vdso function descriptors (VDS64_HAS_DESCRIPTORS)?

index b5e1f8f8a05c..2ff884853f97 100644
@@ -13,9 +13,6 @@
 
 #define VDSO_VERSION_STRING	LINUX_2.6.15
 
-/* Define if 64 bits VDSO has procedure descriptors */
-#undef VDS64_HAS_DESCRIPTORS
-
 #ifndef __ASSEMBLY__
 
 /* Offsets relative to thread->vdso_base */

@@ -28,25 +25,6 @@ int vdso_getcpu_init(void);
 #else /* __ASSEMBLY__ */
 
 #ifdef __VDSO64__
-#ifdef VDS64_HAS_DESCRIPTORS
-#define V_FUNCTION_BEGIN(name)		\
-	.globl name;			\
-        .section ".opd","a";		\
-        .align 3;			\
-	name:				\
-	.quad .name,.TOC.@tocbase,0;	\
-	.previous;			\
-	.globl .name;			\
-	.type .name,@function; 		\
-	.name:				\
-
-#define V_FUNCTION_END(name)		\
-	.size .name,.-.name;
-
-#define V_LOCAL_FUNC(name) (.name)
-
-#else /* VDS64_HAS_DESCRIPTORS */
-
 #define V_FUNCTION_BEGIN(name)		\
 	.globl name;			\
 	name:				\

@@ -55,8 +33,6 @@ int vdso_getcpu_init(void);
 	.size name,.-name;
 
 #define V_LOCAL_FUNC(name) (name)
-
-#endif /* VDS64_HAS_DESCRIPTORS */
 #endif /* __VDSO64__ */
 
 #ifdef __VDSO32__

index b9a108411c0d..d3b77c15f9ce 100644
@@ -391,12 +391,7 @@ static unsigned long __init find_function64(struct lib64_elfinfo *lib,
 		       symname);
 		return 0;
 	}
-#ifdef VDS64_HAS_DESCRIPTORS
-	return *((u64 *)(vdso64_kbase + sym->st_value - VDSO64_LBASE)) -
-		VDSO64_LBASE;
-#else
 	return sym->st_value - VDSO64_LBASE;
-#endif
 }
 
 static int __init vdso_do_func_patch64(struct lib32_elfinfo *v32,

index 11a85558d0da..0094ac79a18c 100644
@@ -22,6 +22,7 @@
 #include <linux/types.h>
 #include <linux/mman.h>
 #include <linux/mm.h>
+#include <linux/time.h>
 #include <linux/hardirq.h>
 #include <asm/io.h>
 #include <asm/page.h>

@@ -35,6 +36,8 @@
 #include <asm/rtas.h>
 #include <asm/cputable.h>
 #include <asm/cache.h>
+#include <asm/systemcfg.h>
+#include <asm/compat.h>
 
 #define DEFINE(sym, val) \
 	asm volatile("\n->" #sym " %0 " #val : : "i" (val))

@@ -167,5 +170,24 @@ int main(void)
 	DEFINE(CPU_SPEC_FEATURES, offsetof(struct cpu_spec, cpu_features));
 	DEFINE(CPU_SPEC_SETUP, offsetof(struct cpu_spec, cpu_setup));
 
+	/* systemcfg offsets for use by vdso */
+	DEFINE(CFG_TB_ORIG_STAMP, offsetof(struct systemcfg, tb_orig_stamp));
+	DEFINE(CFG_TB_TICKS_PER_SEC, offsetof(struct systemcfg, tb_ticks_per_sec));
+	DEFINE(CFG_TB_TO_XS, offsetof(struct systemcfg, tb_to_xs));
+	DEFINE(CFG_STAMP_XSEC, offsetof(struct systemcfg, stamp_xsec));
+	DEFINE(CFG_TB_UPDATE_COUNT, offsetof(struct systemcfg, tb_update_count));
+	DEFINE(CFG_TZ_MINUTEWEST, offsetof(struct systemcfg, tz_minuteswest));
+	DEFINE(CFG_TZ_DSTTIME, offsetof(struct systemcfg, tz_dsttime));
+	DEFINE(CFG_SYSCALL_MAP32, offsetof(struct systemcfg, syscall_map_32));
+	DEFINE(CFG_SYSCALL_MAP64, offsetof(struct systemcfg, syscall_map_64));
+
+	/* timeval/timezone offsets for use by vdso */
+	DEFINE(TVAL64_TV_SEC, offsetof(struct timeval, tv_sec));
+	DEFINE(TVAL64_TV_USEC, offsetof(struct timeval, tv_usec));
+	DEFINE(TVAL32_TV_SEC, offsetof(struct compat_timeval, tv_sec));
+	DEFINE(TVAL32_TV_USEC, offsetof(struct compat_timeval, tv_usec));
+	DEFINE(TZONE_TZ_MINWEST, offsetof(struct timezone, tz_minuteswest));
+	DEFINE(TZONE_TZ_DSTTIME, offsetof(struct timezone, tz_dsttime));
+
 	return 0;
 }

index a3a92863a0ac..d98c320828e5 100644
@@ -990,6 +990,34 @@ static void __init emergency_stack_init(void)
 						limit)) + PAGE_SIZE;
 }
 
+/*
+ * Called from setup_arch to initialize the bitmap of available
+ * syscalls in the systemcfg page
+ */
+void __init setup_syscall_map(void)
+{
+	unsigned int i, count64 = 0, count32 = 0;
+	extern unsigned long *sys_call_table;
+	extern unsigned long *sys_call_table32;
+	extern unsigned long sys_ni_syscall;
+
+
+	for (i = 0; i < __NR_syscalls; i++) {
+		if (sys_call_table[i] == sys_ni_syscall)
+			continue;
+		count64++;
+		systemcfg->syscall_map_64[i >> 5] |= 0x80000000UL >> (i & 0x1f);
+	}
+	for (i = 0; i < __NR_syscalls; i++) {
+		if (sys_call_table32[i] == sys_ni_syscall)
+			continue;
+		count32++;
+		systemcfg->syscall_map_32[i >> 5] |= 0x80000000UL >> (i & 0x1f);
+	}
+	printk(KERN_INFO "Syscall map setup, %d 32 bits and %d 64 bits syscalls\n",
+	       count32, count64);
+}
+
 /*
  * Called into from start_kernel, after lock_kernel has been called.
  * Initializes bootmem, which is unsed to manage page allocation until

@@ -1028,6 +1056,9 @@ void __init setup_arch(char **cmdline_p)
 	/* set up the bootmem stuff with available memory */
 	do_init_bootmem();
 
+	/* initialize the syscall map in systemcfg */
+	setup_syscall_map();
+
 	ppc_md.setup_arch();
 
 	/* Select the correct idle loop for the platform. */

index 52f8b4c718b0..00e80e3e6986 100644
@@ -36,6 +36,7 @@
 #include <asm/ppcdebug.h>
 #include <asm/unistd.h>
 #include <asm/cacheflush.h>
+#include <asm/vdso.h>
 
 #define DEBUG_SIG 0
 

@@ -428,10 +429,14 @@ static int setup_rt_frame(int signr, struct k_sigaction *ka, siginfo_t *info,
 		goto badframe;
 
 	/* Set up to return from userspace. */
-	err |= setup_trampoline(__NR_rt_sigreturn, &frame->tramp[0]);
-	if (err)
-		goto badframe;
-
+	if (vdso64_rt_sigtramp && current->thread.vdso_base) {
+		regs->link = current->thread.vdso_base + vdso64_rt_sigtramp;
+	} else {
+		err |= setup_trampoline(__NR_rt_sigreturn, &frame->tramp[0]);
+		if (err)
+			goto badframe;
+		regs->link = (unsigned long) &frame->tramp[0];
+	}
 	funct_desc_ptr = (func_descr_t __user *) ka->sa.sa_handler;
 
 	/* Allocate a dummy caller frame for the signal handler. */

@@ -440,7 +445,6 @@ static int setup_rt_frame(int signr, struct k_sigaction *ka, siginfo_t *info,
 
 	/* Set up "regs" so we "return" to the signal handler. */
 	err |= get_user(regs->nip, &funct_desc_ptr->entry);
-	regs->link = (unsigned long) &frame->tramp[0];
 	regs->gpr[1] = newsp;
 	err |= get_user(regs->gpr[2], &funct_desc_ptr->toc);
 	regs->gpr[3] = signr;

index 145eac7ef8f4..b9093e9d2c72 100644
@@ -31,6 +31,7 @@
 #include <asm/ppcdebug.h>
 #include <asm/unistd.h>
 #include <asm/cacheflush.h>
+#include <asm/vdso.h>
 
 #define DEBUG_SIG 0
 

@@ -656,18 +657,24 @@ static int handle_rt_signal32(unsigned long sig, struct k_sigaction *ka,
 
 	/* Save user registers on the stack */
 	frame = &rt_sf->uc.uc_mcontext;
-	if (save_user_regs(regs, frame, __NR_rt_sigreturn))
-		goto badframe;
-
 	if (put_user(regs->gpr[1], (unsigned long __user *)newsp))
 		goto badframe;
+
+	if (vdso32_rt_sigtramp && current->thread.vdso_base) {
+		if (save_user_regs(regs, frame, 0))
+			goto badframe;
+		regs->link = current->thread.vdso_base + vdso32_rt_sigtramp;
+	} else {
+		if (save_user_regs(regs, frame, __NR_rt_sigreturn))
+			goto badframe;
+		regs->link = (unsigned long) frame->tramp;
+	}
 	regs->gpr[1] = (unsigned long) newsp;
 	regs->gpr[3] = sig;
 	regs->gpr[4] = (unsigned long) &rt_sf->info;
 	regs->gpr[5] = (unsigned long) &rt_sf->uc;
 	regs->gpr[6] = (unsigned long) rt_sf;
 	regs->nip = (unsigned long) ka->sa.sa_handler;
-	regs->link = (unsigned long) frame->tramp;
 	regs->trap = 0;
 	regs->result = 0;
 

@@ -825,8 +832,15 @@ static int handle_signal32(unsigned long sig, struct k_sigaction *ka,
 	    || __put_user(sig, &sc->signal))
 		goto badframe;
 
-	if (save_user_regs(regs, &frame->mctx, __NR_sigreturn))
-		goto badframe;
+	if (vdso32_sigtramp && current->thread.vdso_base) {
+		if (save_user_regs(regs, &frame->mctx, 0))
+			goto badframe;
+		regs->link = current->thread.vdso_base + vdso32_sigtramp;
+	} else {
+		if (save_user_regs(regs, &frame->mctx, __NR_sigreturn))
+			goto badframe;
+		regs->link = (unsigned long) frame->mctx.tramp;
+	}
 
 	if (put_user(regs->gpr[1], (unsigned long __user *)newsp))
 		goto badframe;

@@ -834,7 +848,6 @@ static int handle_signal32(unsigned long sig, struct k_sigaction *ka,
 	regs->gpr[3] = sig;
 	regs->gpr[4] = (unsigned long) sc;
 	regs->nip = (unsigned long) ka->sa.sa_handler;
-	regs->link = (unsigned long) frame->mctx.tramp;
 	regs->trap = 0;
 	regs->result = 0;
 

index d6ecf0727596..a9e43792f8fe 100644
@@ -383,7 +383,7 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
 	 * For now we leave it which means the time can be some
 	 * number of msecs off until someone does a settimeofday()
 	 */
-	do_gtod.tb_orig_stamp = tb_last_stamp;
+	do_gtod.varp->tb_orig_stamp = tb_last_stamp;
 	systemcfg->tb_orig_stamp = tb_last_stamp;
 #endif
 

157 lines not on this page · raw message

614 lines not on this page · raw message

index d876a18dbcf7..968222827dbe 100644
@@ -63,6 +63,7 @@
 #include <asm/system.h>
 #include <asm/iommu.h>
 #include <asm/abs_addr.h>
+#include <asm/vdso.h>
 
 int mem_init_done;
 unsigned long ioremap_bot = IMALLOC_BASE;

@@ -748,6 +749,8 @@ void __init mem_init(void)
 #ifdef CONFIG_PPC_ISERIES
 	iommu_vio_init();
 #endif
+	/* Initialize the vDSO */
+	vdso_init();
 }
 
 /*

index 3ad9cef2cd28..4c873236d06a 100644
@@ -782,6 +782,14 @@ static int load_elf_binary(struct linux_binprm * bprm, struct pt_regs * regs)
 		goto out_free_dentry;
 	}
 	
+#ifdef ARCH_HAS_SETUP_ADDITIONAL_PAGES
+	retval = arch_setup_additional_pages(bprm, executable_stack);
+	if (retval < 0) {
+		send_sig(SIGKILL, current, 0);
+		goto out_free_dentry;
+	}
+#endif /* ARCH_HAS_SETUP_ADDITIONAL_PAGES */
+
 	current->mm->start_stack = bprm->p;
 
 	/* Now we do a little grungy work by mmaping the ELF image into

index 7e2b95f3cdce..802338efcb19 100644
@@ -30,14 +30,11 @@ struct exec
 
 #ifdef __KERNEL__
 
-#define STACK_TOP_USER64 (TASK_SIZE_USER64)
+#define STACK_TOP_USER64 TASK_SIZE_USER64
+#define STACK_TOP_USER32 TASK_SIZE_USER32
 
-/* Give 32-bit user space a full 4G address space to live in. */
-#define STACK_TOP_USER32 (TASK_SIZE_USER32)
-
-#define STACK_TOP ((test_thread_flag(TIF_32BIT) || \
-		(ppcdebugset(PPCDBG_BINFMT_32ADDR))) ? \
-		STACK_TOP_USER32 : STACK_TOP_USER64)
+#define STACK_TOP (test_thread_flag(TIF_32BIT) ? \
+		   STACK_TOP_USER32 : STACK_TOP_USER64)
 
 #endif /* __KERNEL__ */
 

index b7530725026e..d815b9c89145 100644
@@ -238,10 +238,20 @@ do {								\
 /* A special ignored type value for PPC, for glibc compatibility.  */
 #define AT_IGNOREPPC		22
 
+/* The vDSO location. We have to use the same value as x86 for glibc's
+ * sake :-)
+ */
+#define AT_SYSINFO_EHDR		33
+
 extern int dcache_bsize;
 extern int icache_bsize;
 extern int ucache_bsize;
 
+/* We do have an arch_setup_additional_pages for vDSO matters */
+#define ARCH_HAS_SETUP_ADDITIONAL_PAGES
+struct linux_binprm;
+extern int arch_setup_additional_pages(struct linux_binprm *bprm, int executable_stack);
+
 /*
  * The requirements here are:
  * - keep the final alignment of sp (sp & 0xf)

@@ -260,6 +270,8 @@ do {									\
 	NEW_AUX_ENT(AT_DCACHEBSIZE, dcache_bsize);			\
 	NEW_AUX_ENT(AT_ICACHEBSIZE, icache_bsize);			\
 	NEW_AUX_ENT(AT_UCACHEBSIZE, ucache_bsize);			\
+	/* vDSO base */							\
+	NEW_AUX_ENT(AT_SYSINFO_EHDR, current->thread.vdso_base);       	\
  } while (0)
 
 /* PowerPC64 relocations defined by the ABIs */

index ef16df988b62..4db453081fe3 100644
@@ -185,6 +185,9 @@ extern int page_is_ram(unsigned long pfn);
 
 extern u64 ppc64_pft_size;		/* Log 2 of page table size */
 
+/* We do define AT_SYSINFO_EHDR but don't use the gate mecanism */
+#define __HAVE_ARCH_GATE_AREA		1
+
 #endif /* __ASSEMBLY__ */
 
 #ifdef MODULE

index ae3a5bb3ea98..80c5eb8de01f 100644
@@ -544,8 +544,8 @@ extern struct task_struct *last_task_used_altivec;
 /* This decides where the kernel will search for a free chunk of vm
  * space during mmap's.
  */
-#define TASK_UNMAPPED_BASE_USER32 (PAGE_ALIGN(STACK_TOP_USER32 / 4))
-#define TASK_UNMAPPED_BASE_USER64 (PAGE_ALIGN(STACK_TOP_USER64 / 4))
+#define TASK_UNMAPPED_BASE_USER32 (PAGE_ALIGN(TASK_SIZE_USER32 / 4))
+#define TASK_UNMAPPED_BASE_USER64 (PAGE_ALIGN(TASK_SIZE_USER64 / 4))
 
 #define TASK_UNMAPPED_BASE ((test_thread_flag(TIF_32BIT)||(ppcdebugset(PPCDBG_BINFMT_32ADDR))) ? \
 		TASK_UNMAPPED_BASE_USER32 : TASK_UNMAPPED_BASE_USER64 )

@@ -564,7 +564,7 @@ struct thread_struct {
 	unsigned long	fpexc_mode;	/* Floating-point exception mode */
 	unsigned long	start_tb;	/* Start purr when proc switched in */
 	unsigned long	accum_tb;	/* Total accumilated purr for process */
-	unsigned long	pad;		/* was saved_msr, saved_softe */
+	unsigned long	vdso_base;	/* base of the vDSO library */
 #ifdef CONFIG_ALTIVEC
 	/* Complete AltiVec register set */
 	vector128	vr[32] __attribute((aligned(16)));

index ab328ad80b73..9b86b53129aa 100644
@@ -20,10 +20,14 @@
  * Minor version changes are a hint.
  */
 #define SYSTEMCFG_MAJOR 1
-#define SYSTEMCFG_MINOR 0
+#define SYSTEMCFG_MINOR 1
 
 #ifndef __ASSEMBLY__
 
+#include <linux/unistd.h>
+
+#define SYSCALL_MAP_SIZE      ((__NR_syscalls + 31) / 32)
+
 struct systemcfg {
 	__u8  eye_catcher[16];		/* Eyecatcher: SYSTEMCFG:PPC64	0x00 */
 	struct {			/* Systemcfg version numbers	     */

@@ -47,6 +51,8 @@ struct systemcfg {
 	__u32 dcache_line_size;		/* L1 d-cache line size		0x64 */
 	__u32 icache_size;		/* L1 i-cache size		0x68 */
 	__u32 icache_line_size;		/* L1 i-cache line size		0x6C */
+   	__u32 syscall_map_64[SYSCALL_MAP_SIZE]; /* map of available syscalls 0x70 */
+   	__u32 syscall_map_32[SYSCALL_MAP_SIZE]; /* map of available syscalls */
 };
 
 #ifdef __KERNEL__

index b7205e3b7193..8d6e3760ee10 100644
@@ -43,10 +43,10 @@ extern time_t last_rtc_update;
 struct gettimeofday_vars {
 	unsigned long tb_to_xs;
 	unsigned long stamp_xsec;
+	unsigned long tb_orig_stamp;
 };
 
 struct gettimeofday_struct {
-	unsigned long tb_orig_stamp;
 	unsigned long tb_ticks_per_sec;
 	struct gettimeofday_vars vars[2];
 	struct gettimeofday_vars * volatile varp;

83 lines not on this page · raw message