paravirt: refactor struct paravirt_ops into smaller pv_*_ops

This patch refactors the paravirt_ops structure into groups of
functionally related ops:

pv_info - random info, rather than function entrypoints
pv_init_ops - functions used at boot time (some for module_init too)
pv_misc_ops - lazy mode, which didn't fit well anywhere else
pv_time_ops - time-related functions
pv_cpu_ops - various privileged instruction ops
pv_irq_ops - operations for managing interrupt state
pv_apic_ops - APIC operations
pv_mmu_ops - operations for managing pagetables

There are several motivations for this:

1. Some of these ops will be general to all x86, and some will be
   i386/x86-64 specific.  This makes it easier to share common stuff
   while allowing separate implementations where needed.

2. At the moment we must export all of paravirt_ops, but modules only
   need selected parts of it.  This allows us to export on a case by case
   basis (and also choose which export license we want to apply).

3. Functional groupings make things a bit more readable.

Struct paravirt_ops is now only used as a template to generate
patch-site identifiers, and to extract function pointers for inserting
into jmp/calls when patching.  It is only instantiated when needed.

Signed-off-by: Jeremy Fitzhardinge <jeremy@xensource.com>
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
Cc: Andi Kleen <ak@suse.de>
Cc: Zach Amsden <zach@vmware.com>
Cc: Avi Kivity <avi@qumranet.com>
Cc: Anthony Liguory <aliguori@us.ibm.com>
Cc: "Glauber de Oliveira Costa" <glommer@gmail.com>
Cc: Jun Nakajima <jun.nakajima@intel.com>

3 files changed, 73 insertions, 59 deletions

diff --git a/drivers/lguest/core.c b/drivers/lguest/core.c
index 4a315f08a567..a0788c12b392 100644
--- a/drivers/lguest/core.c
+++ b/drivers/lguest/core.c
@@ -248,8 +248,8 @@ static void unmap_switcher(void)
 }
 
 /*H:130 Our Guest is usually so well behaved; it never tries to do things it
- * isn't allowed to.  Unfortunately, "struct paravirt_ops" isn't quite
- * complete, because it doesn't contain replacements for the Intel I/O
+ * isn't allowed to.  Unfortunately, Linux's paravirtual infrastructure isn't
+ * quite complete, because it doesn't contain replacements for the Intel I/O
  * instructions.  As a result, the Guest sometimes fumbles across one during
  * the boot process as it probes for various things which are usually attached
  * to a PC.
@@ -694,7 +694,7 @@ static int __init init(void)
 
         /* Lguest can't run under Xen, VMI or itself.  It does Tricky Stuff. */
         if (paravirt_enabled()) {
-                printk("lguest is afraid of %s\n", paravirt_ops.name);
+                printk("lguest is afraid of %s\n", pv_info.name);
                 return -EPERM;
         }
 
diff --git a/drivers/lguest/lguest.c b/drivers/lguest/lguest.c
index ee1c6d05c3d3..ca9b844f37c2 100644
--- a/drivers/lguest/lguest.c
+++ b/drivers/lguest/lguest.c
@@ -23,7 +23,7 @@
  *
  * So how does the kernel know it's a Guest?  The Guest starts at a special
  * entry point marked with a magic string, which sets up a few things then
- * calls here.  We replace the native functions in "struct paravirt_ops"
+ * calls here.  We replace the native functions various "paravirt" structures
  * with our Guest versions, then boot like normal. :*/
 
 /*
@@ -331,7 +331,7 @@ static void lguest_load_tls(struct thread_struct *t, unsigned int cpu)
 }
 
 /*G:038 That's enough excitement for now, back to ploughing through each of
- * the paravirt_ops (we're about 1/3 of the way through).
+ * the different pv_ops structures (we're about 1/3 of the way through).
  *
  * This is the Local Descriptor Table, another weird Intel thingy.  Linux only
  * uses this for some strange applications like Wine.  We don't do anything
@@ -558,7 +558,7 @@ static void lguest_set_pte(pte_t *ptep, pte_t pteval)
                 lazy_hcall(LHCALL_FLUSH_TLB, 1, 0, 0);
 }
 
-/* Unfortunately for Lguest, the paravirt_ops for page tables were based on
+/* Unfortunately for Lguest, the pv_mmu_ops for page tables were based on
  * native page table operations.  On native hardware you can set a new page
  * table entry whenever you want, but if you want to remove one you have to do
  * a TLB flush (a TLB is a little cache of page table entries kept by the CPU).
@@ -782,7 +782,7 @@ static void lguest_time_init(void)
         clocksource_register(&lguest_clock);
 
         /* Now we've set up our clock, we can use it as the scheduler clock */
-        paravirt_ops.sched_clock = lguest_sched_clock;
+        pv_time_ops.sched_clock = lguest_sched_clock;
 
         /* We can't set cpumask in the initializer: damn C limitations!  Set it
          * here and register our timer device. */
@@ -902,7 +902,7 @@ static __init char *lguest_memory_setup(void)
 /*G:050
  * Patching (Powerfully Placating Performance Pedants)
  *
- * We have already seen that "struct paravirt_ops" lets us replace simple
+ * We have already seen that pv_ops structures let us replace simple
  * native instructions with calls to the appropriate back end all throughout
  * the kernel.  This allows the same kernel to run as a Guest and as a native
  * kernel, but it's slow because of all the indirect branches.
@@ -927,10 +927,10 @@ static const struct lguest_insns
 {
         const char *start, *end;
 } lguest_insns[] = {
-        [PARAVIRT_PATCH(irq_disable)] = { lgstart_cli, lgend_cli },
-        [PARAVIRT_PATCH(irq_enable)] = { lgstart_sti, lgend_sti },
-        [PARAVIRT_PATCH(restore_fl)] = { lgstart_popf, lgend_popf },
-        [PARAVIRT_PATCH(save_fl)] = { lgstart_pushf, lgend_pushf },
+        [PARAVIRT_PATCH(pv_irq_ops.irq_disable)] = { lgstart_cli, lgend_cli },
+        [PARAVIRT_PATCH(pv_irq_ops.irq_enable)] = { lgstart_sti, lgend_sti },
+        [PARAVIRT_PATCH(pv_irq_ops.restore_fl)] = { lgstart_popf, lgend_popf },
+        [PARAVIRT_PATCH(pv_irq_ops.save_fl)] = { lgstart_pushf, lgend_pushf },
 };
 
 /* Now our patch routine is fairly simple (based on the native one in
@@ -957,9 +957,9 @@ static unsigned lguest_patch(u8 type, u16 clobber, void *ibuf,
         return insn_len;
 }
 
-/*G:030 Once we get to lguest_init(), we know we're a Guest.  The paravirt_ops
- * structure in the kernel provides a single point for (almost) every routine
- * we have to override to avoid privileged instructions. */
+/*G:030 Once we get to lguest_init(), we know we're a Guest.  The pv_ops
+ * structures in the kernel provide points for (almost) every routine we have
+ * to override to avoid privileged instructions. */
 __init void lguest_init(void *boot)
 {
         /* Copy boot parameters first: the Launcher put the physical location
@@ -974,54 +974,68 @@ __init void lguest_init(void *boot)
 
         /* We're under lguest, paravirt is enabled, and we're running at
          * privilege level 1, not 0 as normal. */
-        paravirt_ops.name = "lguest";
-        paravirt_ops.paravirt_enabled = 1;
-        paravirt_ops.kernel_rpl = 1;
+        pv_info.name = "lguest";
+        pv_info.paravirt_enabled = 1;
+        pv_info.kernel_rpl = 1;
 
         /* We set up all the lguest overrides for sensitive operations.  These
          * are detailed with the operations themselves. */
-        paravirt_ops.save_fl = save_fl;
-        paravirt_ops.restore_fl = restore_fl;
-        paravirt_ops.irq_disable = irq_disable;
-        paravirt_ops.irq_enable = irq_enable;
-        paravirt_ops.load_gdt = lguest_load_gdt;
-        paravirt_ops.memory_setup = lguest_memory_setup;
-        paravirt_ops.cpuid = lguest_cpuid;
-        paravirt_ops.write_cr3 = lguest_write_cr3;
-        paravirt_ops.flush_tlb_user = lguest_flush_tlb_user;
-        paravirt_ops.flush_tlb_single = lguest_flush_tlb_single;
-        paravirt_ops.flush_tlb_kernel = lguest_flush_tlb_kernel;
-        paravirt_ops.set_pte = lguest_set_pte;
-        paravirt_ops.set_pte_at = lguest_set_pte_at;
-        paravirt_ops.set_pmd = lguest_set_pmd;
+
+        /* interrupt-related operations */
+        pv_irq_ops.init_IRQ = lguest_init_IRQ;
+        pv_irq_ops.save_fl = save_fl;
+        pv_irq_ops.restore_fl = restore_fl;
+        pv_irq_ops.irq_disable = irq_disable;
+        pv_irq_ops.irq_enable = irq_enable;
+        pv_irq_ops.safe_halt = lguest_safe_halt;
+
+        /* init-time operations */
+        pv_init_ops.memory_setup = lguest_memory_setup;
+        pv_init_ops.patch = lguest_patch;
+
+        /* Intercepts of various cpu instructions */
+        pv_cpu_ops.load_gdt = lguest_load_gdt;
+        pv_cpu_ops.cpuid = lguest_cpuid;
+        pv_cpu_ops.load_idt = lguest_load_idt;
+        pv_cpu_ops.iret = lguest_iret;
+        pv_cpu_ops.load_esp0 = lguest_load_esp0;
+        pv_cpu_ops.load_tr_desc = lguest_load_tr_desc;
+        pv_cpu_ops.set_ldt = lguest_set_ldt;
+        pv_cpu_ops.load_tls = lguest_load_tls;
+        pv_cpu_ops.set_debugreg = lguest_set_debugreg;
+        pv_cpu_ops.clts = lguest_clts;
+        pv_cpu_ops.read_cr0 = lguest_read_cr0;
+        pv_cpu_ops.write_cr0 = lguest_write_cr0;
+        pv_cpu_ops.read_cr4 = lguest_read_cr4;
+        pv_cpu_ops.write_cr4 = lguest_write_cr4;
+        pv_cpu_ops.write_gdt_entry = lguest_write_gdt_entry;
+        pv_cpu_ops.write_idt_entry = lguest_write_idt_entry;
+        pv_cpu_ops.wbinvd = lguest_wbinvd;
+
+        /* pagetable management */
+        pv_mmu_ops.write_cr3 = lguest_write_cr3;
+        pv_mmu_ops.flush_tlb_user = lguest_flush_tlb_user;
+        pv_mmu_ops.flush_tlb_single = lguest_flush_tlb_single;
+        pv_mmu_ops.flush_tlb_kernel = lguest_flush_tlb_kernel;
+        pv_mmu_ops.set_pte = lguest_set_pte;
+        pv_mmu_ops.set_pte_at = lguest_set_pte_at;
+        pv_mmu_ops.set_pmd = lguest_set_pmd;
+        pv_mmu_ops.read_cr2 = lguest_read_cr2;
+        pv_mmu_ops.read_cr3 = lguest_read_cr3;
+
 #ifdef CONFIG_X86_LOCAL_APIC
-        paravirt_ops.apic_write = lguest_apic_write;
-        paravirt_ops.apic_write_atomic = lguest_apic_write;
-        paravirt_ops.apic_read = lguest_apic_read;
+        /* apic read/write intercepts */
+        pv_apic_ops.apic_write = lguest_apic_write;
+        pv_apic_ops.apic_write_atomic = lguest_apic_write;
+        pv_apic_ops.apic_read = lguest_apic_read;
 #endif
-        paravirt_ops.load_idt = lguest_load_idt;
-        paravirt_ops.iret = lguest_iret;
-        paravirt_ops.load_esp0 = lguest_load_esp0;
-        paravirt_ops.load_tr_desc = lguest_load_tr_desc;
-        paravirt_ops.set_ldt = lguest_set_ldt;
-        paravirt_ops.load_tls = lguest_load_tls;
-        paravirt_ops.set_debugreg = lguest_set_debugreg;
-        paravirt_ops.clts = lguest_clts;
-        paravirt_ops.read_cr0 = lguest_read_cr0;
-        paravirt_ops.write_cr0 = lguest_write_cr0;
-        paravirt_ops.init_IRQ = lguest_init_IRQ;
-        paravirt_ops.read_cr2 = lguest_read_cr2;
-        paravirt_ops.read_cr3 = lguest_read_cr3;
-        paravirt_ops.read_cr4 = lguest_read_cr4;
-        paravirt_ops.write_cr4 = lguest_write_cr4;
-        paravirt_ops.write_gdt_entry = lguest_write_gdt_entry;
-        paravirt_ops.write_idt_entry = lguest_write_idt_entry;
-        paravirt_ops.patch = lguest_patch;
-        paravirt_ops.safe_halt = lguest_safe_halt;
-        paravirt_ops.get_wallclock = lguest_get_wallclock;
-        paravirt_ops.time_init = lguest_time_init;
-        paravirt_ops.set_lazy_mode = lguest_lazy_mode;
-        paravirt_ops.wbinvd = lguest_wbinvd;
+
+        /* time operations */
+        pv_time_ops.get_wallclock = lguest_get_wallclock;
+        pv_time_ops.time_init = lguest_time_init;
+
+        pv_misc_ops.set_lazy_mode = lguest_lazy_mode;
+
         /* Now is a good time to look at the implementations of these functions
          * before returning to the rest of lguest_init(). */
 
diff --git a/drivers/lguest/lguest_bus.c b/drivers/lguest/lguest_bus.c
index 9e7752cc8002..57329788f8a7 100644
--- a/drivers/lguest/lguest_bus.c
+++ b/drivers/lguest/lguest_bus.c
@@ -201,7 +201,7 @@ static void scan_devices(void)
  * "struct lguest_device_desc" array. */
 static int __init lguest_bus_init(void)
 {
-        if (strcmp(paravirt_ops.name, "lguest") != 0)
+        if (strcmp(pv_info.name, "lguest") != 0)
                 return 0;
 
         /* Devices are in a single page above top of "normal" mem */