@ static void generic_identify(struct cpuinfo_x86 *c)
* ESPFIX issue, we can change this.
*/
#ifdef CONFIG_X86_32
-# ifdef CONFIG_PARAVIRT
+# ifdef CONFIG_PARAVIRT_XXL
do {
extern void native_iret(void);
if (pv_ops.cpu.iret == native_iret)
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index 15ebc2fc166e..a5bd72a0ee1a 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -31,6 +31,8 @@
#define GET_CR2_INTO(reg) GET_CR2_INTO_RAX ; movq %rax, reg
#else
#define GET_CR2_INTO(reg) movq %cr2, reg
+#endif
+#ifndef CONFIG_PARAVIRT_XXL
#define INTERRUPT_RETURN iretq
#endif
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index ee7da9ec3ea2..d29b46621543 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -101,6 +101,7 @@ static unsigned paravirt_patch_call(void *insnbuf, const void *target,
return 5;
}
+#ifdef CONFIG_PARAVIRT_XXL
static unsigned paravirt_patch_jmp(void *insnbuf, const void *target,
unsigned long addr, unsigned len)
{
@@ -119,6 +120,7 @@ static unsigned paravirt_patch_jmp(void *insnbuf, const void *target,
return 5;
}
+#endif
DEFINE_STATIC_KEY_TRUE(virt_spin_lock_key);
@@ -150,10 +152,12 @@ unsigned paravirt_patch_default(u8 type, void *insnbuf,
else if (opfunc == _paravirt_ident_64)
ret = paravirt_patch_ident_64(insnbuf, len);
+#ifdef CONFIG_PARAVIRT_XXL
else if (type == PARAVIRT_PATCH(cpu.iret) ||
type == PARAVIRT_PATCH(cpu.usergs_sysret64))
/* If operation requires a jmp, then jmp */
ret = paravirt_patch_jmp(insnbuf, opfunc, addr, len);
+#endif
else
/* Otherwise call the function. */
ret = paravirt_patch_call(insnbuf, opfunc, addr, len);
@@ -262,6 +266,7 @@ void paravirt_flush_lazy_mmu(void)
preempt_enable();
}
+#ifdef CONFIG_PARAVIRT_XXL
void paravirt_start_context_switch(struct task_struct *prev)
{
BUG_ON(preemptible());
@@ -282,6 +287,7 @@ void paravirt_end_context_switch(struct task_struct *next)
if (test_and_clear_ti_thread_flag(task_thread_info(next), TIF_LAZY_MMU_UPDATES))
arch_enter_lazy_mmu_mode();
}
+#endif
enum paravirt_lazy_mode paravirt_get_lazy_mode(void)
{
@@ -320,6 +326,9 @@ struct paravirt_patch_template pv_ops = {
.time.steal_clock = native_steal_clock,
/* Cpu ops. */
+ .cpu.io_delay = native_io_delay,
+
+#ifdef CONFIG_PARAVIRT_XXL
.cpu.cpuid = native_cpuid,
.cpu.get_debugreg = native_get_debugreg,
.cpu.set_debugreg = native_set_debugreg,
@@ -361,10 +370,10 @@ struct paravirt_patch_template pv_ops = {
.cpu.swapgs = native_swapgs,
.cpu.set_iopl_mask = native_set_iopl_mask,
- .cpu.io_delay = native_io_delay,
.cpu.start_context_switch = paravirt_nop,
.cpu.end_context_switch = paravirt_nop,
+#endif
/* Irq ops. */
.irq.save_fl = __PV_IS_CALLEE_SAVE(native_save_fl),
@@ -463,10 +472,12 @@ struct paravirt_patch_template pv_ops = {
#endif
};
+#ifdef CONFIG_PARAVIRT_XXL
/* At this point, native_get/set_debugreg has real function entries */
NOKPROBE_SYMBOL(native_get_debugreg);
NOKPROBE_SYMBOL(native_set_debugreg);
NOKPROBE_SYMBOL(native_load_idt);
+#endif
EXPORT_SYMBOL_GPL(pv_ops);
EXPORT_SYMBOL_GPL(pv_info);
diff --git a/arch/x86/kernel/paravirt_patch_32.c b/arch/x86/kernel/paravirt_patch_32.c
index 026fa43e9261..5a20aa56efc0 100644
--- a/arch/x86/kernel/paravirt_patch_32.c
+++ b/arch/x86/kernel/paravirt_patch_32.c
@@ -5,7 +5,9 @@ DEF_NATIVE(irq, irq_disable, "cli");
DEF_NATIVE(irq, irq_enable, "sti");
DEF_NATIVE(irq, restore_fl, "push %eax; popf");
DEF_NATIVE(irq, save_fl, "pushf; pop %eax");
+#ifdef CONFIG_PARAVIRT_XXL
DEF_NATIVE(cpu, iret, "iret");
+#endif
DEF_NATIVE(mmu, read_cr2, "mov %cr2, %eax");
DEF_NATIVE(mmu, write_cr3, "mov %eax, %cr3");
DEF_NATIVE(mmu, read_cr3, "mov %cr3, %eax");
@@ -45,7 +47,9 @@ unsigned native_patch(u8 type, void *ibuf, unsigned long addr, unsigned len)
PATCH_SITE(irq, irq_enable);
PATCH_SITE(irq, restore_fl);
PATCH_SITE(irq, save_fl);
+#ifdef CONFIG_PARAVIRT_XXL
PATCH_SITE(cpu, iret);
+#endif
PATCH_SITE(mmu, read_cr2);
PATCH_SITE(mmu, read_cr3);
PATCH_SITE(mmu, write_cr3);
diff --git a/arch/x86/kernel/paravirt_patch_64.c b/arch/x86/kernel/paravirt_patch_64.c
index 582e893728e8..461aba038ada 100644
--- a/arch/x86/kernel/paravirt_patch_64.c
+++ b/arch/x86/kernel/paravirt_patch_64.c
@@ -10,10 +10,12 @@ DEF_NATIVE(irq, save_fl, "pushfq; popq %rax");
DEF_NATIVE(mmu, read_cr2, "movq %cr2, %rax");
DEF_NATIVE(mmu, read_cr3, "movq %cr3, %rax");
DEF_NATIVE(mmu, write_cr3, "movq %rdi, %cr3");
+#ifdef CONFIG_PARAVIRT_XXL
DEF_NATIVE(cpu, wbinvd, "wbinvd");
DEF_NATIVE(cpu, usergs_sysret64, "swapgs; sysretq");
DEF_NATIVE(cpu, swapgs, "swapgs");
+#endif
DEF_NATIVE(, mov32, "mov %edi, %eax");
DEF_NATIVE(, mov64, "mov %rdi, %rax");
@@ -53,12 +55,14 @@ unsigned native_patch(u8 type, void *ibuf, unsigned long addr, unsigned len)
PATCH_SITE(irq, save_fl);
PATCH_SITE(irq, irq_enable);
PATCH_SITE(irq, irq_disable);
+#ifdef CONFIG_PARAVIRT_XXL
PATCH_SITE(cpu, usergs_sysret64);
PATCH_SITE(cpu, swapgs);
+ PATCH_SITE(cpu, wbinvd);
+#endif
PATCH_SITE(mmu, read_cr2);
PATCH_SITE(mmu, read_cr3);
PATCH_SITE(mmu, write_cr3);
- PATCH_SITE(cpu, wbinvd);
#if defined(CONFIG_PARAVIRT_SPINLOCKS)
case PARAVIRT_PATCH(lock.queued_spin_unlock):
if (pv_is_native_spin_unlock()) {
--
2.16.4
^ permalink raw reply related
* [PATCH v3 13/15] x86/paravirt: move the pv_irq_ops under the PARAVIRT_XXL umbrella
From: Juergen Gross @ 2018-08-28 7:40 UTC (permalink / raw)
To: linux-kernel, xen-devel, x86, virtualization
Cc: Juergen Gross, boris.ostrovsky, rusty, mingo, hpa, akataria, tglx
In-Reply-To: <20180828074026.820-1-jgross@suse.com>
All of the paravirt ops defined in pv_irq_ops are for Xen PV guests
or VSMP only. Define them only if CONFIG_PARAVIRT_XXL is set.
Signed-off-by: Juergen Gross <jgross@suse.com>
---
V3:
- put all irq ops under XXL (Peter Zijlstra)
---
arch/x86/include/asm/irqflags.h | 8 +-------
arch/x86/include/asm/paravirt.h | 6 +++---
arch/x86/include/asm/paravirt_types.h | 3 ++-
arch/x86/kernel/asm-offsets.c | 2 +-
arch/x86/kernel/asm-offsets_64.c | 2 +-
arch/x86/kernel/paravirt.c | 2 +-
arch/x86/kernel/paravirt_patch_32.c | 4 ++--
arch/x86/kernel/paravirt_patch_64.c | 4 +++-
arch/x86/kernel/vsmp_64.c | 2 +-
9 files changed, 15 insertions(+), 18 deletions(-)
diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h
index c5e74ba2c95e..d84517184841 100644
--- a/arch/x86/include/asm/irqflags.h
+++ b/arch/x86/include/asm/irqflags.h
@@ -63,7 +63,7 @@ static inline __cpuidle void native_halt(void)
#endif
-#ifdef CONFIG_PARAVIRT
+#ifdef CONFIG_PARAVIRT_XXL
#include <asm/paravirt.h>
#else
#ifndef __ASSEMBLY__
@@ -125,13 +125,7 @@ static inline notrace unsigned long arch_local_irq_save(void)
#ifdef CONFIG_DEBUG_ENTRY
#define SAVE_FLAGS(x) pushfq; popq %rax
#endif
-#endif
-#endif /* __ASSEMBLY__ */
-#endif /* CONFIG_PARAVIRT */
-#ifndef CONFIG_PARAVIRT_XXL
-#ifdef __ASSEMBLY__
-#ifdef CONFIG_X86_64
#define SWAPGS swapgs
/*
* Currently paravirt can't handle swapgs nicely when we
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index 686a68004b5f..512433c56c33 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -91,7 +91,6 @@ static inline void write_cr8(unsigned long x)
PVOP_VCALL1(cpu.write_cr8, x);
}
#endif
-#endif
static inline void arch_safe_halt(void)
{
@@ -103,7 +102,6 @@ static inline void halt(void)
PVOP_VCALL0(irq.halt);
}
-#ifdef CONFIG_PARAVIRT_XXL
static inline void wbinvd(void)
{
PVOP_VCALL0(cpu.wbinvd);
@@ -770,6 +768,7 @@ bool __raw_callee_save___native_vcpu_is_preempted(long cpu);
#define __PV_IS_CALLEE_SAVE(func) \
((struct paravirt_callee_save) { func })
+#ifdef CONFIG_PARAVIRT_XXL
static inline notrace unsigned long arch_local_save_flags(void)
{
return PVOP_CALLEE0(unsigned long, irq.save_fl);
@@ -798,6 +797,7 @@ static inline notrace unsigned long arch_local_irq_save(void)
arch_local_irq_disable();
return f;
}
+#endif
/* Make sure as little as possible of this mess escapes. */
@@ -884,7 +884,6 @@ extern void default_banner(void);
PARA_SITE(PARA_PATCH(PV_CPU_iret), \
ANNOTATE_RETPOLINE_SAFE; \
jmp PARA_INDIRECT(pv_ops+PV_CPU_iret);)
-#endif
#define DISABLE_INTERRUPTS(clobbers) \
PARA_SITE(PARA_PATCH(PV_IRQ_irq_disable), \
@@ -899,6 +898,7 @@ extern void default_banner(void);
ANNOTATE_RETPOLINE_SAFE; \
call PARA_INDIRECT(pv_ops+PV_IRQ_irq_enable); \
PV_RESTORE_REGS(clobbers | CLBR_CALLEE_SAVE);)
+#endif
#ifdef CONFIG_X86_64
#ifdef CONFIG_PARAVIRT_XXL
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index 30ee6538442c..44738bf39584 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -184,6 +184,7 @@ struct pv_cpu_ops {
} __no_randomize_layout;
struct pv_irq_ops {
+#ifdef CONFIG_PARAVIRT_XXL
/*
* Get/set interrupt state. save_fl and restore_fl are only
* expected to use X86_EFLAGS_IF; all other bits
@@ -200,7 +201,7 @@ struct pv_irq_ops {
void (*safe_halt)(void);
void (*halt)(void);
-
+#endif
} __no_randomize_layout;
struct pv_mmu_ops {
diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c
index 0fe233d98d17..28e7572ff74d 100644
--- a/arch/x86/kernel/asm-offsets.c
+++ b/arch/x86/kernel/asm-offsets.c
@@ -66,9 +66,9 @@ void common(void) {
#ifdef CONFIG_PARAVIRT
BLANK();
+#ifdef CONFIG_PARAVIRT_XXL
OFFSET(PV_IRQ_irq_disable, paravirt_patch_template, irq.irq_disable);
OFFSET(PV_IRQ_irq_enable, paravirt_patch_template, irq.irq_enable);
-#ifdef CONFIG_PARAVIRT_XXL
OFFSET(PV_CPU_iret, paravirt_patch_template, cpu.iret);
#endif
OFFSET(PV_MMU_read_cr2, paravirt_patch_template, mmu.read_cr2);
diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c
index 2a15d420a84d..ddced33184b5 100644
--- a/arch/x86/kernel/asm-offsets_64.c
+++ b/arch/x86/kernel/asm-offsets_64.c
@@ -25,9 +25,9 @@ int main(void)
OFFSET(PV_CPU_usergs_sysret64, paravirt_patch_template,
cpu.usergs_sysret64);
OFFSET(PV_CPU_swapgs, paravirt_patch_template, cpu.swapgs);
-#endif
#ifdef CONFIG_DEBUG_ENTRY
OFFSET(PV_IRQ_save_fl, paravirt_patch_template, irq.save_fl);
+#endif
#endif
BLANK();
#endif
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index d29b46621543..d48124be3b01 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -373,7 +373,6 @@ struct paravirt_patch_template pv_ops = {
.cpu.start_context_switch = paravirt_nop,
.cpu.end_context_switch = paravirt_nop,
-#endif
/* Irq ops. */
.irq.save_fl = __PV_IS_CALLEE_SAVE(native_save_fl),
@@ -382,6 +381,7 @@ struct paravirt_patch_template pv_ops = {
.irq.irq_enable = __PV_IS_CALLEE_SAVE(native_irq_enable),
.irq.safe_halt = native_safe_halt,
.irq.halt = native_halt,
+#endif
/* Mmu ops. */
.mmu.read_cr2 = native_read_cr2,
diff --git a/arch/x86/kernel/paravirt_patch_32.c b/arch/x86/kernel/paravirt_patch_32.c
index 5a20aa56efc0..1d44705c6528 100644
--- a/arch/x86/kernel/paravirt_patch_32.c
+++ b/arch/x86/kernel/paravirt_patch_32.c
@@ -1,11 +1,11 @@
// SPDX-License-Identifier: GPL-2.0
#include <asm/paravirt.h>
+#ifdef CONFIG_PARAVIRT_XXL
DEF_NATIVE(irq, irq_disable, "cli");
DEF_NATIVE(irq, irq_enable, "sti");
DEF_NATIVE(irq, restore_fl, "push %eax; popf");
DEF_NATIVE(irq, save_fl, "pushf; pop %eax");
-#ifdef CONFIG_PARAVIRT_XXL
DEF_NATIVE(cpu, iret, "iret");
#endif
DEF_NATIVE(mmu, read_cr2, "mov %cr2, %eax");
@@ -43,11 +43,11 @@ unsigned native_patch(u8 type, void *ibuf, unsigned long addr, unsigned len)
end = end_##ops##_##x; \
goto patch_site
switch (type) {
+#ifdef CONFIG_PARAVIRT_XXL
PATCH_SITE(irq, irq_disable);
PATCH_SITE(irq, irq_enable);
PATCH_SITE(irq, restore_fl);
PATCH_SITE(irq, save_fl);
-#ifdef CONFIG_PARAVIRT_XXL
PATCH_SITE(cpu, iret);
#endif
PATCH_SITE(mmu, read_cr2);
diff --git a/arch/x86/kernel/paravirt_patch_64.c b/arch/x86/kernel/paravirt_patch_64.c
index 461aba038ada..b00937963a0f 100644
--- a/arch/x86/kernel/paravirt_patch_64.c
+++ b/arch/x86/kernel/paravirt_patch_64.c
@@ -3,10 +3,12 @@
#include <asm/asm-offsets.h>
#include <linux/stringify.h>
+#ifdef CONFIG_PARAVIRT_XXL
DEF_NATIVE(irq, irq_disable, "cli");
DEF_NATIVE(irq, irq_enable, "sti");
DEF_NATIVE(irq, restore_fl, "pushq %rdi; popfq");
DEF_NATIVE(irq, save_fl, "pushfq; popq %rax");
+#endif
DEF_NATIVE(mmu, read_cr2, "movq %cr2, %rax");
DEF_NATIVE(mmu, read_cr3, "movq %cr3, %rax");
DEF_NATIVE(mmu, write_cr3, "movq %rdi, %cr3");
@@ -51,11 +53,11 @@ unsigned native_patch(u8 type, void *ibuf, unsigned long addr, unsigned len)
end = end_##ops##_##x; \
goto patch_site
switch(type) {
+#ifdef CONFIG_PARAVIRT_XXL
PATCH_SITE(irq, restore_fl);
PATCH_SITE(irq, save_fl);
PATCH_SITE(irq, irq_enable);
PATCH_SITE(irq, irq_disable);
-#ifdef CONFIG_PARAVIRT_XXL
PATCH_SITE(cpu, usergs_sysret64);
PATCH_SITE(cpu, swapgs);
PATCH_SITE(cpu, wbinvd);
diff --git a/arch/x86/kernel/vsmp_64.c b/arch/x86/kernel/vsmp_64.c
index 789918d78697..1eae5af491c2 100644
--- a/arch/x86/kernel/vsmp_64.c
+++ b/arch/x86/kernel/vsmp_64.c
@@ -26,7 +26,7 @@
#define TOPOLOGY_REGISTER_OFFSET 0x10
-#if defined CONFIG_PCI && defined CONFIG_PARAVIRT
+#if defined CONFIG_PCI && defined CONFIG_PARAVIRT_XXL
/*
* Interrupt control on vSMPowered systems:
* ~AC is a shadow of IF. If IF is 'on' AC should be 'off'
--
2.16.4
^ permalink raw reply related
* [PATCH v3 14/15] x86/paravirt: move the Xen-only pv_mmu_ops under the PARAVIRT_XXL umbrella
From: Juergen Gross @ 2018-08-28 7:40 UTC (permalink / raw)
To: linux-kernel, xen-devel, x86, virtualization
Cc: Juergen Gross, boris.ostrovsky, rusty, mingo, hpa, akataria, tglx
In-Reply-To: <20180828074026.820-1-jgross@suse.com>
Most of the paravirt ops defined in pv_mmu_ops are for Xen PV guests
only. Define them only if CONFIG_PARAVIRT_XXL is set.
Signed-off-by: Juergen Gross <jgross@suse.com>
---
arch/x86/include/asm/fixmap.h | 2 +-
arch/x86/include/asm/mmu_context.h | 4 +-
arch/x86/include/asm/paravirt.h | 125 +++++++++++++++++-----------------
arch/x86/include/asm/paravirt_types.h | 33 ++++-----
arch/x86/include/asm/pgalloc.h | 2 +-
arch/x86/include/asm/pgtable.h | 7 +-
arch/x86/include/asm/special_insns.h | 11 +--
arch/x86/kernel/asm-offsets.c | 4 +-
arch/x86/kernel/head_64.S | 4 +-
arch/x86/kernel/paravirt.c | 15 ++--
arch/x86/kernel/paravirt_patch_32.c | 4 +-
arch/x86/kernel/paravirt_patch_64.c | 4 +-
12 files changed, 103 insertions(+), 112 deletions(-)
diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h
index e203169931c7..ac80e7eadc3a 100644
--- a/arch/x86/include/asm/fixmap.h
+++ b/arch/x86/include/asm/fixmap.h
@@ -152,7 +152,7 @@ void __native_set_fixmap(enum fixed_addresses idx, pte_t pte);
void native_set_fixmap(enum fixed_addresses idx,
phys_addr_t phys, pgprot_t flags);
-#ifndef CONFIG_PARAVIRT
+#ifndef CONFIG_PARAVIRT_XXL
static inline void __set_fixmap(enum fixed_addresses idx,
phys_addr_t phys, pgprot_t flags)
{
diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index eeeb9289c764..0ca50611e8ce 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -16,12 +16,12 @@
extern atomic64_t last_mm_ctx_id;
-#ifndef CONFIG_PARAVIRT
+#ifndef CONFIG_PARAVIRT_XXL
static inline void paravirt_activate_mm(struct mm_struct *prev,
struct mm_struct *next)
{
}
-#endif /* !CONFIG_PARAVIRT */
+#endif /* !CONFIG_PARAVIRT_XXL */
#ifdef CONFIG_PERF_EVENTS
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index 512433c56c33..63ab58dc5b73 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -17,6 +17,62 @@
#include <linux/cpumask.h>
#include <asm/frame.h>
+static inline unsigned long long paravirt_sched_clock(void)
+{
+ return PVOP_CALL0(unsigned long long, time.sched_clock);
+}
+
+struct static_key;
+extern struct static_key paravirt_steal_enabled;
+extern struct static_key paravirt_steal_rq_enabled;
+
+static inline u64 paravirt_steal_clock(int cpu)
+{
+ return PVOP_CALL1(u64, time.steal_clock, cpu);
+}
+
+/* The paravirtualized I/O functions */
+static inline void slow_down_io(void)
+{
+ pv_ops.cpu.io_delay();
+#ifdef REALLY_SLOW_IO
+ pv_ops.cpu.io_delay();
+ pv_ops.cpu.io_delay();
+ pv_ops.cpu.io_delay();
+#endif
+}
+
+static inline void __flush_tlb(void)
+{
+ PVOP_VCALL0(mmu.flush_tlb_user);
+}
+
+static inline void __flush_tlb_global(void)
+{
+ PVOP_VCALL0(mmu.flush_tlb_kernel);
+}
+
+static inline void __flush_tlb_one_user(unsigned long addr)
+{
+ PVOP_VCALL1(mmu.flush_tlb_one_user, addr);
+}
+
+static inline void flush_tlb_others(const struct cpumask *cpumask,
+ const struct flush_tlb_info *info)
+{
+ PVOP_VCALL2(mmu.flush_tlb_others, cpumask, info);
+}
+
+static inline void paravirt_tlb_remove_table(struct mmu_gather *tlb, void *table)
+{
+ PVOP_VCALL2(mmu.tlb_remove_table, tlb, table);
+}
+
+static inline void paravirt_arch_exit_mmap(struct mm_struct *mm)
+{
+ PVOP_VCALL1(mmu.exit_mmap, mm);
+}
+
#ifdef CONFIG_PARAVIRT_XXL
static inline void load_sp0(unsigned long sp0)
{
@@ -52,7 +108,6 @@ static inline void write_cr0(unsigned long x)
{
PVOP_VCALL1(cpu.write_cr0, x);
}
-#endif
static inline unsigned long read_cr2(void)
{
@@ -74,7 +129,6 @@ static inline void write_cr3(unsigned long x)
PVOP_VCALL1(mmu.write_cr3, x);
}
-#ifdef CONFIG_PARAVIRT_XXL
static inline void __write_cr4(unsigned long x)
{
PVOP_VCALL1(cpu.write_cr4, x);
@@ -172,23 +226,7 @@ static inline int rdmsrl_safe(unsigned msr, unsigned long long *p)
*p = paravirt_read_msr_safe(msr, &err);
return err;
}
-#endif
-static inline unsigned long long paravirt_sched_clock(void)
-{
- return PVOP_CALL0(unsigned long long, time.sched_clock);
-}
-
-struct static_key;
-extern struct static_key paravirt_steal_enabled;
-extern struct static_key paravirt_steal_rq_enabled;
-
-static inline u64 paravirt_steal_clock(int cpu)
-{
- return PVOP_CALL1(u64, time.steal_clock, cpu);
-}
-
-#ifdef CONFIG_PARAVIRT_XXL
static inline unsigned long long paravirt_read_pmc(int counter)
{
return PVOP_CALL1(u64, cpu.read_pmc, counter);
@@ -267,18 +305,6 @@ static inline void set_iopl_mask(unsigned mask)
{
PVOP_VCALL1(cpu.set_iopl_mask, mask);
}
-#endif
-
-/* The paravirtualized I/O functions */
-static inline void slow_down_io(void)
-{
- pv_ops.cpu.io_delay();
-#ifdef REALLY_SLOW_IO
- pv_ops.cpu.io_delay();
- pv_ops.cpu.io_delay();
- pv_ops.cpu.io_delay();
-#endif
-}
static inline void paravirt_activate_mm(struct mm_struct *prev,
struct mm_struct *next)
@@ -292,35 +318,6 @@ static inline void paravirt_arch_dup_mmap(struct mm_struct *oldmm,
PVOP_VCALL2(mmu.dup_mmap, oldmm, mm);
}
-static inline void paravirt_arch_exit_mmap(struct mm_struct *mm)
-{
- PVOP_VCALL1(mmu.exit_mmap, mm);
-}
-
-static inline void __flush_tlb(void)
-{
- PVOP_VCALL0(mmu.flush_tlb_user);
-}
-static inline void __flush_tlb_global(void)
-{
- PVOP_VCALL0(mmu.flush_tlb_kernel);
-}
-static inline void __flush_tlb_one_user(unsigned long addr)
-{
- PVOP_VCALL1(mmu.flush_tlb_one_user, addr);
-}
-
-static inline void flush_tlb_others(const struct cpumask *cpumask,
- const struct flush_tlb_info *info)
-{
- PVOP_VCALL2(mmu.flush_tlb_others, cpumask, info);
-}
-
-static inline void paravirt_tlb_remove_table(struct mmu_gather *tlb, void *table)
-{
- PVOP_VCALL2(mmu.tlb_remove_table, tlb, table);
-}
-
static inline int paravirt_pgd_alloc(struct mm_struct *mm)
{
return PVOP_CALL1(int, mmu.pgd_alloc, mm);
@@ -623,7 +620,6 @@ static inline void pmd_clear(pmd_t *pmdp)
}
#endif /* CONFIG_X86_PAE */
-#ifdef CONFIG_PARAVIRT_XXL
#define __HAVE_ARCH_START_CONTEXT_SWITCH
static inline void arch_start_context_switch(struct task_struct *prev)
{
@@ -634,7 +630,6 @@ static inline void arch_end_context_switch(struct task_struct *next)
{
PVOP_VCALL1(cpu.end_context_switch, next);
}
-#endif
#define __HAVE_ARCH_ENTER_LAZY_MMU_MODE
static inline void arch_enter_lazy_mmu_mode(void)
@@ -657,6 +652,7 @@ static inline void __set_fixmap(unsigned /* enum fixed_addresses */ idx,
{
pv_ops.mmu.set_fixmap(idx, phys, flags);
}
+#endif
#if defined(CONFIG_SMP) && defined(CONFIG_PARAVIRT_SPINLOCKS)
@@ -948,15 +944,20 @@ extern void default_banner(void);
#endif /* __ASSEMBLY__ */
#else /* CONFIG_PARAVIRT */
# define default_banner x86_init_noop
+#endif /* !CONFIG_PARAVIRT */
+
#ifndef __ASSEMBLY__
+#ifndef CONFIG_PARAVIRT_XXL
static inline void paravirt_arch_dup_mmap(struct mm_struct *oldmm,
struct mm_struct *mm)
{
}
+#endif
+#ifndef CONFIG_PARAVIRT
static inline void paravirt_arch_exit_mmap(struct mm_struct *mm)
{
}
+#endif
#endif /* __ASSEMBLY__ */
-#endif /* !CONFIG_PARAVIRT */
#endif /* _ASM_X86_PARAVIRT_H */
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index 44738bf39584..f95b7228c615 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -91,13 +91,14 @@ struct pv_init_ops {
unsigned long addr, unsigned len);
} __no_randomize_layout;
-
+#ifdef CONFIG_PARAVIRT_XXL
struct pv_lazy_ops {
/* Set deferred update mode, used for batching operations. */
void (*enter)(void);
void (*leave)(void);
void (*flush)(void);
} __no_randomize_layout;
+#endif
struct pv_time_ops {
unsigned long long (*sched_clock)(void);
@@ -205,31 +206,30 @@ struct pv_irq_ops {
} __no_randomize_layout;
struct pv_mmu_ops {
+ /* TLB operations */
+ void (*flush_tlb_user)(void);
+ void (*flush_tlb_kernel)(void);
+ void (*flush_tlb_one_user)(unsigned long addr);
+ void (*flush_tlb_others)(const struct cpumask *cpus,
+ const struct flush_tlb_info *info);
+
+ void (*tlb_remove_table)(struct mmu_gather *tlb, void *table);
+
+ /* Hook for intercepting the destruction of an mm_struct. */
+ void (*exit_mmap)(struct mm_struct *mm);
+
+#ifdef CONFIG_PARAVIRT_XXL
unsigned long (*read_cr2)(void);
void (*write_cr2)(unsigned long);
unsigned long (*read_cr3)(void);
void (*write_cr3)(unsigned long);
- /*
- * Hooks for intercepting the creation/use/destruction of an
- * mm_struct.
- */
+ /* Hooks for intercepting the creation/use of an mm_struct. */
void (*activate_mm)(struct mm_struct *prev,
struct mm_struct *next);
void (*dup_mmap)(struct mm_struct *oldmm,
struct mm_struct *mm);
- void (*exit_mmap)(struct mm_struct *mm);
-
-
- /* TLB operations */
- void (*flush_tlb_user)(void);
- void (*flush_tlb_kernel)(void);
- void (*flush_tlb_one_user)(unsigned long addr);
- void (*flush_tlb_others)(const struct cpumask *cpus,
- const struct flush_tlb_info *info);
-
- void (*tlb_remove_table)(struct mmu_gather *tlb, void *table);
/* Hooks for allocating and freeing a pagetable top-level */
int (*pgd_alloc)(struct mm_struct *mm);
@@ -304,6 +304,7 @@ struct pv_mmu_ops {
an mfn. We can tell which is which from the index. */
void (*set_fixmap)(unsigned /* enum fixed_addresses */ idx,
phys_addr_t phys, pgprot_t flags);
+#endif
} __no_randomize_layout;
struct arch_spinlock;
diff --git a/arch/x86/include/asm/pgalloc.h b/arch/x86/include/asm/pgalloc.h
index fbd578daa66e..ec7f43327033 100644
--- a/arch/x86/include/asm/pgalloc.h
+++ b/arch/x86/include/asm/pgalloc.h
@@ -8,7 +8,7 @@
static inline int __paravirt_pgd_alloc(struct mm_struct *mm) { return 0; }
-#ifdef CONFIG_PARAVIRT
+#ifdef CONFIG_PARAVIRT_XXL
#include <asm/paravirt.h>
#else
#define paravirt_pgd_alloc(mm) __paravirt_pgd_alloc(mm)
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 5bb0fe3b7e00..7b0489ca027a 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -55,9 +55,9 @@ extern struct mm_struct *pgd_page_get_mm(struct page *page);
extern pmdval_t early_pmd_flags;
-#ifdef CONFIG_PARAVIRT
+#ifdef CONFIG_PARAVIRT_XXL
#include <asm/paravirt.h>
-#else /* !CONFIG_PARAVIRT */
+#else /* !CONFIG_PARAVIRT_XXL */
#define set_pte(ptep, pte) native_set_pte(ptep, pte)
#define set_pte_at(mm, addr, ptep, pte) native_set_pte_at(mm, addr, ptep, pte)
@@ -111,9 +111,6 @@ extern pmdval_t early_pmd_flags;
#define pte_val(x) native_pte_val(x)
#define __pte(x) native_make_pte(x)
-#endif /* CONFIG_PARAVIRT */
-
-#ifndef CONFIG_PARAVIRT_XXL
#define arch_end_context_switch(prev) do {} while(0)
#endif /* CONFIG_PARAVIRT_XXL */
diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h
index 2aa6ce4bf159..43c029cdc3fe 100644
--- a/arch/x86/include/asm/special_insns.h
+++ b/arch/x86/include/asm/special_insns.h
@@ -141,11 +141,10 @@ static inline unsigned long __read_cr4(void)
return native_read_cr4();
}
-#ifdef CONFIG_PARAVIRT
+#ifdef CONFIG_PARAVIRT_XXL
#include <asm/paravirt.h>
-#endif
+#else
-#ifndef CONFIG_PARAVIRT_XXL
static inline unsigned long read_cr0(void)
{
return native_read_cr0();
@@ -155,9 +154,7 @@ static inline void write_cr0(unsigned long x)
{
native_write_cr0(x);
}
-#endif
-#ifndef CONFIG_PARAVIRT
static inline unsigned long read_cr2(void)
{
return native_read_cr2();
@@ -181,9 +178,7 @@ static inline void write_cr3(unsigned long x)
{
native_write_cr3(x);
}
-#endif
-#ifndef CONFIG_PARAVIRT_XXL
static inline void __write_cr4(unsigned long x)
{
native_write_cr4(x);
@@ -213,7 +208,7 @@ static inline void load_gs_index(unsigned selector)
#endif
-#endif/* CONFIG_PARAVIRT_XXL */
+#endif /* CONFIG_PARAVIRT_XXL */
static inline void clflush(volatile void *__p)
{
diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c
index 28e7572ff74d..fc02c3cf238f 100644
--- a/arch/x86/kernel/asm-offsets.c
+++ b/arch/x86/kernel/asm-offsets.c
@@ -64,13 +64,11 @@ void common(void) {
OFFSET(IA32_RT_SIGFRAME_sigcontext, rt_sigframe_ia32, uc.uc_mcontext);
#endif
-#ifdef CONFIG_PARAVIRT
- BLANK();
#ifdef CONFIG_PARAVIRT_XXL
+ BLANK();
OFFSET(PV_IRQ_irq_disable, paravirt_patch_template, irq.irq_disable);
OFFSET(PV_IRQ_irq_enable, paravirt_patch_template, irq.irq_enable);
OFFSET(PV_CPU_iret, paravirt_patch_template, cpu.iret);
-#endif
OFFSET(PV_MMU_read_cr2, paravirt_patch_template, mmu.read_cr2);
#endif
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index a5bd72a0ee1a..827bca2c2782 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -25,14 +25,12 @@
#include <asm/export.h>
#include <asm/nospec-branch.h>
-#ifdef CONFIG_PARAVIRT
+#ifdef CONFIG_PARAVIRT_XXL
#include <asm/asm-offsets.h>
#include <asm/paravirt.h>
#define GET_CR2_INTO(reg) GET_CR2_INTO_RAX ; movq %rax, reg
#else
#define GET_CR2_INTO(reg) movq %cr2, reg
-#endif
-#ifndef CONFIG_PARAVIRT_XXL
#define INTERRUPT_RETURN iretq
#endif
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index d48124be3b01..afa9a2a5acdc 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -384,11 +384,6 @@ struct paravirt_patch_template pv_ops = {
#endif
/* Mmu ops. */
- .mmu.read_cr2 = native_read_cr2,
- .mmu.write_cr2 = native_write_cr2,
- .mmu.read_cr3 = __native_read_cr3,
- .mmu.write_cr3 = native_write_cr3,
-
.mmu.flush_tlb_user = native_flush_tlb,
.mmu.flush_tlb_kernel = native_flush_tlb_global,
.mmu.flush_tlb_one_user = native_flush_tlb_one_user,
@@ -396,6 +391,14 @@ struct paravirt_patch_template pv_ops = {
.mmu.tlb_remove_table =
(void (*)(struct mmu_gather *, void *))tlb_remove_page,
+ .mmu.exit_mmap = paravirt_nop,
+
+#ifdef CONFIG_PARAVIRT_XXL
+ .mmu.read_cr2 = native_read_cr2,
+ .mmu.write_cr2 = native_write_cr2,
+ .mmu.read_cr3 = __native_read_cr3,
+ .mmu.write_cr3 = native_write_cr3,
+
.mmu.pgd_alloc = __paravirt_pgd_alloc,
.mmu.pgd_free = paravirt_nop,
@@ -448,7 +451,6 @@ struct paravirt_patch_template pv_ops = {
.mmu.make_pgd = PTE_IDENT,
.mmu.dup_mmap = paravirt_nop,
- .mmu.exit_mmap = paravirt_nop,
.mmu.activate_mm = paravirt_nop,
.mmu.lazy_mode = {
@@ -458,6 +460,7 @@ struct paravirt_patch_template pv_ops = {
},
.mmu.set_fixmap = native_set_fixmap,
+#endif
#if defined(CONFIG_PARAVIRT_SPINLOCKS)
/* Lock ops. */
diff --git a/arch/x86/kernel/paravirt_patch_32.c b/arch/x86/kernel/paravirt_patch_32.c
index 1d44705c6528..d460cbcabcfe 100644
--- a/arch/x86/kernel/paravirt_patch_32.c
+++ b/arch/x86/kernel/paravirt_patch_32.c
@@ -7,10 +7,10 @@ DEF_NATIVE(irq, irq_enable, "sti");
DEF_NATIVE(irq, restore_fl, "push %eax; popf");
DEF_NATIVE(irq, save_fl, "pushf; pop %eax");
DEF_NATIVE(cpu, iret, "iret");
-#endif
DEF_NATIVE(mmu, read_cr2, "mov %cr2, %eax");
DEF_NATIVE(mmu, write_cr3, "mov %eax, %cr3");
DEF_NATIVE(mmu, read_cr3, "mov %cr3, %eax");
+#endif
#if defined(CONFIG_PARAVIRT_SPINLOCKS)
DEF_NATIVE(lock, queued_spin_unlock, "movb $0, (%eax)");
@@ -49,10 +49,10 @@ unsigned native_patch(u8 type, void *ibuf, unsigned long addr, unsigned len)
PATCH_SITE(irq, restore_fl);
PATCH_SITE(irq, save_fl);
PATCH_SITE(cpu, iret);
-#endif
PATCH_SITE(mmu, read_cr2);
PATCH_SITE(mmu, read_cr3);
PATCH_SITE(mmu, write_cr3);
+#endif
#if defined(CONFIG_PARAVIRT_SPINLOCKS)
case PARAVIRT_PATCH(lock.queued_spin_unlock):
if (pv_is_native_spin_unlock()) {
diff --git a/arch/x86/kernel/paravirt_patch_64.c b/arch/x86/kernel/paravirt_patch_64.c
index b00937963a0f..5ad5bcda9dc6 100644
--- a/arch/x86/kernel/paravirt_patch_64.c
+++ b/arch/x86/kernel/paravirt_patch_64.c
@@ -8,11 +8,9 @@ DEF_NATIVE(irq, irq_disable, "cli");
DEF_NATIVE(irq, irq_enable, "sti");
DEF_NATIVE(irq, restore_fl, "pushq %rdi; popfq");
DEF_NATIVE(irq, save_fl, "pushfq; popq %rax");
-#endif
DEF_NATIVE(mmu, read_cr2, "movq %cr2, %rax");
DEF_NATIVE(mmu, read_cr3, "movq %cr3, %rax");
DEF_NATIVE(mmu, write_cr3, "movq %rdi, %cr3");
-#ifdef CONFIG_PARAVIRT_XXL
DEF_NATIVE(cpu, wbinvd, "wbinvd");
DEF_NATIVE(cpu, usergs_sysret64, "swapgs; sysretq");
@@ -61,10 +59,10 @@ unsigned native_patch(u8 type, void *ibuf, unsigned long addr, unsigned len)
PATCH_SITE(cpu, usergs_sysret64);
PATCH_SITE(cpu, swapgs);
PATCH_SITE(cpu, wbinvd);
-#endif
PATCH_SITE(mmu, read_cr2);
PATCH_SITE(mmu, read_cr3);
PATCH_SITE(mmu, write_cr3);
+#endif
#if defined(CONFIG_PARAVIRT_SPINLOCKS)
case PARAVIRT_PATCH(lock.queued_spin_unlock):
if (pv_is_native_spin_unlock()) {
--
2.16.4
^ permalink raw reply related
* [PATCH v3 15/15] x86/paravirt: remove unneeded mmu related paravirt ops bits
From: Juergen Gross @ 2018-08-28 7:40 UTC (permalink / raw)
To: linux-kernel, xen-devel, x86, virtualization
Cc: Juergen Gross, boris.ostrovsky, rusty, mingo, hpa, akataria, tglx
In-Reply-To: <20180828074026.820-1-jgross@suse.com>
There is no need to have 32-bit code for CONFIG_PGTABLE_LEVELS >= 4.
Remove it.
Signed-off-by: Juergen Gross <jgross@suse.com>
---
arch/x86/include/asm/paravirt.h | 20 +++-----------------
1 file changed, 3 insertions(+), 17 deletions(-)
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index 63ab58dc5b73..969343c72a9b 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -506,25 +506,14 @@ static inline pud_t __pud(pudval_t val)
{
pudval_t ret;
- if (sizeof(pudval_t) > sizeof(long))
- ret = PVOP_CALLEE2(pudval_t, mmu.make_pud, val, (u64)val >> 32);
- else
- ret = PVOP_CALLEE1(pudval_t, mmu.make_pud, val);
+ ret = PVOP_CALLEE1(pudval_t, mmu.make_pud, val);
return (pud_t) { ret };
}
static inline pudval_t pud_val(pud_t pud)
{
- pudval_t ret;
-
- if (sizeof(pudval_t) > sizeof(long))
- ret = PVOP_CALLEE2(pudval_t, mmu.pud_val,
- pud.pud, (u64)pud.pud >> 32);
- else
- ret = PVOP_CALLEE1(pudval_t, mmu.pud_val, pud.pud);
-
- return ret;
+ return PVOP_CALLEE1(pudval_t, mmu.pud_val, pud.pud);
}
static inline void pud_clear(pud_t *pudp)
@@ -536,10 +525,7 @@ static inline void set_p4d(p4d_t *p4dp, p4d_t p4d)
{
p4dval_t val = native_p4d_val(p4d);
- if (sizeof(p4dval_t) > sizeof(long))
- PVOP_VCALL3(mmu.set_p4d, p4dp, val, (u64)val >> 32);
- else
- PVOP_VCALL2(mmu.set_p4d, p4dp, val);
+ PVOP_VCALL2(mmu.set_p4d, p4dp, val);
}
#if CONFIG_PGTABLE_LEVELS >= 5
--
2.16.4
^ permalink raw reply related
* Re: KASAN: use-after-free Read in vhost_work_queue
From: Michael S. Tsirkin @ 2018-08-28 15:11 UTC (permalink / raw)
To: syzbot; +Cc: kvm, netdev, syzkaller-bugs, linux-kernel, virtualization,
stefanha
In-Reply-To: <000000000000863e0205747fdfef@google.com>
On Tue, Aug 28, 2018 at 07:44:03AM -0700, syzbot wrote:
> Hello,
>
> syzbot found the following crash on:
>
> HEAD commit: 33e17876ea4e Merge branch 'akpm' (patches from Andrew)
> git tree: upstream
> console output: https://syzkaller.appspot.com/x/log.txt?x=12d8a20a400000
> kernel config: https://syzkaller.appspot.com/x/.config?x=40e5d6b26b73cd5b
> dashboard link: https://syzkaller.appspot.com/bug?extid=d5a0a170c5069658b141
> compiler: gcc (GCC) 8.0.1 20180413 (experimental)
> userspace arch: i386
>
> Unfortunately, I don't have any reproducer for this crash yet.
>
> IMPORTANT: if you fix the bug, please add the following tag to the commit:
> Reported-by: syzbot+d5a0a170c5069658b141@syzkaller.appspotmail.com
>
> ==================================================================
> BUG: KASAN: use-after-free in vhost_work_queue+0xc3/0xe0
> drivers/vhost/vhost.c:258
> Read of size 8 at addr ffff880193862068 by task syz-executor7/22100
>
> CPU: 0 PID: 22100 Comm: syz-executor7 Not tainted 4.18.0+ #108
> Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS
> Google 01/01/2011
> Call Trace:
> __dump_stack lib/dump_stack.c:77 [inline]
> dump_stack+0x1c9/0x2b4 lib/dump_stack.c:113
> print_address_description+0x6c/0x20b mm/kasan/report.c:256
> kasan_report_error mm/kasan/report.c:354 [inline]
> kasan_report.cold.7+0x242/0x30d mm/kasan/report.c:412
> __asan_report_load8_noabort+0x14/0x20 mm/kasan/report.c:433
> vhost_work_queue+0xc3/0xe0 drivers/vhost/vhost.c:258
> vhost_transport_send_pkt+0x28a/0x380 drivers/vhost/vsock.c:227
> virtio_transport_send_pkt_info+0x31d/0x460
> net/vmw_vsock/virtio_transport_common.c:190
> virtio_transport_shutdown+0x1b1/0x270
> net/vmw_vsock/virtio_transport_common.c:604
> vsock_send_shutdown net/vmw_vsock/af_vsock.c:451 [inline]
> vsock_shutdown+0x229/0x290 net/vmw_vsock/af_vsock.c:849
> __sys_shutdown+0x15c/0x2c0 net/socket.c:1964
> __do_sys_shutdown net/socket.c:1972 [inline]
> __se_sys_shutdown net/socket.c:1970 [inline]
> __ia32_sys_shutdown+0x54/0x80 net/socket.c:1970
> do_syscall_32_irqs_on arch/x86/entry/common.c:326 [inline]
> do_fast_syscall_32+0x34d/0xfb2 arch/x86/entry/common.c:397
> entry_SYSENTER_compat+0x70/0x7f arch/x86/entry/entry_64_compat.S:139
> RIP: 0023:0xf7fa4ca9
> Code: 55 08 8b 88 64 cd ff ff 8b 98 68 cd ff ff 89 c8 85 d2 74 02 89 0a 5b
> 5d c3 8b 04 24 c3 8b 1c 24 c3 51 52 55 89 e5 0f 34 cd 80 <5d> 5a 59 c3 90 90
> 90 90 eb 0d 90 90 90 90 90 90 90 90 90 90 90 90
> RSP: 002b:00000000f5f7f0cc EFLAGS: 00000296 ORIG_RAX: 0000000000000175
> RAX: ffffffffffffffda RBX: 0000000000000009 RCX: 0000000000000000
> RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000000
> RBP: 0000000000000000 R08: 0000000000000000 R09: 0000000000000000
> R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000000
> R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000
>
> Allocated by task 22094:
> save_stack+0x43/0xd0 mm/kasan/kasan.c:448
> set_track mm/kasan/kasan.c:460 [inline]
> kasan_kmalloc+0xc4/0xe0 mm/kasan/kasan.c:553
> __do_kmalloc_node mm/slab.c:3682 [inline]
> __kmalloc_node+0x47/0x70 mm/slab.c:3689
> kmalloc_node include/linux/slab.h:555 [inline]
> kvmalloc_node+0xb9/0xf0 mm/util.c:423
> kvmalloc include/linux/mm.h:577 [inline]
> vhost_vsock_dev_open+0xa2/0x5a0 drivers/vhost/vsock.c:511
> misc_open+0x3ca/0x560 drivers/char/misc.c:141
> chrdev_open+0x25a/0x770 fs/char_dev.c:417
> do_dentry_open+0x49c/0x1140 fs/open.c:771
> vfs_open+0xa0/0xd0 fs/open.c:880
> do_last fs/namei.c:3418 [inline]
> path_openat+0x12fb/0x5300 fs/namei.c:3534
> do_filp_open+0x255/0x380 fs/namei.c:3564
> do_sys_open+0x584/0x720 fs/open.c:1063
> __do_compat_sys_openat fs/open.c:1109 [inline]
> __se_compat_sys_openat fs/open.c:1107 [inline]
> __ia32_compat_sys_openat+0x98/0xf0 fs/open.c:1107
> do_syscall_32_irqs_on arch/x86/entry/common.c:326 [inline]
> do_fast_syscall_32+0x34d/0xfb2 arch/x86/entry/common.c:397
> entry_SYSENTER_compat+0x70/0x7f arch/x86/entry/entry_64_compat.S:139
>
> Freed by task 22093:
> save_stack+0x43/0xd0 mm/kasan/kasan.c:448
> set_track mm/kasan/kasan.c:460 [inline]
> __kasan_slab_free+0x11a/0x170 mm/kasan/kasan.c:521
> kasan_slab_free+0xe/0x10 mm/kasan/kasan.c:528
> __cache_free mm/slab.c:3498 [inline]
> kfree+0xd9/0x210 mm/slab.c:3813
> kvfree+0x61/0x70 mm/util.c:449
> vhost_vsock_free drivers/vhost/vsock.c:499 [inline]
> vhost_vsock_dev_release+0x4fd/0x750 drivers/vhost/vsock.c:604
> __fput+0x36e/0x8c0 fs/file_table.c:278
> ____fput+0x15/0x20 fs/file_table.c:309
> task_work_run+0x1e8/0x2a0 kernel/task_work.c:113
> tracehook_notify_resume include/linux/tracehook.h:193 [inline]
> exit_to_usermode_loop+0x318/0x380 arch/x86/entry/common.c:166
> prepare_exit_to_usermode arch/x86/entry/common.c:197 [inline]
> syscall_return_slowpath arch/x86/entry/common.c:268 [inline]
> do_syscall_32_irqs_on arch/x86/entry/common.c:341 [inline]
> do_fast_syscall_32+0xcd5/0xfb2 arch/x86/entry/common.c:397
> entry_SYSENTER_compat+0x70/0x7f arch/x86/entry/entry_64_compat.S:139
>
> The buggy address belongs to the object at ffff880193861fc0
> which belongs to the cache kmalloc-65536 of size 65536
> The buggy address is located 168 bytes inside of
> 65536-byte region [ffff880193861fc0, ffff880193871fc0)
> The buggy address belongs to the page:
> page:ffffea00064e1800 count:1 mapcount:0 mapping:ffff8801dac02500 index:0x0
> compound_mapcount: 0
> flags: 0x2fffc0000008100(slab|head)
> raw: 02fffc0000008100 ffffea00064c7008 ffffea00064e5008 ffff8801dac02500
> raw: 0000000000000000 ffff880193861fc0 0000000100000001 0000000000000000
> page dumped because: kasan: bad access detected
>
> Memory state around the buggy address:
> ffff880193861f00: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
> ffff880193861f80: fc fc fc fc fc fc fc fc fb fb fb fb fb fb fb fb
> > ffff880193862000: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
> ^
> ffff880193862080: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
> ffff880193862100: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
> ==================================================================
Seems like a duplicate of the bug Stefan's working on now.
>
> ---
> This bug is generated by a bot. It may contain errors.
> See https://goo.gl/tpsmEJ for more information about syzbot.
> syzbot engineers can be reached at syzkaller@googlegroups.com.
>
> syzbot will keep track of this bug report. See:
> https://goo.gl/tpsmEJ#bug-status-tracking for how to communicate with
> syzbot.
^ permalink raw reply
* [PATCH v7] virtio_blk: add discard and write zeroes support
From: Daniel Verkamp @ 2018-08-28 22:25 UTC (permalink / raw)
To: virtualization
Cc: Jens Axboe, Michael S. Tsirkin, Stefan Hajnoczi, Changpeng Liu
In-Reply-To: <1528258740-6581-1-git-send-email-changpeng.liu@intel.com>
From: Changpeng Liu <changpeng.liu@intel.com>
In commit 88c85538, "virtio-blk: add discard and write zeroes features
to specification" (https://github.com/oasis-tcs/virtio-spec), the virtio
block specification has been extended to add VIRTIO_BLK_T_DISCARD and
VIRTIO_BLK_T_WRITE_ZEROES commands. This patch enables support for
discard and write zeroes in the virtio-blk driver when the device
advertises the corresponding features, VIRTIO_BLK_F_DISCARD and
VIRTIO_BLK_F_WRITE_ZEROES.
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Signed-off-by: Daniel Verkamp <dverkamp@chromium.org>
---
dverkamp: I've picked up this patch and made a few minor changes (as
listed below); most notably, I changed the kmalloc back to GFP_ATOMIC,
since it can be called from a context where sleeping is not allowed.
To prevent large allocations, I've also clamped the maximum number of
discard segments to 256; this results in a 4K allocation and should be
plenty of descriptors for most use cases.
I also removed most of the description from the commit message, since it
was duplicating the comments from virtio_blk.h and quoting parts of the
spec without adding any extra information. I have tested this iteration
of the patch using crosvm with modifications to enable the new features:
https://chromium.googlesource.com/chromiumos/platform/crosvm/
CHANGELOG:
v7: [dverkamp] use GFP_ATOMIC for allocation that may not sleep; clarify
descriptor flags field; comment wording cleanups.
v6: don't set T_OUT bit to discard and write zeroes commands.
v5: use new block layer API: blk_queue_flag_set.
v4: several optimizations based on MST's comments, remove bit field
usage for command descriptor.
v3: define the virtio-blk protocol to add discard and write zeroes
support, first version implementation based on proposed specification.
v2: add write zeroes command support.
v1: initial proposal implementation for discard command.
---
drivers/block/virtio_blk.c | 95 ++++++++++++++++++++++++++++++++-
include/uapi/linux/virtio_blk.h | 54 +++++++++++++++++++
2 files changed, 147 insertions(+), 2 deletions(-)
diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index 23752dc99b00..c033e718a36a 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -18,6 +18,7 @@
#define PART_BITS 4
#define VQ_NAME_LEN 16
+#define DISCARD_MAX_SEGMENTS 256
static int major;
static DEFINE_IDA(vd_index_ida);
@@ -172,10 +173,50 @@ static int virtblk_add_req(struct virtqueue *vq, struct virtblk_req *vbr,
return virtqueue_add_sgs(vq, sgs, num_out, num_in, vbr, GFP_ATOMIC);
}
+
+static inline int virtblk_setup_discard_write_zeroes(struct request *req,
+ bool unmap)
+{
+ unsigned short segments = blk_rq_nr_discard_segments(req);
+ unsigned short n = 0;
+ struct virtio_blk_discard_write_zeroes *range;
+ struct bio *bio;
+ u32 flags = 0;
+
+ if (unmap)
+ flags |= VIRTIO_BLK_WRITE_ZEROES_FLAG_UNMAP;
+
+ range = kmalloc_array(segments, sizeof(*range), GFP_ATOMIC);
+ if (!range)
+ return -ENOMEM;
+
+ __rq_for_each_bio(bio, req) {
+ u64 sector = bio->bi_iter.bi_sector;
+ u32 num_sectors = bio->bi_iter.bi_size >> 9;
+
+ range[n].flags = cpu_to_le32(flags);
+ range[n].num_sectors = cpu_to_le32(num_sectors);
+ range[n].sector = cpu_to_le64(sector);
+ n++;
+ }
+
+ req->special_vec.bv_page = virt_to_page(range);
+ req->special_vec.bv_offset = offset_in_page(range);
+ req->special_vec.bv_len = sizeof(*range) * segments;
+ req->rq_flags |= RQF_SPECIAL_PAYLOAD;
+
+ return 0;
+}
+
static inline void virtblk_request_done(struct request *req)
{
struct virtblk_req *vbr = blk_mq_rq_to_pdu(req);
+ if (req->rq_flags & RQF_SPECIAL_PAYLOAD) {
+ kfree(page_address(req->special_vec.bv_page) +
+ req->special_vec.bv_offset);
+ }
+
switch (req_op(req)) {
case REQ_OP_SCSI_IN:
case REQ_OP_SCSI_OUT:
@@ -225,6 +266,7 @@ static blk_status_t virtio_queue_rq(struct blk_mq_hw_ctx *hctx,
int qid = hctx->queue_num;
int err;
bool notify = false;
+ bool unmap = false;
u32 type;
BUG_ON(req->nr_phys_segments + 2 > vblk->sg_elems);
@@ -237,6 +279,13 @@ static blk_status_t virtio_queue_rq(struct blk_mq_hw_ctx *hctx,
case REQ_OP_FLUSH:
type = VIRTIO_BLK_T_FLUSH;
break;
+ case REQ_OP_DISCARD:
+ type = VIRTIO_BLK_T_DISCARD;
+ break;
+ case REQ_OP_WRITE_ZEROES:
+ type = VIRTIO_BLK_T_WRITE_ZEROES;
+ unmap = !(req->cmd_flags & REQ_NOUNMAP);
+ break;
case REQ_OP_SCSI_IN:
case REQ_OP_SCSI_OUT:
type = VIRTIO_BLK_T_SCSI_CMD;
@@ -256,6 +305,12 @@ static blk_status_t virtio_queue_rq(struct blk_mq_hw_ctx *hctx,
blk_mq_start_request(req);
+ if (type == VIRTIO_BLK_T_DISCARD || type == VIRTIO_BLK_T_WRITE_ZEROES) {
+ err = virtblk_setup_discard_write_zeroes(req, unmap);
+ if (err)
+ return BLK_STS_RESOURCE;
+ }
+
num = blk_rq_map_sg(hctx->queue, req, vbr->sg);
if (num) {
if (rq_data_dir(req) == WRITE)
@@ -777,6 +832,42 @@ static int virtblk_probe(struct virtio_device *vdev)
if (!err && opt_io_size)
blk_queue_io_opt(q, blk_size * opt_io_size);
+ if (virtio_has_feature(vdev, VIRTIO_BLK_F_DISCARD)) {
+ q->limits.discard_granularity = blk_size;
+
+ virtio_cread(vdev, struct virtio_blk_config,
+ discard_sector_alignment, &v);
+ if (v)
+ q->limits.discard_alignment = v << 9;
+ else
+ q->limits.discard_alignment = 0;
+
+ virtio_cread(vdev, struct virtio_blk_config,
+ max_discard_sectors, &v);
+ if (v)
+ blk_queue_max_discard_sectors(q, v);
+ else
+ blk_queue_max_discard_sectors(q, UINT_MAX);
+
+ virtio_cread(vdev, struct virtio_blk_config, max_discard_seg,
+ &v);
+ if (v && v <= DISCARD_MAX_SEGMENTS)
+ blk_queue_max_discard_segments(q, v);
+ else
+ blk_queue_max_discard_segments(q, DISCARD_MAX_SEGMENTS);
+
+ blk_queue_flag_set(QUEUE_FLAG_DISCARD, q);
+ }
+
+ if (virtio_has_feature(vdev, VIRTIO_BLK_F_WRITE_ZEROES)) {
+ virtio_cread(vdev, struct virtio_blk_config,
+ max_write_zeroes_sectors, &v);
+ if (v)
+ blk_queue_max_write_zeroes_sectors(q, v);
+ else
+ blk_queue_max_write_zeroes_sectors(q, UINT_MAX);
+ }
+
virtblk_update_capacity(vblk, false);
virtio_device_ready(vdev);
@@ -885,14 +976,14 @@ static unsigned int features_legacy[] = {
VIRTIO_BLK_F_SCSI,
#endif
VIRTIO_BLK_F_FLUSH, VIRTIO_BLK_F_TOPOLOGY, VIRTIO_BLK_F_CONFIG_WCE,
- VIRTIO_BLK_F_MQ,
+ VIRTIO_BLK_F_MQ, VIRTIO_BLK_F_DISCARD, VIRTIO_BLK_F_WRITE_ZEROES,
}
;
static unsigned int features[] = {
VIRTIO_BLK_F_SEG_MAX, VIRTIO_BLK_F_SIZE_MAX, VIRTIO_BLK_F_GEOMETRY,
VIRTIO_BLK_F_RO, VIRTIO_BLK_F_BLK_SIZE,
VIRTIO_BLK_F_FLUSH, VIRTIO_BLK_F_TOPOLOGY, VIRTIO_BLK_F_CONFIG_WCE,
- VIRTIO_BLK_F_MQ,
+ VIRTIO_BLK_F_MQ, VIRTIO_BLK_F_DISCARD, VIRTIO_BLK_F_WRITE_ZEROES,
};
static struct virtio_driver virtio_blk = {
diff --git a/include/uapi/linux/virtio_blk.h b/include/uapi/linux/virtio_blk.h
index 9ebe4d968dd5..682afbfe3aa4 100644
--- a/include/uapi/linux/virtio_blk.h
+++ b/include/uapi/linux/virtio_blk.h
@@ -38,6 +38,8 @@
#define VIRTIO_BLK_F_BLK_SIZE 6 /* Block size of disk is available*/
#define VIRTIO_BLK_F_TOPOLOGY 10 /* Topology information is available */
#define VIRTIO_BLK_F_MQ 12 /* support more than one vq */
+#define VIRTIO_BLK_F_DISCARD 13 /* DISCARD is supported */
+#define VIRTIO_BLK_F_WRITE_ZEROES 14 /* WRITE ZEROES is supported */
/* Legacy feature bits */
#ifndef VIRTIO_BLK_NO_LEGACY
@@ -86,6 +88,39 @@ struct virtio_blk_config {
/* number of vqs, only available when VIRTIO_BLK_F_MQ is set */
__u16 num_queues;
+
+ /* the next 3 entries are guarded by VIRTIO_BLK_F_DISCARD */
+ /*
+ * The maximum discard sectors (in 512-byte sectors) for
+ * one segment.
+ */
+ __u32 max_discard_sectors;
+ /*
+ * The maximum number of discard segments in a
+ * discard command.
+ */
+ __u32 max_discard_seg;
+ /* Discard commands must be aligned to this number of sectors. */
+ __u32 discard_sector_alignment;
+
+ /* the next 3 entries are guarded by VIRTIO_BLK_F_WRITE_ZEROES */
+ /*
+ * The maximum number of write zeroes sectors (in 512-byte sectors) in
+ * one segment.
+ */
+ __u32 max_write_zeroes_sectors;
+ /*
+ * The maximum number of segments in a write zeroes
+ * command.
+ */
+ __u32 max_write_zeroes_seg;
+ /*
+ * Set if a VIRTIO_BLK_T_WRITE_ZEROES request may result in the
+ * deallocation of one or more of the sectors.
+ */
+ __u8 write_zeroes_may_unmap;
+
+ __u8 unused1[3];
} __attribute__((packed));
/*
@@ -114,6 +149,12 @@ struct virtio_blk_config {
/* Get device ID command */
#define VIRTIO_BLK_T_GET_ID 8
+/* Discard command */
+#define VIRTIO_BLK_T_DISCARD 11
+
+/* Write zeroes command */
+#define VIRTIO_BLK_T_WRITE_ZEROES 13
+
#ifndef VIRTIO_BLK_NO_LEGACY
/* Barrier before this op. */
#define VIRTIO_BLK_T_BARRIER 0x80000000
@@ -133,6 +174,19 @@ struct virtio_blk_outhdr {
__virtio64 sector;
};
+/* Unmap this range (only valid for write zeroes command) */
+#define VIRTIO_BLK_WRITE_ZEROES_FLAG_UNMAP 0x00000001
+
+/* Discard/write zeroes range for each request. */
+struct virtio_blk_discard_write_zeroes {
+ /* discard/write zeroes start sector */
+ __virtio64 sector;
+ /* number of discard/write zeroes sectors */
+ __virtio32 num_sectors;
+ /* flags for this range */
+ __virtio32 flags;
+};
+
#ifndef VIRTIO_BLK_NO_LEGACY
struct virtio_scsi_inhdr {
__virtio32 errors;
--
2.19.0.rc0.228.g281dcd1b4d0-goog
^ permalink raw reply related
* [PATCH 1/2] drm/virtio: add virtio_gpu_object_detach() function
From: Gerd Hoffmann @ 2018-08-29 12:20 UTC (permalink / raw)
To: dri-devel, virtio-dev
Cc: David Airlie, open list, open list:VIRTIO GPU DRIVER
In-Reply-To: <20180829122026.27012-1-kraxel@redhat.com>
The new function balances virtio_gpu_object_attach().
Also make virtio_gpu_cmd_resource_inval_backing() static and switch
call sites to the new virtio_gpu_object_attach() function.
Signed-off-by: Gerd Hoffmann <kraxel@redhat.com>
---
drivers/gpu/drm/virtio/virtgpu_drv.h | 4 ++--
drivers/gpu/drm/virtio/virtgpu_fb.c | 2 +-
drivers/gpu/drm/virtio/virtgpu_ttm.c | 3 +--
drivers/gpu/drm/virtio/virtgpu_vq.c | 10 ++++++++--
4 files changed, 12 insertions(+), 7 deletions(-)
diff --git a/drivers/gpu/drm/virtio/virtgpu_drv.h b/drivers/gpu/drm/virtio/virtgpu_drv.h
index 65605e207b..cbbff01077 100644
--- a/drivers/gpu/drm/virtio/virtgpu_drv.h
+++ b/drivers/gpu/drm/virtio/virtgpu_drv.h
@@ -276,13 +276,13 @@ int virtio_gpu_object_attach(struct virtio_gpu_device *vgdev,
struct virtio_gpu_object *obj,
uint32_t resource_id,
struct virtio_gpu_fence **fence);
+void virtio_gpu_object_detach(struct virtio_gpu_device *vgdev,
+ struct virtio_gpu_object *obj);
int virtio_gpu_attach_status_page(struct virtio_gpu_device *vgdev);
int virtio_gpu_detach_status_page(struct virtio_gpu_device *vgdev);
void virtio_gpu_cursor_ping(struct virtio_gpu_device *vgdev,
struct virtio_gpu_output *output);
int virtio_gpu_cmd_get_display_info(struct virtio_gpu_device *vgdev);
-void virtio_gpu_cmd_resource_inval_backing(struct virtio_gpu_device *vgdev,
- uint32_t resource_id);
int virtio_gpu_cmd_get_capset_info(struct virtio_gpu_device *vgdev, int idx);
int virtio_gpu_cmd_get_capset(struct virtio_gpu_device *vgdev,
int idx, int version,
diff --git a/drivers/gpu/drm/virtio/virtgpu_fb.c b/drivers/gpu/drm/virtio/virtgpu_fb.c
index a121b1c795..b5cebc9a17 100644
--- a/drivers/gpu/drm/virtio/virtgpu_fb.c
+++ b/drivers/gpu/drm/virtio/virtgpu_fb.c
@@ -291,7 +291,7 @@ static int virtio_gpufb_create(struct drm_fb_helper *helper,
return 0;
err_fb_alloc:
- virtio_gpu_cmd_resource_inval_backing(vgdev, resid);
+ virtio_gpu_object_detach(vgdev, obj);
err_obj_attach:
err_obj_vmap:
virtio_gpu_gem_free_object(&obj->gem_base);
diff --git a/drivers/gpu/drm/virtio/virtgpu_ttm.c b/drivers/gpu/drm/virtio/virtgpu_ttm.c
index 11f8ae5b53..3ea115e026 100644
--- a/drivers/gpu/drm/virtio/virtgpu_ttm.c
+++ b/drivers/gpu/drm/virtio/virtgpu_ttm.c
@@ -377,8 +377,7 @@ static void virtio_gpu_bo_move_notify(struct ttm_buffer_object *tbo,
if (!new_mem || (new_mem->placement & TTM_PL_FLAG_SYSTEM)) {
if (bo->hw_res_handle)
- virtio_gpu_cmd_resource_inval_backing(vgdev,
- bo->hw_res_handle);
+ virtio_gpu_object_detach(vgdev, bo);
} else if (new_mem->placement & TTM_PL_FLAG_TT) {
if (bo->hw_res_handle) {
diff --git a/drivers/gpu/drm/virtio/virtgpu_vq.c b/drivers/gpu/drm/virtio/virtgpu_vq.c
index 020070d483..af24e91267 100644
--- a/drivers/gpu/drm/virtio/virtgpu_vq.c
+++ b/drivers/gpu/drm/virtio/virtgpu_vq.c
@@ -423,8 +423,8 @@ void virtio_gpu_cmd_unref_resource(struct virtio_gpu_device *vgdev,
virtio_gpu_queue_ctrl_buffer(vgdev, vbuf);
}
-void virtio_gpu_cmd_resource_inval_backing(struct virtio_gpu_device *vgdev,
- uint32_t resource_id)
+static void virtio_gpu_cmd_resource_inval_backing(struct virtio_gpu_device *vgdev,
+ uint32_t resource_id)
{
struct virtio_gpu_resource_detach_backing *cmd_p;
struct virtio_gpu_vbuffer *vbuf;
@@ -882,6 +882,12 @@ int virtio_gpu_object_attach(struct virtio_gpu_device *vgdev,
return 0;
}
+void virtio_gpu_object_detach(struct virtio_gpu_device *vgdev,
+ struct virtio_gpu_object *obj)
+{
+ virtio_gpu_cmd_resource_inval_backing(vgdev, obj->hw_res_handle);
+}
+
void virtio_gpu_cursor_ping(struct virtio_gpu_device *vgdev,
struct virtio_gpu_output *output)
{
--
2.9.3
^ permalink raw reply related
* [PATCH 2/2] drm/virtio: add iommu support.
From: Gerd Hoffmann @ 2018-08-29 12:20 UTC (permalink / raw)
To: dri-devel, virtio-dev
Cc: David Airlie, open list, open list:VIRTIO GPU DRIVER
In-Reply-To: <20180829122026.27012-1-kraxel@redhat.com>
Use the dma mapping api and properly add iommu mappings for
objects, unless virtio is in iommu quirk mode.
Signed-off-by: Gerd Hoffmann <kraxel@redhat.com>
---
drivers/gpu/drm/virtio/virtgpu_drv.h | 1 +
drivers/gpu/drm/virtio/virtgpu_vq.c | 46 +++++++++++++++++++++++++++++-------
2 files changed, 38 insertions(+), 9 deletions(-)
diff --git a/drivers/gpu/drm/virtio/virtgpu_drv.h b/drivers/gpu/drm/virtio/virtgpu_drv.h
index cbbff01077..ec9a38f995 100644
--- a/drivers/gpu/drm/virtio/virtgpu_drv.h
+++ b/drivers/gpu/drm/virtio/virtgpu_drv.h
@@ -57,6 +57,7 @@ struct virtio_gpu_object {
uint32_t hw_res_handle;
struct sg_table *pages;
+ uint32_t mapped;
void *vmap;
bool dumb;
struct ttm_place placement_code;
diff --git a/drivers/gpu/drm/virtio/virtgpu_vq.c b/drivers/gpu/drm/virtio/virtgpu_vq.c
index af24e91267..bf631d32d4 100644
--- a/drivers/gpu/drm/virtio/virtgpu_vq.c
+++ b/drivers/gpu/drm/virtio/virtgpu_vq.c
@@ -424,7 +424,8 @@ void virtio_gpu_cmd_unref_resource(struct virtio_gpu_device *vgdev,
}
static void virtio_gpu_cmd_resource_inval_backing(struct virtio_gpu_device *vgdev,
- uint32_t resource_id)
+ uint32_t resource_id,
+ struct virtio_gpu_fence **fence)
{
struct virtio_gpu_resource_detach_backing *cmd_p;
struct virtio_gpu_vbuffer *vbuf;
@@ -435,7 +436,7 @@ static void virtio_gpu_cmd_resource_inval_backing(struct virtio_gpu_device *vgde
cmd_p->hdr.type = cpu_to_le32(VIRTIO_GPU_CMD_RESOURCE_DETACH_BACKING);
cmd_p->resource_id = cpu_to_le32(resource_id);
- virtio_gpu_queue_ctrl_buffer(vgdev, vbuf);
+ virtio_gpu_queue_fenced_ctrl_buffer(vgdev, vbuf, &cmd_p->hdr, fence);
}
void virtio_gpu_cmd_set_scanout(struct virtio_gpu_device *vgdev,
@@ -848,9 +849,10 @@ int virtio_gpu_object_attach(struct virtio_gpu_device *vgdev,
uint32_t resource_id,
struct virtio_gpu_fence **fence)
{
+ bool use_dma_api = !virtio_has_iommu_quirk(vgdev->vdev);
struct virtio_gpu_mem_entry *ents;
struct scatterlist *sg;
- int si;
+ int si, nents;
if (!obj->pages) {
int ret;
@@ -860,23 +862,33 @@ int virtio_gpu_object_attach(struct virtio_gpu_device *vgdev,
return ret;
}
+ if (use_dma_api) {
+ obj->mapped = dma_map_sg(vgdev->vdev->dev.parent,
+ obj->pages->sgl, obj->pages->nents,
+ DMA_TO_DEVICE);
+ nents = obj->mapped;
+ } else {
+ nents = obj->pages->nents;
+ }
+
/* gets freed when the ring has consumed it */
- ents = kmalloc_array(obj->pages->nents,
- sizeof(struct virtio_gpu_mem_entry),
+ ents = kmalloc_array(nents, sizeof(struct virtio_gpu_mem_entry),
GFP_KERNEL);
if (!ents) {
DRM_ERROR("failed to allocate ent list\n");
return -ENOMEM;
}
- for_each_sg(obj->pages->sgl, sg, obj->pages->nents, si) {
- ents[si].addr = cpu_to_le64(sg_phys(sg));
+ for_each_sg(obj->pages->sgl, sg, nents, si) {
+ ents[si].addr = cpu_to_le64(use_dma_api
+ ? sg_dma_address(sg)
+ : sg_phys(sg));
ents[si].length = cpu_to_le32(sg->length);
ents[si].padding = 0;
}
virtio_gpu_cmd_resource_attach_backing(vgdev, resource_id,
- ents, obj->pages->nents,
+ ents, nents,
fence);
obj->hw_res_handle = resource_id;
return 0;
@@ -885,7 +897,23 @@ int virtio_gpu_object_attach(struct virtio_gpu_device *vgdev,
void virtio_gpu_object_detach(struct virtio_gpu_device *vgdev,
struct virtio_gpu_object *obj)
{
- virtio_gpu_cmd_resource_inval_backing(vgdev, obj->hw_res_handle);
+ bool use_dma_api = !virtio_has_iommu_quirk(vgdev->vdev);
+ struct virtio_gpu_fence *fence;
+
+ if (use_dma_api && obj->mapped) {
+ /* detach backing and wait for the host process it ... */
+ virtio_gpu_cmd_resource_inval_backing(vgdev, obj->hw_res_handle, &fence);
+ dma_fence_wait(&fence->f, true);
+ dma_fence_put(&fence->f);
+
+ /* ... then tear down iommu mappings */
+ dma_unmap_sg(vgdev->vdev->dev.parent,
+ obj->pages->sgl, obj->mapped,
+ DMA_TO_DEVICE);
+ obj->mapped = 0;
+ } else {
+ virtio_gpu_cmd_resource_inval_backing(vgdev, obj->hw_res_handle, NULL);
+ }
}
void virtio_gpu_cursor_ping(struct virtio_gpu_device *vgdev,
--
2.9.3
^ permalink raw reply related
* Re: [PATCH 0/2] Provide init/release functions for struct ttm_bo_global
From: Christian König @ 2018-08-30 6:45 UTC (permalink / raw)
To: Thomas Zimmermann, ray.huang, Jerry.Zhang, dri-devel
Cc: David1.Zhou, thellstrom, nouveau, syeh, airlied, puck.chen,
amd-gfx, virtualization, z.liuxinliang, zourongrong,
kong.kongxinwei, linux-graphics-maintainer, gregkh,
alexander.deucher, bskeggs
In-Reply-To: <5e815e50-d0be-5069-cf1d-aa881a18f094@suse.de>
Hi Thomas,
Am 30.08.2018 um 08:34 schrieb Thomas Zimmermann:
> Hi Christian,
>
> I just wanted to ask if there's something else required to get this
> patch set reviewed and landed.
I just need to find some time to review them.
> On top of these two patches, I have a patch set that replaces the
> driver-specific global-bo-and-mem combos with a single struct ttm_global
> structure. It further merges struct drm_global into struct ttm_global
> and implements it such that drivers can either share the global memory
That sounds good.
> or create their private instance.
That doesn't sounds good. Drivers should not be allowed to create their
own private instance of that.
Thanks for doing this,
Christian.
> It's also a step towards drm device
> hotplug, which someone just asked.
>
> Best regards
> Thomas
>
>
> Am 13.08.2018 um 12:33 schrieb Christian König:
>> Yes, please! I had it on my TODO list to clean that up for an eternity.
>>
>> Actually I never understood why that should be driver work to setup TTM?
>>
>> I mean can't we just have a module_init/module_exit for TTM?
>>
>> Thanks,
>> Christian.
>>
>> Am 13.08.2018 um 12:24 schrieb Thomas Zimmermann:
>>> TTM uses global memory and BO for backing graphics buffers. These are
>>> represented by struct ttm_mem_global and struct ttm_bo_global.
>>>
>>> Currently, struct ttm_bo_global can only be initialized and released
>>> through
>>> struct ttm_bo_global_ref. This is a workaround for passing an instance of
>>> ttm_mem_global to the BO global initialization code.
>>>
>>> The use of struct ttm_bo_global_ref makes driver code unnecessary hard to
>>> understand. At the same time drivers can use any combination of memory
>>> and
>>> BO for initializing the global instances. This can result in subtle bugs
>>> when the order of initializing and releasing drivers changes.
>>>
>>> As a first step for resolving these problems, the provided patch set
>>> separates initialization and release of struct ttm_bo_global from
>>> struct ttm_bo_global_ref.
>>>
>>> The first patch only renames ttm_bo_global_{init/release}. Hopefully this
>>> change can be applied at once for all drivers.
>>>
>>> Future directions: All TTM-based drivers follow the same pattern for
>>> setting
>>> up the TTM. In a follow-up patch, this code can be moved into a single
>>> place
>>> and shared among drivers.
>>>
>>> Thomas Zimmermann (2):
>>> drm/ttm: Rename ttm_bo_global_{init,release}() to
>>> ttm_bo_global_ref_*()
>>> drm/ttm: Provide ttm_bo_global_{init/release}() for struct
>>> ttm_bo_global
>>>
>>> drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 4 +-
>>> drivers/gpu/drm/ast/ast_ttm.c | 4 +-
>>> drivers/gpu/drm/bochs/bochs_mm.c | 4 +-
>>> drivers/gpu/drm/cirrus/cirrus_ttm.c | 4 +-
>>> drivers/gpu/drm/hisilicon/hibmc/hibmc_ttm.c | 4 +-
>>> drivers/gpu/drm/mgag200/mgag200_ttm.c | 4 +-
>>> drivers/gpu/drm/nouveau/nouveau_ttm.c | 4 +-
>>> drivers/gpu/drm/qxl/qxl_ttm.c | 4 +-
>>> drivers/gpu/drm/radeon/radeon_ttm.c | 4 +-
>>> drivers/gpu/drm/ttm/ttm_bo.c | 12 ++---
>>> drivers/gpu/drm/virtio/virtgpu_ttm.c | 4 +-
>>> drivers/gpu/drm/vmwgfx/vmwgfx_ttm_glue.c | 4 +-
>>> drivers/staging/vboxvideo/vbox_ttm.c | 4 +-
>>> include/drm/ttm/ttm_bo_driver.h | 53 ++++++++++++++++-----
>>> 14 files changed, 70 insertions(+), 43 deletions(-)
>>>
>>> --
>>> 2.18.0
>>>
_______________________________________________
Virtualization mailing list
Virtualization@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/virtualization
^ permalink raw reply
* Re: [PATCH] drm/bochs: Replace ttm_bo_unref with ttm_bo_put
From: Gerd Hoffmann @ 2018-08-30 7:18 UTC (permalink / raw)
To: Thomas Zimmermann; +Cc: dri-devel, virtualization
In-Reply-To: <a469ab44-f2b4-32b7-f162-d40e3db1dc80@suse.de>
On Thu, Aug 30, 2018 at 08:14:02AM +0200, Thomas Zimmermann wrote:
> Hi Gerd
>
> Am 09.08.2018 um 17:27 schrieb Gerd Hoffmann:
> >> diff --git a/drivers/gpu/drm/bochs/bochs_mm.c b/drivers/gpu/drm/bochs/bochs_mm.c
> >> index 39cd08416773..c9c7097030ca 100644
> >> --- a/drivers/gpu/drm/bochs/bochs_mm.c
> >> +++ b/drivers/gpu/drm/bochs/bochs_mm.c
> >> @@ -430,7 +430,7 @@ static void bochs_bo_unref(struct bochs_bo **bo)
> >> return;
> >>
> >> tbo = &((*bo)->bo);
> >> - ttm_bo_unref(&tbo);
> >> + ttm_bo_put(tbo);
> >
> > fails to build:
> >
> > CC [M] drivers/gpu/drm/bochs/bochs_mm.o
> > /home/kraxel/projects/linux/drivers/gpu/drm/bochs/bochs_mm.c: In function ‘bochs_bo_unref’:
> > /home/kraxel/projects/linux/drivers/gpu/drm/bochs/bochs_mm.c:433:2: error: implicit declaration of function ‘ttm_bo_put’ [-Werror=implicit-function-declaration]
> > ttm_bo_put(tbo);
> > ^
> > cc1: some warnings being treated as errors
>
> The required interfaces are now available in mainline. [1] I rebuilt to
> make sure it compiles.
>
> Besides bochs, [2] the patches for qxl, [3] cirrus, [4] vmwgfx, [5][6]
> and virtio [7][8] should now build as well. They still apply cleanly
> AFAICT. Let me know if you prefer a new patch set instead.
Yes. builds now. vmwgfx is not my cup of tea, but I'll pick up the
other ones (and can finally remove them from my patches mailbox) and let
you know in case I run into trouble.
cheers,
Gerd
_______________________________________________
Virtualization mailing list
Virtualization@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/virtualization
^ permalink raw reply
* [PATCH v2 00/12] remove_conflicting_framebuffers() cleanup
From: Michał Mirosław @ 2018-08-30 21:00 UTC (permalink / raw)
To: dri-devel
Cc: linux-fbdev, linux-tegra, Bartlomiej Zolnierkiewicz, David Airlie,
amd-gfx, virtualization, Eric Anholt, Thierry Reding,
Alex Deucher, Maxime Ripard, linux-arm-kernel
In-Reply-To: <cover.1511544782.git.mirq-linux@rere.qmqm.pl>
This series cleans up duplicated code for replacing firmware FB
driver with proper DRI driver and adds handover support to
Tegra driver.
This is a sligtly updated version of a series sent on 24 Nov 2017.
v2:
- rebased on current drm-next
- dropped staging/sm750fb changes
- added kernel docs for DRM helpers
Michał Mirosław (12):
fbdev: show fbdev number for debugging
fbdev: allow apertures == NULL in remove_conflicting_framebuffers()
fbdev: add remove_conflicting_pci_framebuffers()
drm/amdgpu: use simpler remove_conflicting_pci_framebuffers()
drm/bochs: use simpler remove_conflicting_pci_framebuffers()
drm/cirrus: use simpler remove_conflicting_pci_framebuffers()
drm/mgag200: use simpler remove_conflicting_pci_framebuffers()
drm/radeon: use simpler remove_conflicting_pci_framebuffers()
drm/virtio: use simpler remove_conflicting_pci_framebuffers()
drm/vc4: use simpler remove_conflicting_framebuffers(NULL)
drm/sun4i: use simpler remove_conflicting_framebuffers(NULL)
drm/tegra: kick out simplefb
drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c | 24 +-------------
drivers/gpu/drm/bochs/bochs_drv.c | 18 +----------
drivers/gpu/drm/cirrus/cirrus_drv.c | 23 +-------------
drivers/gpu/drm/mgag200/mgag200_drv.c | 21 +------------
drivers/gpu/drm/mgag200/mgag200_main.c | 9 ------
drivers/gpu/drm/radeon/radeon_drv.c | 23 +-------------
drivers/gpu/drm/sun4i/sun4i_drv.c | 18 +----------
drivers/gpu/drm/tegra/drm.c | 4 +++
drivers/gpu/drm/vc4/vc4_drv.c | 20 +-----------
drivers/gpu/drm/virtio/virtgpu_drm_bus.c | 24 ++------------
drivers/video/fbdev/core/fbmem.c | 40 ++++++++++++++++++++++--
include/drm/drm_fb_helper.h | 34 ++++++++++++++++++++
include/linux/fb.h | 2 ++
13 files changed, 88 insertions(+), 172 deletions(-)
--
2.18.0
_______________________________________________
Virtualization mailing list
Virtualization@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/virtualization
^ permalink raw reply
* [PATCH v2 01/12] fbdev: show fbdev number for debugging
From: Michał Mirosław @ 2018-08-30 21:00 UTC (permalink / raw)
To: dri-devel
Cc: linux-fbdev, linux-tegra, Bartlomiej Zolnierkiewicz, David Airlie,
amd-gfx, virtualization, Eric Anholt, Thierry Reding,
Alex Deucher, Maxime Ripard, linux-arm-kernel
In-Reply-To: <cover.1535656077.git.mirq-linux@rere.qmqm.pl>
Signed-off-by: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Acked-by: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com>
Acked-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
drivers/video/fbdev/core/fbmem.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/video/fbdev/core/fbmem.c b/drivers/video/fbdev/core/fbmem.c
index f741ba8df01b..30a18d4c9de4 100644
--- a/drivers/video/fbdev/core/fbmem.c
+++ b/drivers/video/fbdev/core/fbmem.c
@@ -1618,8 +1618,8 @@ static int do_remove_conflicting_framebuffers(struct apertures_struct *a,
(primary && gen_aper && gen_aper->count &&
gen_aper->ranges[0].base == VGA_FB_PHYS)) {
- printk(KERN_INFO "fb: switching to %s from %s\n",
- name, registered_fb[i]->fix.id);
+ printk(KERN_INFO "fb%d: switching to %s from %s\n",
+ i, name, registered_fb[i]->fix.id);
ret = do_unregister_framebuffer(registered_fb[i]);
if (ret)
return ret;
--
2.18.0
_______________________________________________
Virtualization mailing list
Virtualization@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/virtualization
^ permalink raw reply related
* [PATCH v2 02/12] fbdev: allow apertures == NULL in remove_conflicting_framebuffers()
From: Michał Mirosław @ 2018-08-30 21:00 UTC (permalink / raw)
To: dri-devel
Cc: linux-fbdev, linux-tegra, Bartlomiej Zolnierkiewicz, David Airlie,
amd-gfx, virtualization, Eric Anholt, Thierry Reding,
Alex Deucher, Maxime Ripard, linux-arm-kernel
In-Reply-To: <cover.1535656077.git.mirq-linux@rere.qmqm.pl>
Interpret (otherwise-invalid) NULL apertures argument to mean all-memory
range. This will allow to remove several duplicates of this code from
drivers in following patches.
Signed-off-by: Michał Mirosław <mirq-linux@rere.qmqm.pl>
[for v1]
Acked-by: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com>
---
v2: added kerneldoc to corresponding DRM helper
---
drivers/video/fbdev/core/fbmem.c | 14 ++++++++++++++
include/drm/drm_fb_helper.h | 10 ++++++++++
2 files changed, 24 insertions(+)
diff --git a/drivers/video/fbdev/core/fbmem.c b/drivers/video/fbdev/core/fbmem.c
index 30a18d4c9de4..0df148eb4699 100644
--- a/drivers/video/fbdev/core/fbmem.c
+++ b/drivers/video/fbdev/core/fbmem.c
@@ -1779,11 +1779,25 @@ int remove_conflicting_framebuffers(struct apertures_struct *a,
const char *name, bool primary)
{
int ret;
+ bool do_free = false;
+
+ if (!a) {
+ a = alloc_apertures(1);
+ if (!a)
+ return -ENOMEM;
+
+ a->ranges[0].base = 0;
+ a->ranges[0].size = ~0;
+ do_free = true;
+ }
mutex_lock(®istration_lock);
ret = do_remove_conflicting_framebuffers(a, name, primary);
mutex_unlock(®istration_lock);
+ if (do_free)
+ kfree(a);
+
return ret;
}
EXPORT_SYMBOL(remove_conflicting_framebuffers);
diff --git a/include/drm/drm_fb_helper.h b/include/drm/drm_fb_helper.h
index b069433e7fc1..1c1e53abb25d 100644
--- a/include/drm/drm_fb_helper.h
+++ b/include/drm/drm_fb_helper.h
@@ -566,6 +566,16 @@ static inline void drm_fb_helper_output_poll_changed(struct drm_device *dev)
#endif
+/**
+ * drm_fb_helper_remove_conflicting_framebuffers - remove firmware framebuffers
+ * @a: memory range, users of which are to be removed
+ * @name: requesting driver name
+ * @primary: also kick vga16fb if present
+ *
+ * This function removes framebuffer devices (eg. initialized by firmware)
+ * which use memory range described by @a. If @a is NULL all such devices are
+ * removed.
+ */
static inline int
drm_fb_helper_remove_conflicting_framebuffers(struct apertures_struct *a,
const char *name, bool primary)
--
2.18.0
_______________________________________________
Virtualization mailing list
Virtualization@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/virtualization
^ permalink raw reply related
* [PATCH v2 03/12] fbdev: add remove_conflicting_pci_framebuffers()
From: Michał Mirosław @ 2018-08-30 21:00 UTC (permalink / raw)
To: dri-devel
Cc: linux-fbdev, linux-tegra, Bartlomiej Zolnierkiewicz, David Airlie,
amd-gfx, virtualization, Eric Anholt, Thierry Reding,
Alex Deucher, Maxime Ripard, linux-arm-kernel
In-Reply-To: <cover.1535656077.git.mirq-linux@rere.qmqm.pl>
Almost all PCI drivers using remove_conflicting_framebuffers() wrap it
with the same code.
Signed-off-by: Michał Mirosław <mirq-linux@rere.qmqm.pl>
[for v1]
Acked-by: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com>
---
v2: add kerneldoc for DRM helper
---
drivers/video/fbdev/core/fbmem.c | 22 ++++++++++++++++++++++
include/drm/drm_fb_helper.h | 24 ++++++++++++++++++++++++
include/linux/fb.h | 2 ++
3 files changed, 48 insertions(+)
diff --git a/drivers/video/fbdev/core/fbmem.c b/drivers/video/fbdev/core/fbmem.c
index 0df148eb4699..927e016487e9 100644
--- a/drivers/video/fbdev/core/fbmem.c
+++ b/drivers/video/fbdev/core/fbmem.c
@@ -34,6 +34,7 @@
#include <linux/fb.h>
#include <linux/fbcon.h>
#include <linux/mem_encrypt.h>
+#include <linux/pci.h>
#include <asm/fb.h>
@@ -1802,6 +1803,27 @@ int remove_conflicting_framebuffers(struct apertures_struct *a,
}
EXPORT_SYMBOL(remove_conflicting_framebuffers);
+int remove_conflicting_pci_framebuffers(struct pci_dev *pdev, int res_id, const char *name)
+{
+ struct apertures_struct *ap;
+ bool primary = false;
+
+ ap = alloc_apertures(1);
+ if (!ap)
+ return -ENOMEM;
+
+ ap->ranges[0].base = pci_resource_start(pdev, res_id);
+ ap->ranges[0].size = pci_resource_len(pdev, res_id);
+#ifdef CONFIG_X86
+ primary = pdev->resource[PCI_ROM_RESOURCE].flags &
+ IORESOURCE_ROM_SHADOW;
+#endif
+ remove_conflicting_framebuffers(ap, name, primary);
+ kfree(ap);
+ return 0;
+}
+EXPORT_SYMBOL(remove_conflicting_pci_framebuffers);
+
/**
* register_framebuffer - registers a frame buffer device
* @fb_info: frame buffer info structure
diff --git a/include/drm/drm_fb_helper.h b/include/drm/drm_fb_helper.h
index 1c1e53abb25d..6e1fc52d1b1b 100644
--- a/include/drm/drm_fb_helper.h
+++ b/include/drm/drm_fb_helper.h
@@ -587,4 +587,28 @@ drm_fb_helper_remove_conflicting_framebuffers(struct apertures_struct *a,
#endif
}
+/**
+ * drm_fb_helper_remove_conflicting_framebuffers - remove firmware framebuffers for PCI devices
+ * @pdev: PCI device being driven
+ * @resource_id: index of PCI BAR configuring framebuffer memory
+ * @name: requesting driver name
+ *
+ * This function removes framebuffer devices (eg. initialized by firmware)
+ * using memory range configured for @pdev's BAR @resource_id.
+ *
+ * The function assumes that PCI device with shadowed ROM is drives a primary
+ * display and so kicks out vga16fb.
+ */
+static inline int
+drm_fb_helper_remove_conflicting_pci_framebuffers(struct pci_dev *pdev,
+ int resource_id,
+ const char *name)
+{
+#if IS_REACHABLE(CONFIG_FB)
+ return remove_conflicting_pci_framebuffers(pdev, resource_id, name);
+#else
+ return 0;
+#endif
+}
+
#endif
diff --git a/include/linux/fb.h b/include/linux/fb.h
index aa74a228bb92..abeffd55b66a 100644
--- a/include/linux/fb.h
+++ b/include/linux/fb.h
@@ -632,6 +632,8 @@ extern ssize_t fb_sys_write(struct fb_info *info, const char __user *buf,
extern int register_framebuffer(struct fb_info *fb_info);
extern int unregister_framebuffer(struct fb_info *fb_info);
extern int unlink_framebuffer(struct fb_info *fb_info);
+extern int remove_conflicting_pci_framebuffers(struct pci_dev *pdev, int res_id,
+ const char *name);
extern int remove_conflicting_framebuffers(struct apertures_struct *a,
const char *name, bool primary);
extern int fb_prepare_logo(struct fb_info *fb_info, int rotate);
--
2.18.0
_______________________________________________
Virtualization mailing list
Virtualization@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/virtualization
^ permalink raw reply related
* [PATCH v2 04/12] drm/amdgpu: use simpler remove_conflicting_pci_framebuffers()
From: Michał Mirosław @ 2018-08-30 21:00 UTC (permalink / raw)
To: dri-devel
Cc: linux-fbdev, linux-tegra, Bartlomiej Zolnierkiewicz, David Airlie,
amd-gfx, virtualization, Eric Anholt, Thierry Reding,
Alex Deucher, Maxime Ripard, linux-arm-kernel
In-Reply-To: <cover.1535656077.git.mirq-linux@rere.qmqm.pl>
Signed-off-by: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Acked-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c | 24 +-----------------------
1 file changed, 1 insertion(+), 23 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 0b19482b36b8..9b6e037719db 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -560,28 +560,6 @@ MODULE_DEVICE_TABLE(pci, pciidlist);
static struct drm_driver kms_driver;
-static int amdgpu_kick_out_firmware_fb(struct pci_dev *pdev)
-{
- struct apertures_struct *ap;
- bool primary = false;
-
- ap = alloc_apertures(1);
- if (!ap)
- return -ENOMEM;
-
- ap->ranges[0].base = pci_resource_start(pdev, 0);
- ap->ranges[0].size = pci_resource_len(pdev, 0);
-
-#ifdef CONFIG_X86
- primary = pdev->resource[PCI_ROM_RESOURCE].flags & IORESOURCE_ROM_SHADOW;
-#endif
- drm_fb_helper_remove_conflicting_framebuffers(ap, "amdgpudrmfb", primary);
- kfree(ap);
-
- return 0;
-}
-
-
static int amdgpu_pci_probe(struct pci_dev *pdev,
const struct pci_device_id *ent)
{
@@ -609,7 +587,7 @@ static int amdgpu_pci_probe(struct pci_dev *pdev,
return ret;
/* Get rid of things like offb */
- ret = amdgpu_kick_out_firmware_fb(pdev);
+ ret = drm_fb_helper_remove_conflicting_pci_framebuffers(pdev, 0, "amdgpudrmfb");
if (ret)
return ret;
--
2.18.0
_______________________________________________
Virtualization mailing list
Virtualization@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/virtualization
^ permalink raw reply related
* [PATCH v2 06/12] drm/cirrus: use simpler remove_conflicting_pci_framebuffers()
From: Michał Mirosław @ 2018-08-30 21:00 UTC (permalink / raw)
To: dri-devel
Cc: linux-fbdev, linux-tegra, Bartlomiej Zolnierkiewicz, David Airlie,
amd-gfx, virtualization, Eric Anholt, Thierry Reding,
Alex Deucher, Maxime Ripard, linux-arm-kernel
In-Reply-To: <cover.1535656077.git.mirq-linux@rere.qmqm.pl>
Signed-off-by: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Acked-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
drivers/gpu/drm/cirrus/cirrus_drv.c | 23 +----------------------
1 file changed, 1 insertion(+), 22 deletions(-)
diff --git a/drivers/gpu/drm/cirrus/cirrus_drv.c b/drivers/gpu/drm/cirrus/cirrus_drv.c
index 69c4e352dd78..85ed8657c862 100644
--- a/drivers/gpu/drm/cirrus/cirrus_drv.c
+++ b/drivers/gpu/drm/cirrus/cirrus_drv.c
@@ -42,33 +42,12 @@ static const struct pci_device_id pciidlist[] = {
};
-static int cirrus_kick_out_firmware_fb(struct pci_dev *pdev)
-{
- struct apertures_struct *ap;
- bool primary = false;
-
- ap = alloc_apertures(1);
- if (!ap)
- return -ENOMEM;
-
- ap->ranges[0].base = pci_resource_start(pdev, 0);
- ap->ranges[0].size = pci_resource_len(pdev, 0);
-
-#ifdef CONFIG_X86
- primary = pdev->resource[PCI_ROM_RESOURCE].flags & IORESOURCE_ROM_SHADOW;
-#endif
- drm_fb_helper_remove_conflicting_framebuffers(ap, "cirrusdrmfb", primary);
- kfree(ap);
-
- return 0;
-}
-
static int cirrus_pci_probe(struct pci_dev *pdev,
const struct pci_device_id *ent)
{
int ret;
- ret = cirrus_kick_out_firmware_fb(pdev);
+ ret = drm_fb_helper_remove_conflicting_pci_framebuffers(pdev, 0, "cirrusdrmfb");
if (ret)
return ret;
--
2.18.0
_______________________________________________
Virtualization mailing list
Virtualization@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/virtualization
^ permalink raw reply related
* [PATCH v2 05/12] drm/bochs: use simpler remove_conflicting_pci_framebuffers()
From: Michał Mirosław @ 2018-08-30 21:00 UTC (permalink / raw)
To: dri-devel
Cc: linux-fbdev, linux-tegra, Bartlomiej Zolnierkiewicz, David Airlie,
amd-gfx, virtualization, Eric Anholt, Thierry Reding,
Alex Deucher, Maxime Ripard, linux-arm-kernel
In-Reply-To: <cover.1535656077.git.mirq-linux@rere.qmqm.pl>
Signed-off-by: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Acked-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
drivers/gpu/drm/bochs/bochs_drv.c | 18 +-----------------
1 file changed, 1 insertion(+), 17 deletions(-)
diff --git a/drivers/gpu/drm/bochs/bochs_drv.c b/drivers/gpu/drm/bochs/bochs_drv.c
index 7b20318483e4..c61b40c72b62 100644
--- a/drivers/gpu/drm/bochs/bochs_drv.c
+++ b/drivers/gpu/drm/bochs/bochs_drv.c
@@ -143,22 +143,6 @@ static const struct dev_pm_ops bochs_pm_ops = {
/* ---------------------------------------------------------------------- */
/* pci interface */
-static int bochs_kick_out_firmware_fb(struct pci_dev *pdev)
-{
- struct apertures_struct *ap;
-
- ap = alloc_apertures(1);
- if (!ap)
- return -ENOMEM;
-
- ap->ranges[0].base = pci_resource_start(pdev, 0);
- ap->ranges[0].size = pci_resource_len(pdev, 0);
- drm_fb_helper_remove_conflicting_framebuffers(ap, "bochsdrmfb", false);
- kfree(ap);
-
- return 0;
-}
-
static int bochs_pci_probe(struct pci_dev *pdev,
const struct pci_device_id *ent)
{
@@ -171,7 +155,7 @@ static int bochs_pci_probe(struct pci_dev *pdev,
return -ENOMEM;
}
- ret = bochs_kick_out_firmware_fb(pdev);
+ ret = drm_fb_helper_remove_conflicting_pci_framebuffers(pdev, 0, "bochsdrmfb");
if (ret)
return ret;
--
2.18.0
_______________________________________________
Virtualization mailing list
Virtualization@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/virtualization
^ permalink raw reply related
* [PATCH v2 08/12] drm/radeon: use simpler remove_conflicting_pci_framebuffers()
From: Michał Mirosław @ 2018-08-30 21:00 UTC (permalink / raw)
To: dri-devel
Cc: linux-fbdev, linux-tegra, Bartlomiej Zolnierkiewicz, David Airlie,
amd-gfx, virtualization, Eric Anholt, Thierry Reding,
Alex Deucher, Maxime Ripard, linux-arm-kernel
In-Reply-To: <cover.1535656077.git.mirq-linux@rere.qmqm.pl>
Signed-off-by: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Acked-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
drivers/gpu/drm/radeon/radeon_drv.c | 23 +----------------------
1 file changed, 1 insertion(+), 22 deletions(-)
diff --git a/drivers/gpu/drm/radeon/radeon_drv.c b/drivers/gpu/drm/radeon/radeon_drv.c
index b28288a781ef..36c98a0ec991 100644
--- a/drivers/gpu/drm/radeon/radeon_drv.c
+++ b/drivers/gpu/drm/radeon/radeon_drv.c
@@ -311,27 +311,6 @@ static struct drm_driver kms_driver;
bool radeon_device_is_virtual(void);
-static int radeon_kick_out_firmware_fb(struct pci_dev *pdev)
-{
- struct apertures_struct *ap;
- bool primary = false;
-
- ap = alloc_apertures(1);
- if (!ap)
- return -ENOMEM;
-
- ap->ranges[0].base = pci_resource_start(pdev, 0);
- ap->ranges[0].size = pci_resource_len(pdev, 0);
-
-#ifdef CONFIG_X86
- primary = pdev->resource[PCI_ROM_RESOURCE].flags & IORESOURCE_ROM_SHADOW;
-#endif
- drm_fb_helper_remove_conflicting_framebuffers(ap, "radeondrmfb", primary);
- kfree(ap);
-
- return 0;
-}
-
static int radeon_pci_probe(struct pci_dev *pdev,
const struct pci_device_id *ent)
{
@@ -341,7 +320,7 @@ static int radeon_pci_probe(struct pci_dev *pdev,
return -EPROBE_DEFER;
/* Get rid of things like offb */
- ret = radeon_kick_out_firmware_fb(pdev);
+ ret = drm_fb_helper_remove_conflicting_pci_framebuffers(pdev, 0, "radeondrmfb");
if (ret)
return ret;
--
2.18.0
_______________________________________________
Virtualization mailing list
Virtualization@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/virtualization
^ permalink raw reply related
* [PATCH v2 07/12] drm/mgag200: use simpler remove_conflicting_pci_framebuffers()
From: Michał Mirosław @ 2018-08-30 21:00 UTC (permalink / raw)
To: dri-devel
Cc: linux-fbdev, linux-tegra, Bartlomiej Zolnierkiewicz, David Airlie,
amd-gfx, virtualization, Eric Anholt, Thierry Reding,
Alex Deucher, Maxime Ripard, linux-arm-kernel
In-Reply-To: <cover.1535656077.git.mirq-linux@rere.qmqm.pl>
Remove duplicated call, while at it.
Signed-off-by: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Acked-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
drivers/gpu/drm/mgag200/mgag200_drv.c | 21 +--------------------
drivers/gpu/drm/mgag200/mgag200_main.c | 9 ---------
2 files changed, 1 insertion(+), 29 deletions(-)
diff --git a/drivers/gpu/drm/mgag200/mgag200_drv.c b/drivers/gpu/drm/mgag200/mgag200_drv.c
index 74cdde2ee474..ac6af4bd9df6 100644
--- a/drivers/gpu/drm/mgag200/mgag200_drv.c
+++ b/drivers/gpu/drm/mgag200/mgag200_drv.c
@@ -42,29 +42,10 @@ static const struct pci_device_id pciidlist[] = {
MODULE_DEVICE_TABLE(pci, pciidlist);
-static void mgag200_kick_out_firmware_fb(struct pci_dev *pdev)
-{
- struct apertures_struct *ap;
- bool primary = false;
-
- ap = alloc_apertures(1);
- if (!ap)
- return;
-
- ap->ranges[0].base = pci_resource_start(pdev, 0);
- ap->ranges[0].size = pci_resource_len(pdev, 0);
-
-#ifdef CONFIG_X86
- primary = pdev->resource[PCI_ROM_RESOURCE].flags & IORESOURCE_ROM_SHADOW;
-#endif
- drm_fb_helper_remove_conflicting_framebuffers(ap, "mgag200drmfb", primary);
- kfree(ap);
-}
-
static int mga_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
{
- mgag200_kick_out_firmware_fb(pdev);
+ drm_fb_helper_remove_conflicting_pci_framebuffers(pdev, 0, "mgag200drmfb");
return drm_get_pci_dev(pdev, ent, &driver);
}
diff --git a/drivers/gpu/drm/mgag200/mgag200_main.c b/drivers/gpu/drm/mgag200/mgag200_main.c
index 780f983b0294..79d54103d470 100644
--- a/drivers/gpu/drm/mgag200/mgag200_main.c
+++ b/drivers/gpu/drm/mgag200/mgag200_main.c
@@ -124,20 +124,11 @@ static int mga_probe_vram(struct mga_device *mdev, void __iomem *mem)
static int mga_vram_init(struct mga_device *mdev)
{
void __iomem *mem;
- struct apertures_struct *aper = alloc_apertures(1);
- if (!aper)
- return -ENOMEM;
/* BAR 0 is VRAM */
mdev->mc.vram_base = pci_resource_start(mdev->dev->pdev, 0);
mdev->mc.vram_window = pci_resource_len(mdev->dev->pdev, 0);
- aper->ranges[0].base = mdev->mc.vram_base;
- aper->ranges[0].size = mdev->mc.vram_window;
-
- drm_fb_helper_remove_conflicting_framebuffers(aper, "mgafb", true);
- kfree(aper);
-
if (!devm_request_mem_region(mdev->dev->dev, mdev->mc.vram_base, mdev->mc.vram_window,
"mgadrmfb_vram")) {
DRM_ERROR("can't reserve VRAM\n");
--
2.18.0
_______________________________________________
Virtualization mailing list
Virtualization@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/virtualization
^ permalink raw reply related
* [PATCH v2 09/12] drm/virtio: use simpler remove_conflicting_pci_framebuffers()
From: Michał Mirosław @ 2018-08-30 21:00 UTC (permalink / raw)
To: dri-devel
Cc: linux-fbdev, linux-tegra, Bartlomiej Zolnierkiewicz, David Airlie,
amd-gfx, virtualization, Eric Anholt, Thierry Reding,
Alex Deucher, Maxime Ripard, linux-arm-kernel
In-Reply-To: <cover.1535656077.git.mirq-linux@rere.qmqm.pl>
Signed-off-by: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Acked-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
drivers/gpu/drm/virtio/virtgpu_drm_bus.c | 24 +++---------------------
1 file changed, 3 insertions(+), 21 deletions(-)
diff --git a/drivers/gpu/drm/virtio/virtgpu_drm_bus.c b/drivers/gpu/drm/virtio/virtgpu_drm_bus.c
index 7df8d0c9026a..115ed546ca4e 100644
--- a/drivers/gpu/drm/virtio/virtgpu_drm_bus.c
+++ b/drivers/gpu/drm/virtio/virtgpu_drm_bus.c
@@ -28,26 +28,6 @@
#include "virtgpu_drv.h"
-static void virtio_pci_kick_out_firmware_fb(struct pci_dev *pci_dev)
-{
- struct apertures_struct *ap;
- bool primary;
-
- ap = alloc_apertures(1);
- if (!ap)
- return;
-
- ap->ranges[0].base = pci_resource_start(pci_dev, 0);
- ap->ranges[0].size = pci_resource_len(pci_dev, 0);
-
- primary = pci_dev->resource[PCI_ROM_RESOURCE].flags
- & IORESOURCE_ROM_SHADOW;
-
- drm_fb_helper_remove_conflicting_framebuffers(ap, "virtiodrmfb", primary);
-
- kfree(ap);
-}
-
int drm_virtio_init(struct drm_driver *driver, struct virtio_device *vdev)
{
struct drm_device *dev;
@@ -69,7 +49,9 @@ int drm_virtio_init(struct drm_driver *driver, struct virtio_device *vdev)
pname);
dev->pdev = pdev;
if (vga)
- virtio_pci_kick_out_firmware_fb(pdev);
+ drm_fb_helper_remove_conflicting_pci_framebuffers(pdev,
+ 0,
+ "virtiodrmfb");
snprintf(unique, sizeof(unique), "pci:%s", pname);
ret = drm_dev_set_unique(dev, unique);
--
2.18.0
_______________________________________________
Virtualization mailing list
Virtualization@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/virtualization
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox