[PATCH v2 1/4] vt: preserve unicode values corresponding to screen characters

From: Nicolas Pitre <nicolas.pitre@linaro.org>
To: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Dave Mielke <Dave@mielke.cc>,
	Samuel Thibault <samuel.thibault@ens-lyon.org>,
	linux-kernel@vger.kernel.org
Subject: [PATCH v2 1/4] vt: preserve unicode values corresponding to screen characters
Date: Sun, 17 Jun 2018 15:07:03 -0400	[thread overview]
Message-ID: <20180617190706.14614-2-nicolas.pitre@linaro.org> (raw)
In-Reply-To: <20180617190706.14614-1-nicolas.pitre@linaro.org>

The vt code translates UTF-8 strings into glyph index values and stores
those glyph values directly in the screen buffer. Because there can only
be at most 512 glyphs, it is impossible to represent most unicode
characters, in which case a default glyph (often '?') is displayed
instead. The original unicode value is then lost.

This patch implements the basic screen buffer handling to preserve unicode
values alongside corresponding display glyphs.  It is not activated by
default, meaning that people not relying on that functionality won't get
the implied overhead.

Signed-off-by: Nicolas Pitre <nico@linaro.org>
Tested-by: Dave Mielke <Dave@mielke.cc>
---
 drivers/tty/vt/vt.c            | 220 +++++++++++++++++++++++++++++++--
 include/linux/console_struct.h |   2 +
 2 files changed, 211 insertions(+), 11 deletions(-)

diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c
index 1eb1a376a0..7b636638b3 100644
--- a/drivers/tty/vt/vt.c
+++ b/drivers/tty/vt/vt.c
@@ -317,6 +317,171 @@ void schedule_console_callback(void)
 	schedule_work(&console_work);
 }
 
+/*
+ * Code to manage unicode-based screen buffers
+ */
+
+#ifdef NO_VC_UNI_SCREEN
+/* this disables and optimizes related code away at compile time */
+#define get_vc_uniscr(vc) NULL
+#else
+#define get_vc_uniscr(vc) vc->vc_uni_screen
+#endif
+
+typedef uint32_t char32_t;
+
+/*
+ * Our screen buffer is preceded by an array of line pointers so that
+ * scrolling only implies some pointer shuffling.
+ */
+struct uni_screen {
+	char32_t *lines[0];
+};
+
+static struct uni_screen *vc_uniscr_alloc(unsigned int cols, unsigned int rows)
+{
+	struct uni_screen *uniscr;
+	void *p;
+	unsigned int memsize, i;
+
+	/* allocate everything in one go */
+	memsize = cols * rows * sizeof(char32_t);
+	memsize += rows * sizeof(char32_t *);
+	p = kmalloc(memsize, GFP_KERNEL);
+	if (!p)
+		return NULL;
+
+	/* initial line pointers */
+	uniscr = p;
+	p = uniscr->lines + rows;
+	for (i = 0; i < rows; i++) {
+		uniscr->lines[i] = p;
+		p += cols * sizeof(char32_t);
+	}
+	return uniscr;
+}
+
+static void vc_uniscr_set(struct vc_data *vc, struct uni_screen *new_uniscr)
+{
+	kfree(vc->vc_uni_screen);
+	vc->vc_uni_screen = new_uniscr;
+}
+
+static void vc_uniscr_putc(struct vc_data *vc, char32_t uc)
+{
+	struct uni_screen *uniscr = get_vc_uniscr(vc);
+
+	if (uniscr)
+		uniscr->lines[vc->vc_y][vc->vc_x] = uc;
+}
+
+static void vc_uniscr_insert(struct vc_data *vc, unsigned int nr)
+{
+	struct uni_screen *uniscr = get_vc_uniscr(vc);
+
+	if (uniscr) {
+		char32_t *ln = uniscr->lines[vc->vc_y];
+		unsigned int x = vc->vc_x, cols = vc->vc_cols;
+
+		memmove(&ln[x + nr], &ln[x], (cols - x - nr) * sizeof(*ln));
+		memset32(&ln[x], ' ', nr);
+	}
+}
+
+static void vc_uniscr_delete(struct vc_data *vc, unsigned int nr)
+{
+	struct uni_screen *uniscr = get_vc_uniscr(vc);
+
+	if (uniscr) {
+		char32_t *ln = uniscr->lines[vc->vc_y];
+		unsigned int x = vc->vc_x, cols = vc->vc_cols;
+
+		memcpy(&ln[x], &ln[x + nr], (cols - x - nr) * sizeof(*ln));
+		memset32(&ln[cols - nr], ' ', nr);
+	}
+}
+
+static void vc_uniscr_clear_line(struct vc_data *vc, unsigned int x,
+				 unsigned int nr)
+{
+	struct uni_screen *uniscr = get_vc_uniscr(vc);
+
+	if (uniscr) {
+		char32_t *ln = uniscr->lines[vc->vc_y];
+
+		memset32(&ln[x], ' ', nr);
+	}
+}
+
+static void vc_uniscr_clear_lines(struct vc_data *vc, unsigned int y,
+				  unsigned int nr)
+{
+	struct uni_screen *uniscr = get_vc_uniscr(vc);
+
+	if (uniscr) {
+		unsigned int cols = vc->vc_cols;
+
+		while (nr--)
+			memset32(uniscr->lines[y++], ' ', cols);
+	}
+}
+
+static void vc_uniscr_scroll(struct vc_data *vc, unsigned int t, unsigned int b,
+			     enum con_scroll dir, unsigned int nr)
+{
+	struct uni_screen *uniscr = get_vc_uniscr(vc);
+
+	if (uniscr) {
+		unsigned int s, d, rescue, clear;
+		char32_t *save[nr];
+
+		s = clear = t;
+		d = t + nr;
+		rescue = b - nr;
+		if (dir == SM_UP) {
+			swap(s, d);
+			swap(clear, rescue);
+		}
+		memcpy(save, uniscr->lines + rescue, nr * sizeof(*save));
+		memmove(uniscr->lines + d, uniscr->lines + s,
+			(b - t - nr) * sizeof(*uniscr->lines));
+		memcpy(uniscr->lines + clear, save, nr * sizeof(*save));
+		vc_uniscr_clear_lines(vc, clear, nr);
+	}
+}
+
+static void vc_uniscr_copy_area(struct uni_screen *dst,
+				unsigned int dst_cols,
+				unsigned int dst_rows,
+				struct uni_screen *src,
+				unsigned int src_cols,
+				unsigned int src_top_row,
+				unsigned int src_bot_row)
+{
+	unsigned int dst_row = 0;
+
+	if (!dst)
+		return;
+
+	while (src_top_row < src_bot_row) {
+		char32_t *src_line = src->lines[src_top_row];
+		char32_t *dst_line = dst->lines[dst_row];
+
+		memcpy(dst_line, src_line, src_cols * sizeof(char32_t));
+		if (dst_cols - src_cols)
+			memset32(dst_line + src_cols, ' ', dst_cols - src_cols);
+		src_top_row++;
+		dst_row++;
+	}
+	while (dst_row < dst_rows) {
+		char32_t *dst_line = dst->lines[dst_row];
+
+		memset32(dst_line, ' ', dst_cols);
+		dst_row++;
+	}
+}
+
+
 static void con_scroll(struct vc_data *vc, unsigned int t, unsigned int b,
 		enum con_scroll dir, unsigned int nr)
 {
@@ -326,6 +491,7 @@ static void con_scroll(struct vc_data *vc, unsigned int t, unsigned int b,
 		nr = b - t - 1;
 	if (b > vc->vc_rows || t >= b || nr < 1)
 		return;
+	vc_uniscr_scroll(vc, t, b, dir, nr);
 	if (con_is_visible(vc) && vc->vc_sw->con_scroll(vc, t, b, dir, nr))
 		return;
 
@@ -533,6 +699,7 @@ static void insert_char(struct vc_data *vc, unsigned int nr)
 {
 	unsigned short *p = (unsigned short *) vc->vc_pos;
 
+	vc_uniscr_insert(vc, nr);
 	scr_memmovew(p + nr, p, (vc->vc_cols - vc->vc_x - nr) * 2);
 	scr_memsetw(p, vc->vc_video_erase_char, nr * 2);
 	vc->vc_need_wrap = 0;
@@ -545,6 +712,7 @@ static void delete_char(struct vc_data *vc, unsigned int nr)
 {
 	unsigned short *p = (unsigned short *) vc->vc_pos;
 
+	vc_uniscr_delete(vc, nr);
 	scr_memcpyw(p, p + nr, (vc->vc_cols - vc->vc_x - nr) * 2);
 	scr_memsetw(p + vc->vc_cols - vc->vc_x - nr, vc->vc_video_erase_char,
 			nr * 2);
@@ -845,10 +1013,11 @@ static int vc_do_resize(struct tty_struct *tty, struct vc_data *vc,
 {
 	unsigned long old_origin, new_origin, new_scr_end, rlth, rrem, err = 0;
 	unsigned long end;
-	unsigned int old_rows, old_row_size;
+	unsigned int old_rows, old_row_size, first_copied_row;
 	unsigned int new_cols, new_rows, new_row_size, new_screen_size;
 	unsigned int user;
 	unsigned short *newscreen;
+	struct uni_screen *new_uniscr = NULL;
 
 	WARN_CONSOLE_UNLOCKED();
 
@@ -875,6 +1044,14 @@ static int vc_do_resize(struct tty_struct *tty, struct vc_data *vc,
 	if (!newscreen)
 		return -ENOMEM;
 
+	if (get_vc_uniscr(vc)) {
+		new_uniscr = vc_uniscr_alloc(new_cols, new_rows);
+		if (!new_uniscr) {
+			kfree(newscreen);
+			return -ENOMEM;
+		}
+	}
+
 	if (vc == sel_cons)
 		clear_selection();
 
@@ -884,6 +1061,7 @@ static int vc_do_resize(struct tty_struct *tty, struct vc_data *vc,
 	err = resize_screen(vc, new_cols, new_rows, user);
 	if (err) {
 		kfree(newscreen);
+		kfree(new_uniscr);
 		return err;
 	}
 
@@ -904,18 +1082,24 @@ static int vc_do_resize(struct tty_struct *tty, struct vc_data *vc,
 			 * Cursor near the bottom, copy contents from the
 			 * bottom of buffer
 			 */
-			old_origin += (old_rows - new_rows) * old_row_size;
+			first_copied_row = (old_rows - new_rows);
 		} else {
 			/*
 			 * Cursor is in no man's land, copy 1/2 screenful
 			 * from the top and bottom of cursor position
 			 */
-			old_origin += (vc->vc_y - new_rows/2) * old_row_size;
+			first_copied_row = (vc->vc_y - new_rows/2);
 		}
-	}
-
+		old_origin += first_copied_row * old_row_size;
+	} else
+		first_copied_row = 0;
 	end = old_origin + old_row_size * min(old_rows, new_rows);
 
+	vc_uniscr_copy_area(new_uniscr, new_cols, new_rows,
+			    get_vc_uniscr(vc), rlth/2, first_copied_row,
+			    min(old_rows, new_rows));
+	vc_uniscr_set(vc, new_uniscr);
+
 	update_attr(vc);
 
 	while (old_origin < end) {
@@ -1013,6 +1197,7 @@ struct vc_data *vc_deallocate(unsigned int currcons)
 		vc->vc_sw->con_deinit(vc);
 		put_pid(vc->vt_pid);
 		module_put(vc->vc_sw->owner);
+		vc_uniscr_set(vc, NULL);
 		kfree(vc->vc_screenbuf);
 		vc_cons[currcons].d = NULL;
 	}
@@ -1171,15 +1356,22 @@ static void csi_J(struct vc_data *vc, int vpar)
 
 	switch (vpar) {
 		case 0:	/* erase from cursor to end of display */
+			vc_uniscr_clear_line(vc, vc->vc_x,
+					     vc->vc_cols - vc->vc_x);
+			vc_uniscr_clear_lines(vc, vc->vc_y + 1,
+					      vc->vc_rows - vc->vc_y - 1);
 			count = (vc->vc_scr_end - vc->vc_pos) >> 1;
 			start = (unsigned short *)vc->vc_pos;
 			break;
 		case 1:	/* erase from start to cursor */
+			vc_uniscr_clear_line(vc, 0, vc->vc_x + 1);
+			vc_uniscr_clear_lines(vc, 0, vc->vc_y);
 			count = ((vc->vc_pos - vc->vc_origin) >> 1) + 1;
 			start = (unsigned short *)vc->vc_origin;
 			break;
 		case 2: /* erase whole display */
 		case 3: /* (and scrollback buffer later) */
+			vc_uniscr_clear_lines(vc, 0, vc->vc_rows);
 			count = vc->vc_cols * vc->vc_rows;
 			start = (unsigned short *)vc->vc_origin;
 			break;
@@ -1200,25 +1392,27 @@ static void csi_J(struct vc_data *vc, int vpar)
 static void csi_K(struct vc_data *vc, int vpar)
 {
 	unsigned int count;
-	unsigned short * start;
+	unsigned short *start = (unsigned short *)vc->vc_pos;
+	int offset;
 
 	switch (vpar) {
 		case 0:	/* erase from cursor to end of line */
+			offset = 0;
 			count = vc->vc_cols - vc->vc_x;
-			start = (unsigned short *)vc->vc_pos;
 			break;
 		case 1:	/* erase from start of line to cursor */
-			start = (unsigned short *)(vc->vc_pos - (vc->vc_x << 1));
+			offset = -vc->vc_x;
 			count = vc->vc_x + 1;
 			break;
 		case 2: /* erase whole line */
-			start = (unsigned short *)(vc->vc_pos - (vc->vc_x << 1));
+			offset = -vc->vc_x;
 			count = vc->vc_cols;
 			break;
 		default:
 			return;
 	}
-	scr_memsetw(start, vc->vc_video_erase_char, 2 * count);
+	vc_uniscr_clear_line(vc, vc->vc_x + offset, count);
+	scr_memsetw(start + offset, vc->vc_video_erase_char, 2 * count);
 	vc->vc_need_wrap = 0;
 	if (con_should_update(vc))
 		do_update_region(vc, (unsigned long) start, count);
@@ -1232,6 +1426,7 @@ static void csi_X(struct vc_data *vc, int vpar) /* erase the following vpar posi
 		vpar++;
 	count = (vpar > vc->vc_cols - vc->vc_x) ? (vc->vc_cols - vc->vc_x) : vpar;
 
+	vc_uniscr_clear_line(vc, vc->vc_x, count);
 	scr_memsetw((unsigned short *)vc->vc_pos, vc->vc_video_erase_char, 2 * count);
 	if (con_should_update(vc))
 		vc->vc_sw->con_clear(vc, vc->vc_y, vc->vc_x, 1, count);
@@ -2188,7 +2383,7 @@ static void con_flush(struct vc_data *vc, unsigned long draw_from,
 /* acquires console_lock */
 static int do_con_write(struct tty_struct *tty, const unsigned char *buf, int count)
 {
-	int c, tc, ok, n = 0, draw_x = -1;
+	int c, next_c, tc, ok, n = 0, draw_x = -1;
 	unsigned int currcons;
 	unsigned long draw_from = 0, draw_to = 0;
 	struct vc_data *vc;
@@ -2382,6 +2577,7 @@ static int do_con_write(struct tty_struct *tty, const unsigned char *buf, int co
 				con_flush(vc, draw_from, draw_to, &draw_x);
 			}
 
+			next_c = c;
 			while (1) {
 				if (vc->vc_need_wrap || vc->vc_decim)
 					con_flush(vc, draw_from, draw_to,
@@ -2392,6 +2588,7 @@ static int do_con_write(struct tty_struct *tty, const unsigned char *buf, int co
 				}
 				if (vc->vc_decim)
 					insert_char(vc, 1);
+				vc_uniscr_putc(vc, next_c);
 				scr_writew(himask ?
 					     ((vc_attr << 8) & ~himask) + ((tc & 0x100) ? himask : 0) + (tc & 0xff) :
 					     (vc_attr << 8) + tc,
@@ -2412,6 +2609,7 @@ static int do_con_write(struct tty_struct *tty, const unsigned char *buf, int co
 
 				tc = conv_uni_to_pc(vc, ' '); /* A space is printed in the second column */
 				if (tc < 0) tc = ' ';
+				next_c = ' ';
 			}
 			notify_write(vc, c);
 
diff --git a/include/linux/console_struct.h b/include/linux/console_struct.h
index c0ec478ea5..2c8d323989 100644
--- a/include/linux/console_struct.h
+++ b/include/linux/console_struct.h
@@ -19,6 +19,7 @@
 
 struct vt_struct;
 struct uni_pagedir;
+struct uni_screen;
 
 #define NPAR 16
 
@@ -140,6 +141,7 @@ struct vc_data {
 	struct vc_data **vc_display_fg;		/* [!] Ptr to var holding fg console for this display */
 	struct uni_pagedir *vc_uni_pagedir;
 	struct uni_pagedir **vc_uni_pagedir_loc; /* [!] Location of uni_pagedir variable for this console */
+	struct uni_screen *vc_uni_screen;	/* unicode screen content */
 	bool vc_panic_force_write; /* when oops/panic this VC can accept forced output/blanking */
 	/* additional information is in vt_kern.h */
 };
-- 
2.17.1

